Upload checkpoint-165: Vietnamese Traffic QA - Qwen3-VL-4B fine-tuned on dashcam videos
Browse files- added_tokens.json +28 -0
- chat_template.jinja +120 -0
- config.json +68 -0
- generation_config.json +13 -0
- global_step163/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- global_step163/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt +3 -0
- global_step163/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt +3 -0
- global_step163/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt +3 -0
- global_step163/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt +3 -0
- global_step163/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt +3 -0
- global_step163/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt +3 -0
- global_step163/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt +3 -0
- global_step163/mp_rank_00_model_states.pt +3 -0
- latest +1 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +722 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +31 -0
- tokenizer_config.json +240 -0
- trainer_state.json +1189 -0
- training_args.bin +3 -0
- vocab.json +0 -0
- zero_to_fp32.py +760 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{%- if messages[0].content is string %}
|
| 5 |
+
{{- messages[0].content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for content in messages[0].content %}
|
| 8 |
+
{%- if 'text' in content %}
|
| 9 |
+
{{- content.text }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- '\n\n' }}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "\n" }}
|
| 18 |
+
{{- tool | tojson }}
|
| 19 |
+
{%- endfor %}
|
| 20 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{%- if messages[0].role == 'system' %}
|
| 23 |
+
{{- '<|im_start|>system\n' }}
|
| 24 |
+
{%- if messages[0].content is string %}
|
| 25 |
+
{{- messages[0].content }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- for content in messages[0].content %}
|
| 28 |
+
{%- if 'text' in content %}
|
| 29 |
+
{{- content.text }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_end|>\n' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set image_count = namespace(value=0) %}
|
| 37 |
+
{%- set video_count = namespace(value=0) %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.role == "user" %}
|
| 40 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 41 |
+
{%- if message.content is string %}
|
| 42 |
+
{{- message.content }}
|
| 43 |
+
{%- else %}
|
| 44 |
+
{%- for content in message.content %}
|
| 45 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 46 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 47 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 48 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 49 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 50 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 51 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 52 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 53 |
+
{%- elif 'text' in content %}
|
| 54 |
+
{{- content.text }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{{- '<|im_end|>\n' }}
|
| 59 |
+
{%- elif message.role == "assistant" %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 61 |
+
{%- if message.content is string %}
|
| 62 |
+
{{- message.content }}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- for content_item in message.content %}
|
| 65 |
+
{%- if 'text' in content_item %}
|
| 66 |
+
{{- content_item.text }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- endfor %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if message.tool_calls %}
|
| 71 |
+
{%- for tool_call in message.tool_calls %}
|
| 72 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 73 |
+
{{- '\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if tool_call.function %}
|
| 76 |
+
{%- set tool_call = tool_call.function %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 79 |
+
{{- tool_call.name }}
|
| 80 |
+
{{- '", "arguments": ' }}
|
| 81 |
+
{%- if tool_call.arguments is string %}
|
| 82 |
+
{{- tool_call.arguments }}
|
| 83 |
+
{%- else %}
|
| 84 |
+
{{- tool_call.arguments | tojson }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '}\n</tool_call>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '<|im_end|>\n' }}
|
| 90 |
+
{%- elif message.role == "tool" %}
|
| 91 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 92 |
+
{{- '<|im_start|>user' }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '\n<tool_response>\n' }}
|
| 95 |
+
{%- if message.content is string %}
|
| 96 |
+
{{- message.content }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- for content in message.content %}
|
| 99 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 100 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 101 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 102 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 103 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 104 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 105 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 106 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 107 |
+
{%- elif 'text' in content %}
|
| 108 |
+
{{- content.text }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endfor %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '\n</tool_response>' }}
|
| 113 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 114 |
+
{{- '<|im_end|>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endfor %}
|
| 118 |
+
{%- if add_generation_prompt %}
|
| 119 |
+
{{- '<|im_start|>assistant\n' }}
|
| 120 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"image_token_id": 151655,
|
| 8 |
+
"model_type": "qwen3_vl",
|
| 9 |
+
"pad_token_id": 151643,
|
| 10 |
+
"text_config": {
|
| 11 |
+
"attention_bias": false,
|
| 12 |
+
"attention_dropout": 0.0,
|
| 13 |
+
"bos_token_id": 151643,
|
| 14 |
+
"dtype": "bfloat16",
|
| 15 |
+
"eos_token_id": 151645,
|
| 16 |
+
"head_dim": 128,
|
| 17 |
+
"hidden_act": "silu",
|
| 18 |
+
"hidden_size": 2560,
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 9728,
|
| 21 |
+
"max_position_embeddings": 262144,
|
| 22 |
+
"model_type": "qwen3_vl_text",
|
| 23 |
+
"num_attention_heads": 32,
|
| 24 |
+
"num_hidden_layers": 36,
|
| 25 |
+
"num_key_value_heads": 8,
|
| 26 |
+
"rms_norm_eps": 1e-06,
|
| 27 |
+
"rope_scaling": {
|
| 28 |
+
"mrope_interleaved": true,
|
| 29 |
+
"mrope_section": [
|
| 30 |
+
24,
|
| 31 |
+
20,
|
| 32 |
+
20
|
| 33 |
+
],
|
| 34 |
+
"rope_type": "default"
|
| 35 |
+
},
|
| 36 |
+
"rope_theta": 5000000,
|
| 37 |
+
"tie_word_embeddings": true,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 151936
|
| 40 |
+
},
|
| 41 |
+
"tie_word_embeddings": true,
|
| 42 |
+
"transformers_version": "4.57.1",
|
| 43 |
+
"use_cache": false,
|
| 44 |
+
"video_token_id": 151656,
|
| 45 |
+
"vision_config": {
|
| 46 |
+
"deepstack_visual_indexes": [
|
| 47 |
+
5,
|
| 48 |
+
11,
|
| 49 |
+
17
|
| 50 |
+
],
|
| 51 |
+
"depth": 24,
|
| 52 |
+
"dtype": "bfloat16",
|
| 53 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 54 |
+
"hidden_size": 1024,
|
| 55 |
+
"in_channels": 3,
|
| 56 |
+
"initializer_range": 0.02,
|
| 57 |
+
"intermediate_size": 4096,
|
| 58 |
+
"model_type": "qwen3_vl",
|
| 59 |
+
"num_heads": 16,
|
| 60 |
+
"num_position_embeddings": 2304,
|
| 61 |
+
"out_hidden_size": 2560,
|
| 62 |
+
"patch_size": 16,
|
| 63 |
+
"spatial_merge_size": 2,
|
| 64 |
+
"temporal_patch_size": 2
|
| 65 |
+
},
|
| 66 |
+
"vision_end_token_id": 151653,
|
| 67 |
+
"vision_start_token_id": 151652
|
| 68 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.1"
|
| 13 |
+
}
|
global_step163/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd0855d3a252aaea612238e5cc038004e7deadf6e224909230f5709f2de061d9
|
| 3 |
+
size 6656740748
|
global_step163/bf16_zero_pp_rank_1_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99312273d90767c120ac3da8290dad98204e26f730eb20573f4c61c119449a90
|
| 3 |
+
size 6656733900
|
global_step163/bf16_zero_pp_rank_2_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:57557df63d8e9643f431f1dd7e9635876f8ac0c46d77a2dbc4a8088256ca8a08
|
| 3 |
+
size 6656735500
|
global_step163/bf16_zero_pp_rank_3_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:507d59203197443559ff4981c8ab9eadf7c1bf2281cdb0742292ac918a549be5
|
| 3 |
+
size 6656735500
|
global_step163/bf16_zero_pp_rank_4_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9909baaf8c569bcc7d8220f236d91498fc3f32653799f99040ad1c5017969d3e
|
| 3 |
+
size 6656734796
|
global_step163/bf16_zero_pp_rank_5_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:30f71862dae568a691e14ec38364c36bb93215e0b99230084304d70072536451
|
| 3 |
+
size 6656736332
|
global_step163/bf16_zero_pp_rank_6_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c43274ceb91d8960617f795560dc9ef9935675b5e383eab5853b6fff8743e7f4
|
| 3 |
+
size 6656737484
|
global_step163/bf16_zero_pp_rank_7_mp_rank_00_optim_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12edbd9c5732dc67fb7cabf56d77482d170ab5a14b7dca5cfa70791f7fa8bf66
|
| 3 |
+
size 6656736844
|
global_step163/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85675dec6b328193efe48de32f7b5f75c53ec17378b400525da976557ad05601
|
| 3 |
+
size 8875847032
|
latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step163
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c93feb470ed96a77058f49578cdedf8ffb8980d0b68e88d0dea84253858fdf8
|
| 3 |
+
size 4990497880
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16c8d8d2d49b5c01b67c6fe02c00506f01cac4d54c53cdc85e9b28700fa0a1fe
|
| 3 |
+
size 4663133960
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,722 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 4437815808,
|
| 4 |
+
"total_size": 9653543936
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 11 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 13 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 19 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 23 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 31 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 35 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 41 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 43 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 47 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 53 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 55 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 59 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 63 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 67 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 71 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 75 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 77 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 79 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 83 |
+
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 85 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 87 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 89 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 91 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 95 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 97 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 98 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 99 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 101 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 102 |
+
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 103 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 107 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 110 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 111 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 112 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 117 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 118 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 119 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 121 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 122 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 123 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 128 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 129 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 130 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 132 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 133 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 134 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 139 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 140 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 141 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 143 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 145 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 147 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 149 |
+
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 151 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 155 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 156 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 162 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 163 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 166 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 167 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 173 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 174 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 175 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 176 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 177 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 178 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 184 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 185 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 186 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 187 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 188 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 189 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 190 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 191 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 192 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 193 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 194 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 195 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 196 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 197 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 198 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 199 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 200 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 201 |
+
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 202 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 203 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 204 |
+
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 205 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 206 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 207 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 208 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 209 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 210 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 211 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 212 |
+
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 213 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 214 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 215 |
+
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 216 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 217 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 218 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 219 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 220 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 221 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 222 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 223 |
+
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 224 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 225 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 226 |
+
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 227 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 228 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 229 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 230 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 231 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 232 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 233 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 234 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 235 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 236 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 237 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 238 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 239 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 240 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 241 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 242 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 243 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 244 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 245 |
+
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 246 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 247 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 248 |
+
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 249 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 250 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 251 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 252 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 253 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 254 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 255 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 256 |
+
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 257 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 258 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 259 |
+
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 260 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 261 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 262 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 263 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 265 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 267 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 269 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 271 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 274 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 275 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 276 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 277 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 278 |
+
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 279 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 280 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 281 |
+
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 282 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 283 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 284 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 285 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 286 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 287 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 288 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 289 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 290 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 291 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 292 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 293 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 294 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 295 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 298 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 299 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 300 |
+
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 301 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 302 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 303 |
+
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 304 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 305 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 306 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 309 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 310 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 316 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 317 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 320 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 321 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 327 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 328 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 329 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
|
| 330 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
|
| 331 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
|
| 332 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 333 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
|
| 337 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
| 338 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
| 339 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 341 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 343 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 347 |
+
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 349 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 351 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 353 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 355 |
+
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 359 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 361 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 363 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 365 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 367 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 371 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 375 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 383 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 387 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 394 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.language_model.norm.weight": "model-00002-of-00002.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 533 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
|
| 537 |
+
"model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 541 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 545 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
|
| 549 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 553 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
|
| 561 |
+
"model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 565 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 569 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
|
| 573 |
+
"model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 577 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 581 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
|
| 585 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 589 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 593 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 611 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 612 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 613 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 615 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 616 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
|
| 631 |
+
"model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 634 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 635 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 637 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 638 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 639 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 641 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 642 |
+
"model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
|
| 643 |
+
"model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
|
| 645 |
+
"model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 646 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 647 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 648 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 649 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 651 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 652 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 653 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 654 |
+
"model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
|
| 657 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 659 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 660 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 661 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 663 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 664 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 665 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
|
| 667 |
+
"model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 671 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 672 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 673 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 674 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
|
| 681 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 683 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 685 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 686 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 687 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 689 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 690 |
+
"model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
|
| 691 |
+
"model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
|
| 693 |
+
"model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 694 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 695 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 697 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 698 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
|
| 699 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
|
| 700 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 701 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 702 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 703 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 704 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
|
| 705 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
|
| 706 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 707 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 708 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 709 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
|
| 711 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
|
| 712 |
+
"model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
|
| 713 |
+
"model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
|
| 714 |
+
"model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
|
| 715 |
+
"model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
|
| 716 |
+
"model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
|
| 717 |
+
"model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
|
| 719 |
+
"model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
|
| 720 |
+
"model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
|
| 721 |
+
}
|
| 722 |
+
}
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74386f26f36ed67f56395205881e5db2d0c28ffcbeed50dd95b28771d2dac588
|
| 3 |
+
size 15984
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41c88f9de084200454883a13c3717941ea3fd433e2f8735507fc30611f9c5501
|
| 3 |
+
size 15984
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:965b00d4cb4710ebab57c8787b9925bb3f77b8eeba94a186ec4bc1c2f326ef3f
|
| 3 |
+
size 15984
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5dc374b8b9a4c45c950f9d136feab85a767081fa59f0c7d68ed3a62060c4949
|
| 3 |
+
size 15984
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c7c212fb779217f1edac0baf44f67b608eefc1e0e4e3f5a9dd7eb557032c1bc
|
| 3 |
+
size 15984
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86e1effd626ce1e95dd68a0c8089fe19218f2b24dfe9e45ed2cab1c0ebc10ba1
|
| 3 |
+
size 15984
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:799cc83f60dfc1c4243cfd6403592112414a2eec494e6832f10221c96ff62c20
|
| 3 |
+
size 15984
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:586777c398770c3255d3a1f48c7fef44ea9d89117c627c9ea490e16bfd9a49ba
|
| 3 |
+
size 15984
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1b125d691e44399b23e69d47a845899e692facd648b0fc3fafd2285715956cc9
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 8192,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1189 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.761904761904762,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 165,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.016931216931216932,
|
| 14 |
+
"grad_norm": 2322.343994140625,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.2269,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.033862433862433865,
|
| 21 |
+
"grad_norm": 12.033977508544922,
|
| 22 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 23 |
+
"loss": 1.2059,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.050793650793650794,
|
| 28 |
+
"grad_norm": 10.809624671936035,
|
| 29 |
+
"learning_rate": 6.666666666666667e-06,
|
| 30 |
+
"loss": 1.2198,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.06772486772486773,
|
| 35 |
+
"grad_norm": 5.77828311920166,
|
| 36 |
+
"learning_rate": 1e-05,
|
| 37 |
+
"loss": 1.0599,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08465608465608465,
|
| 42 |
+
"grad_norm": 5.281270503997803,
|
| 43 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 44 |
+
"loss": 0.9754,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.10158730158730159,
|
| 49 |
+
"grad_norm": 5.149123191833496,
|
| 50 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 51 |
+
"loss": 0.9476,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.11851851851851852,
|
| 56 |
+
"grad_norm": 6.636379718780518,
|
| 57 |
+
"learning_rate": 2e-05,
|
| 58 |
+
"loss": 1.0585,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.13544973544973546,
|
| 63 |
+
"grad_norm": 3.8481030464172363,
|
| 64 |
+
"learning_rate": 1.9998370105646414e-05,
|
| 65 |
+
"loss": 0.9413,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.1523809523809524,
|
| 70 |
+
"grad_norm": 3.835693120956421,
|
| 71 |
+
"learning_rate": 1.999348095389677e-05,
|
| 72 |
+
"loss": 0.8891,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.1693121693121693,
|
| 77 |
+
"grad_norm": 2.8596138954162598,
|
| 78 |
+
"learning_rate": 1.998533413851124e-05,
|
| 79 |
+
"loss": 0.8795,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.18624338624338624,
|
| 84 |
+
"grad_norm": 2.8256287574768066,
|
| 85 |
+
"learning_rate": 1.9973932315179502e-05,
|
| 86 |
+
"loss": 0.8446,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.20317460317460317,
|
| 91 |
+
"grad_norm": 5.52194356918335,
|
| 92 |
+
"learning_rate": 1.9959279200655044e-05,
|
| 93 |
+
"loss": 0.8027,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.2201058201058201,
|
| 98 |
+
"grad_norm": 2.0485758781433105,
|
| 99 |
+
"learning_rate": 1.9941379571543597e-05,
|
| 100 |
+
"loss": 0.7859,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.23703703703703705,
|
| 105 |
+
"grad_norm": 2.2072129249572754,
|
| 106 |
+
"learning_rate": 1.9920239262746045e-05,
|
| 107 |
+
"loss": 0.7766,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.25396825396825395,
|
| 112 |
+
"grad_norm": 2.154557943344116,
|
| 113 |
+
"learning_rate": 1.9895865165556375e-05,
|
| 114 |
+
"loss": 0.7366,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.2708994708994709,
|
| 119 |
+
"grad_norm": 1.9130762815475464,
|
| 120 |
+
"learning_rate": 1.9868265225415263e-05,
|
| 121 |
+
"loss": 0.7432,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2878306878306878,
|
| 126 |
+
"grad_norm": 1.6504809856414795,
|
| 127 |
+
"learning_rate": 1.9837448439320027e-05,
|
| 128 |
+
"loss": 0.6905,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.3047619047619048,
|
| 133 |
+
"grad_norm": 1.7797411680221558,
|
| 134 |
+
"learning_rate": 1.9803424852891803e-05,
|
| 135 |
+
"loss": 0.6799,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3216931216931217,
|
| 140 |
+
"grad_norm": 1.7259820699691772,
|
| 141 |
+
"learning_rate": 1.976620555710087e-05,
|
| 142 |
+
"loss": 0.6706,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.3386243386243386,
|
| 147 |
+
"grad_norm": 1.4618961811065674,
|
| 148 |
+
"learning_rate": 1.9725802684651235e-05,
|
| 149 |
+
"loss": 0.6687,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.35555555555555557,
|
| 154 |
+
"grad_norm": 1.5048692226409912,
|
| 155 |
+
"learning_rate": 1.9682229406025635e-05,
|
| 156 |
+
"loss": 0.6762,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.3724867724867725,
|
| 161 |
+
"grad_norm": 1.4504609107971191,
|
| 162 |
+
"learning_rate": 1.963549992519223e-05,
|
| 163 |
+
"loss": 0.6631,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.38941798941798944,
|
| 168 |
+
"grad_norm": 1.4441351890563965,
|
| 169 |
+
"learning_rate": 1.9585629474974413e-05,
|
| 170 |
+
"loss": 0.6394,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.40634920634920635,
|
| 175 |
+
"grad_norm": 1.2873355150222778,
|
| 176 |
+
"learning_rate": 1.953263431208523e-05,
|
| 177 |
+
"loss": 0.6279,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.42328042328042326,
|
| 182 |
+
"grad_norm": 1.4676573276519775,
|
| 183 |
+
"learning_rate": 1.9476531711828027e-05,
|
| 184 |
+
"loss": 0.6238,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.4402116402116402,
|
| 189 |
+
"grad_norm": 1.3487250804901123,
|
| 190 |
+
"learning_rate": 1.9417339962465084e-05,
|
| 191 |
+
"loss": 0.6253,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.45714285714285713,
|
| 196 |
+
"grad_norm": 23.1207275390625,
|
| 197 |
+
"learning_rate": 1.935507835925601e-05,
|
| 198 |
+
"loss": 0.6166,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.4740740740740741,
|
| 203 |
+
"grad_norm": 1.408158540725708,
|
| 204 |
+
"learning_rate": 1.9289767198167918e-05,
|
| 205 |
+
"loss": 0.5644,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.491005291005291,
|
| 210 |
+
"grad_norm": 1.199977159500122,
|
| 211 |
+
"learning_rate": 1.9221427769259333e-05,
|
| 212 |
+
"loss": 0.5865,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.5079365079365079,
|
| 217 |
+
"grad_norm": 1.1895148754119873,
|
| 218 |
+
"learning_rate": 1.9150082349740123e-05,
|
| 219 |
+
"loss": 0.5619,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.5248677248677248,
|
| 224 |
+
"grad_norm": 1.1904869079589844,
|
| 225 |
+
"learning_rate": 1.9075754196709574e-05,
|
| 226 |
+
"loss": 0.5642,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5417989417989418,
|
| 231 |
+
"grad_norm": 1.4911994934082031,
|
| 232 |
+
"learning_rate": 1.899846753957507e-05,
|
| 233 |
+
"loss": 0.5684,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5587301587301587,
|
| 238 |
+
"grad_norm": 1.2807954549789429,
|
| 239 |
+
"learning_rate": 1.8918247572153822e-05,
|
| 240 |
+
"loss": 0.532,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.5756613756613757,
|
| 245 |
+
"grad_norm": 1.1882894039154053,
|
| 246 |
+
"learning_rate": 1.883512044446023e-05,
|
| 247 |
+
"loss": 0.5527,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.5925925925925926,
|
| 252 |
+
"grad_norm": 1.3212125301361084,
|
| 253 |
+
"learning_rate": 1.8749113254181498e-05,
|
| 254 |
+
"loss": 0.5621,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.6095238095238096,
|
| 259 |
+
"grad_norm": 1.4091153144836426,
|
| 260 |
+
"learning_rate": 1.866025403784439e-05,
|
| 261 |
+
"loss": 0.5205,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.6264550264550265,
|
| 266 |
+
"grad_norm": 1.1614974737167358,
|
| 267 |
+
"learning_rate": 1.8568571761675893e-05,
|
| 268 |
+
"loss": 0.5181,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6433862433862434,
|
| 273 |
+
"grad_norm": 1.0888781547546387,
|
| 274 |
+
"learning_rate": 1.8474096312160866e-05,
|
| 275 |
+
"loss": 0.5359,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.6603174603174603,
|
| 280 |
+
"grad_norm": 1.303357720375061,
|
| 281 |
+
"learning_rate": 1.837685848629965e-05,
|
| 282 |
+
"loss": 0.5256,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.6772486772486772,
|
| 287 |
+
"grad_norm": 1.1001622676849365,
|
| 288 |
+
"learning_rate": 1.827688998156891e-05,
|
| 289 |
+
"loss": 0.5277,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.6941798941798942,
|
| 294 |
+
"grad_norm": 16.82403564453125,
|
| 295 |
+
"learning_rate": 1.817422338558892e-05,
|
| 296 |
+
"loss": 0.5301,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.7111111111111111,
|
| 301 |
+
"grad_norm": 1.2562721967697144,
|
| 302 |
+
"learning_rate": 1.8068892165500704e-05,
|
| 303 |
+
"loss": 0.5019,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.728042328042328,
|
| 308 |
+
"grad_norm": 1.143244981765747,
|
| 309 |
+
"learning_rate": 1.796093065705644e-05,
|
| 310 |
+
"loss": 0.5098,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.744973544973545,
|
| 315 |
+
"grad_norm": 1.2346585988998413,
|
| 316 |
+
"learning_rate": 1.7850374053426725e-05,
|
| 317 |
+
"loss": 0.5079,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.7619047619047619,
|
| 322 |
+
"grad_norm": 1.292527675628662,
|
| 323 |
+
"learning_rate": 1.7737258393728363e-05,
|
| 324 |
+
"loss": 0.4987,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.7788359788359789,
|
| 329 |
+
"grad_norm": 1.0964988470077515,
|
| 330 |
+
"learning_rate": 1.7621620551276366e-05,
|
| 331 |
+
"loss": 0.52,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.7957671957671958,
|
| 336 |
+
"grad_norm": 1.3093878030776978,
|
| 337 |
+
"learning_rate": 1.7503498221564026e-05,
|
| 338 |
+
"loss": 0.4911,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.8126984126984127,
|
| 343 |
+
"grad_norm": 1.2538305521011353,
|
| 344 |
+
"learning_rate": 1.7382929909974988e-05,
|
| 345 |
+
"loss": 0.4805,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.8296296296296296,
|
| 350 |
+
"grad_norm": 1.5297569036483765,
|
| 351 |
+
"learning_rate": 1.725995491923131e-05,
|
| 352 |
+
"loss": 0.4834,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.8465608465608465,
|
| 357 |
+
"grad_norm": 1.126209020614624,
|
| 358 |
+
"learning_rate": 1.7134613336581602e-05,
|
| 359 |
+
"loss": 0.474,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.8634920634920635,
|
| 364 |
+
"grad_norm": 1.2999428510665894,
|
| 365 |
+
"learning_rate": 1.7006946020733426e-05,
|
| 366 |
+
"loss": 0.4662,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.8804232804232804,
|
| 371 |
+
"grad_norm": 3.900702714920044,
|
| 372 |
+
"learning_rate": 1.6876994588534234e-05,
|
| 373 |
+
"loss": 0.4728,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.8973544973544973,
|
| 378 |
+
"grad_norm": 1.1961653232574463,
|
| 379 |
+
"learning_rate": 1.6744801401405138e-05,
|
| 380 |
+
"loss": 0.4638,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.9142857142857143,
|
| 385 |
+
"grad_norm": 1.1492871046066284,
|
| 386 |
+
"learning_rate": 1.6610409551532006e-05,
|
| 387 |
+
"loss": 0.4608,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.9312169312169312,
|
| 392 |
+
"grad_norm": 1.1923617124557495,
|
| 393 |
+
"learning_rate": 1.647386284781828e-05,
|
| 394 |
+
"loss": 0.4742,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.9481481481481482,
|
| 399 |
+
"grad_norm": 1.0757859945297241,
|
| 400 |
+
"learning_rate": 1.6335205801604242e-05,
|
| 401 |
+
"loss": 0.4757,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.9650793650793651,
|
| 406 |
+
"grad_norm": 1.0793986320495605,
|
| 407 |
+
"learning_rate": 1.6194483612157232e-05,
|
| 408 |
+
"loss": 0.4543,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.982010582010582,
|
| 413 |
+
"grad_norm": 1.0309922695159912,
|
| 414 |
+
"learning_rate": 1.6051742151937655e-05,
|
| 415 |
+
"loss": 0.4637,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.9989417989417989,
|
| 420 |
+
"grad_norm": 1.0178518295288086,
|
| 421 |
+
"learning_rate": 1.590702795164551e-05,
|
| 422 |
+
"loss": 0.4845,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.0,
|
| 427 |
+
"grad_norm": 1.0178518295288086,
|
| 428 |
+
"learning_rate": 1.57603881850524e-05,
|
| 429 |
+
"loss": 0.4151,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 1.016931216931217,
|
| 434 |
+
"grad_norm": 6.670537948608398,
|
| 435 |
+
"learning_rate": 1.5611870653623826e-05,
|
| 436 |
+
"loss": 0.4583,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 1.0338624338624338,
|
| 441 |
+
"grad_norm": 1.1750141382217407,
|
| 442 |
+
"learning_rate": 1.546152377093697e-05,
|
| 443 |
+
"loss": 0.4378,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.0507936507936508,
|
| 448 |
+
"grad_norm": 1.258583903312683,
|
| 449 |
+
"learning_rate": 1.530939654689887e-05,
|
| 450 |
+
"loss": 0.4698,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.0677248677248676,
|
| 455 |
+
"grad_norm": 1.1863641738891602,
|
| 456 |
+
"learning_rate": 1.515553857177022e-05,
|
| 457 |
+
"loss": 0.4493,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.0846560846560847,
|
| 462 |
+
"grad_norm": 1.2087653875350952,
|
| 463 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 464 |
+
"loss": 0.4495,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.1015873015873017,
|
| 469 |
+
"grad_norm": 1.1390602588653564,
|
| 470 |
+
"learning_rate": 1.4842831533876196e-05,
|
| 471 |
+
"loss": 0.4628,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.1185185185185185,
|
| 476 |
+
"grad_norm": 1.0523955821990967,
|
| 477 |
+
"learning_rate": 1.4684084406997903e-05,
|
| 478 |
+
"loss": 0.4444,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.1354497354497355,
|
| 483 |
+
"grad_norm": 1.3320904970169067,
|
| 484 |
+
"learning_rate": 1.4523810367574271e-05,
|
| 485 |
+
"loss": 0.4487,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.1523809523809523,
|
| 490 |
+
"grad_norm": 2.979928970336914,
|
| 491 |
+
"learning_rate": 1.4362061661555675e-05,
|
| 492 |
+
"loss": 0.4568,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.1693121693121693,
|
| 497 |
+
"grad_norm": 1.2313185930252075,
|
| 498 |
+
"learning_rate": 1.4198891015602648e-05,
|
| 499 |
+
"loss": 0.4359,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.1862433862433863,
|
| 504 |
+
"grad_norm": 1.1036418676376343,
|
| 505 |
+
"learning_rate": 1.4034351619898088e-05,
|
| 506 |
+
"loss": 0.4698,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.2031746031746031,
|
| 511 |
+
"grad_norm": 1.1762608289718628,
|
| 512 |
+
"learning_rate": 1.3868497110808394e-05,
|
| 513 |
+
"loss": 0.4313,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.2201058201058201,
|
| 518 |
+
"grad_norm": 1.033484697341919,
|
| 519 |
+
"learning_rate": 1.3701381553399147e-05,
|
| 520 |
+
"loss": 0.45,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.237037037037037,
|
| 525 |
+
"grad_norm": 2.2186121940612793,
|
| 526 |
+
"learning_rate": 1.3533059423811026e-05,
|
| 527 |
+
"loss": 0.4345,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.253968253968254,
|
| 532 |
+
"grad_norm": 1.0926917791366577,
|
| 533 |
+
"learning_rate": 1.3363585591501751e-05,
|
| 534 |
+
"loss": 0.4317,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.270899470899471,
|
| 539 |
+
"grad_norm": 1.094223976135254,
|
| 540 |
+
"learning_rate": 1.31930153013598e-05,
|
| 541 |
+
"loss": 0.4274,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.2878306878306878,
|
| 546 |
+
"grad_norm": 1.0197666883468628,
|
| 547 |
+
"learning_rate": 1.3021404155695728e-05,
|
| 548 |
+
"loss": 0.4465,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.3047619047619048,
|
| 553 |
+
"grad_norm": 1.0113344192504883,
|
| 554 |
+
"learning_rate": 1.2848808096117003e-05,
|
| 555 |
+
"loss": 0.4256,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.3216931216931216,
|
| 560 |
+
"grad_norm": 0.9916861653327942,
|
| 561 |
+
"learning_rate": 1.2675283385292212e-05,
|
| 562 |
+
"loss": 0.4291,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.3386243386243386,
|
| 567 |
+
"grad_norm": 1.0909327268600464,
|
| 568 |
+
"learning_rate": 1.250088658861063e-05,
|
| 569 |
+
"loss": 0.4387,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.3555555555555556,
|
| 574 |
+
"grad_norm": 0.9891695976257324,
|
| 575 |
+
"learning_rate": 1.2325674555743106e-05,
|
| 576 |
+
"loss": 0.4274,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.3724867724867724,
|
| 581 |
+
"grad_norm": 1.053537368774414,
|
| 582 |
+
"learning_rate": 1.2149704402110243e-05,
|
| 583 |
+
"loss": 0.4243,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.3894179894179894,
|
| 588 |
+
"grad_norm": 1.0343950986862183,
|
| 589 |
+
"learning_rate": 1.1973033490264e-05,
|
| 590 |
+
"loss": 0.4029,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.4063492063492062,
|
| 595 |
+
"grad_norm": 1.0367940664291382,
|
| 596 |
+
"learning_rate": 1.1795719411188717e-05,
|
| 597 |
+
"loss": 0.4154,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.4232804232804233,
|
| 602 |
+
"grad_norm": 0.9142754673957825,
|
| 603 |
+
"learning_rate": 1.161781996552765e-05,
|
| 604 |
+
"loss": 0.4352,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.4402116402116403,
|
| 609 |
+
"grad_norm": 0.9767040610313416,
|
| 610 |
+
"learning_rate": 1.1439393144741192e-05,
|
| 611 |
+
"loss": 0.4131,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.457142857142857,
|
| 616 |
+
"grad_norm": 1.1032475233078003,
|
| 617 |
+
"learning_rate": 1.1260497112202895e-05,
|
| 618 |
+
"loss": 0.4177,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.474074074074074,
|
| 623 |
+
"grad_norm": 0.8925254940986633,
|
| 624 |
+
"learning_rate": 1.1081190184239418e-05,
|
| 625 |
+
"loss": 0.4384,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.491005291005291,
|
| 630 |
+
"grad_norm": 0.9563277959823608,
|
| 631 |
+
"learning_rate": 1.0901530811120655e-05,
|
| 632 |
+
"loss": 0.404,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.507936507936508,
|
| 637 |
+
"grad_norm": 0.8952954411506653,
|
| 638 |
+
"learning_rate": 1.0721577558006164e-05,
|
| 639 |
+
"loss": 0.3869,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.524867724867725,
|
| 644 |
+
"grad_norm": 1.1573145389556885,
|
| 645 |
+
"learning_rate": 1.0541389085854177e-05,
|
| 646 |
+
"loss": 0.3898,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.541798941798942,
|
| 651 |
+
"grad_norm": 0.9079419374465942,
|
| 652 |
+
"learning_rate": 1.0361024132299364e-05,
|
| 653 |
+
"loss": 0.4094,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.5587301587301587,
|
| 658 |
+
"grad_norm": 1.1131538152694702,
|
| 659 |
+
"learning_rate": 1.0180541492505605e-05,
|
| 660 |
+
"loss": 0.415,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.5756613756613755,
|
| 665 |
+
"grad_norm": 0.9412957429885864,
|
| 666 |
+
"learning_rate": 1e-05,
|
| 667 |
+
"loss": 0.4063,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.5925925925925926,
|
| 672 |
+
"grad_norm": 0.9416212439537048,
|
| 673 |
+
"learning_rate": 9.819458507494395e-06,
|
| 674 |
+
"loss": 0.4073,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.6095238095238096,
|
| 679 |
+
"grad_norm": 1791.885498046875,
|
| 680 |
+
"learning_rate": 9.638975867700638e-06,
|
| 681 |
+
"loss": 0.3969,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.6264550264550266,
|
| 686 |
+
"grad_norm": 0.9790716767311096,
|
| 687 |
+
"learning_rate": 9.458610914145826e-06,
|
| 688 |
+
"loss": 0.4027,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.6433862433862434,
|
| 693 |
+
"grad_norm": 1.0255053043365479,
|
| 694 |
+
"learning_rate": 9.278422441993841e-06,
|
| 695 |
+
"loss": 0.3969,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.6603174603174602,
|
| 700 |
+
"grad_norm": 0.9520485997200012,
|
| 701 |
+
"learning_rate": 9.098469188879348e-06,
|
| 702 |
+
"loss": 0.3999,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.6772486772486772,
|
| 707 |
+
"grad_norm": 0.8883378505706787,
|
| 708 |
+
"learning_rate": 8.918809815760585e-06,
|
| 709 |
+
"loss": 0.3932,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.6941798941798942,
|
| 714 |
+
"grad_norm": 0.922511875629425,
|
| 715 |
+
"learning_rate": 8.739502887797108e-06,
|
| 716 |
+
"loss": 0.379,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.7111111111111112,
|
| 721 |
+
"grad_norm": 0.978553295135498,
|
| 722 |
+
"learning_rate": 8.560606855258808e-06,
|
| 723 |
+
"loss": 0.4112,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.728042328042328,
|
| 728 |
+
"grad_norm": 1.0453370809555054,
|
| 729 |
+
"learning_rate": 8.382180034472353e-06,
|
| 730 |
+
"loss": 0.3979,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.7449735449735448,
|
| 735 |
+
"grad_norm": 0.9882745146751404,
|
| 736 |
+
"learning_rate": 8.204280588811283e-06,
|
| 737 |
+
"loss": 0.4074,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.7619047619047619,
|
| 742 |
+
"grad_norm": 0.8945300579071045,
|
| 743 |
+
"learning_rate": 8.026966509736001e-06,
|
| 744 |
+
"loss": 0.3615,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.7788359788359789,
|
| 749 |
+
"grad_norm": 1.0022529363632202,
|
| 750 |
+
"learning_rate": 7.85029559788976e-06,
|
| 751 |
+
"loss": 0.3805,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.795767195767196,
|
| 756 |
+
"grad_norm": 0.8616457581520081,
|
| 757 |
+
"learning_rate": 7.674325444256899e-06,
|
| 758 |
+
"loss": 0.3842,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.8126984126984127,
|
| 763 |
+
"grad_norm": 1.4591399431228638,
|
| 764 |
+
"learning_rate": 7.499113411389371e-06,
|
| 765 |
+
"loss": 0.3871,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.8296296296296295,
|
| 770 |
+
"grad_norm": 1.0600188970565796,
|
| 771 |
+
"learning_rate": 7.324716614707794e-06,
|
| 772 |
+
"loss": 0.3905,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.8465608465608465,
|
| 777 |
+
"grad_norm": 0.9007483124732971,
|
| 778 |
+
"learning_rate": 7.1511919038830016e-06,
|
| 779 |
+
"loss": 0.3775,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.8634920634920635,
|
| 784 |
+
"grad_norm": 0.9454174041748047,
|
| 785 |
+
"learning_rate": 6.978595844304272e-06,
|
| 786 |
+
"loss": 0.3803,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.8804232804232806,
|
| 791 |
+
"grad_norm": 0.996856153011322,
|
| 792 |
+
"learning_rate": 6.806984698640202e-06,
|
| 793 |
+
"loss": 0.3961,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.8973544973544973,
|
| 798 |
+
"grad_norm": 1.1498510837554932,
|
| 799 |
+
"learning_rate": 6.636414408498249e-06,
|
| 800 |
+
"loss": 0.3851,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.9142857142857141,
|
| 805 |
+
"grad_norm": 9.213700294494629,
|
| 806 |
+
"learning_rate": 6.466940576188978e-06,
|
| 807 |
+
"loss": 0.375,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.9312169312169312,
|
| 812 |
+
"grad_norm": 0.8880584836006165,
|
| 813 |
+
"learning_rate": 6.298618446600856e-06,
|
| 814 |
+
"loss": 0.3691,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.9481481481481482,
|
| 819 |
+
"grad_norm": 1.0605814456939697,
|
| 820 |
+
"learning_rate": 6.131502889191611e-06,
|
| 821 |
+
"loss": 0.3892,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.9650793650793652,
|
| 826 |
+
"grad_norm": 0.8566351532936096,
|
| 827 |
+
"learning_rate": 5.965648380101916e-06,
|
| 828 |
+
"loss": 0.381,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.982010582010582,
|
| 833 |
+
"grad_norm": 0.9199567437171936,
|
| 834 |
+
"learning_rate": 5.801108984397355e-06,
|
| 835 |
+
"loss": 0.3899,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.9989417989417988,
|
| 840 |
+
"grad_norm": 0.9430050253868103,
|
| 841 |
+
"learning_rate": 5.637938338444325e-06,
|
| 842 |
+
"loss": 0.3742,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.0,
|
| 847 |
+
"grad_norm": 0.9430050253868103,
|
| 848 |
+
"learning_rate": 5.476189632425732e-06,
|
| 849 |
+
"loss": 0.4288,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 2.016931216931217,
|
| 854 |
+
"grad_norm": 4.022532939910889,
|
| 855 |
+
"learning_rate": 5.3159155930021e-06,
|
| 856 |
+
"loss": 0.3637,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 2.033862433862434,
|
| 861 |
+
"grad_norm": 0.9256008267402649,
|
| 862 |
+
"learning_rate": 5.1571684661238075e-06,
|
| 863 |
+
"loss": 0.3864,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 2.0507936507936506,
|
| 868 |
+
"grad_norm": 1.0907351970672607,
|
| 869 |
+
"learning_rate": 5.000000000000003e-06,
|
| 870 |
+
"loss": 0.3566,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 2.0677248677248676,
|
| 875 |
+
"grad_norm": 1.0017610788345337,
|
| 876 |
+
"learning_rate": 4.844461428229782e-06,
|
| 877 |
+
"loss": 0.36,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 2.0846560846560847,
|
| 882 |
+
"grad_norm": 1.0023646354675293,
|
| 883 |
+
"learning_rate": 4.690603453101134e-06,
|
| 884 |
+
"loss": 0.3729,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.1015873015873017,
|
| 889 |
+
"grad_norm": 1.0901212692260742,
|
| 890 |
+
"learning_rate": 4.53847622906303e-06,
|
| 891 |
+
"loss": 0.3773,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.1185185185185187,
|
| 896 |
+
"grad_norm": 1.1009324789047241,
|
| 897 |
+
"learning_rate": 4.388129346376177e-06,
|
| 898 |
+
"loss": 0.3847,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.1354497354497353,
|
| 903 |
+
"grad_norm": 1.0068461894989014,
|
| 904 |
+
"learning_rate": 4.239611814947605e-06,
|
| 905 |
+
"loss": 0.3634,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.1523809523809523,
|
| 910 |
+
"grad_norm": 0.8794623613357544,
|
| 911 |
+
"learning_rate": 4.092972048354491e-06,
|
| 912 |
+
"loss": 0.3645,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.1693121693121693,
|
| 917 |
+
"grad_norm": 0.9761602282524109,
|
| 918 |
+
"learning_rate": 3.948257848062351e-06,
|
| 919 |
+
"loss": 0.3676,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.1862433862433863,
|
| 924 |
+
"grad_norm": 1.0799708366394043,
|
| 925 |
+
"learning_rate": 3.8055163878427703e-06,
|
| 926 |
+
"loss": 0.3738,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.2031746031746033,
|
| 931 |
+
"grad_norm": 1.0237700939178467,
|
| 932 |
+
"learning_rate": 3.6647941983957647e-06,
|
| 933 |
+
"loss": 0.3714,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.22010582010582,
|
| 938 |
+
"grad_norm": 0.9058141112327576,
|
| 939 |
+
"learning_rate": 3.5261371521817247e-06,
|
| 940 |
+
"loss": 0.3856,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.237037037037037,
|
| 945 |
+
"grad_norm": 0.9451678395271301,
|
| 946 |
+
"learning_rate": 3.3895904484679986e-06,
|
| 947 |
+
"loss": 0.3795,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.253968253968254,
|
| 952 |
+
"grad_norm": 0.9849613904953003,
|
| 953 |
+
"learning_rate": 3.255198598594862e-06,
|
| 954 |
+
"loss": 0.3503,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.270899470899471,
|
| 959 |
+
"grad_norm": 0.9847337603569031,
|
| 960 |
+
"learning_rate": 3.123005411465766e-06,
|
| 961 |
+
"loss": 0.3762,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.287830687830688,
|
| 966 |
+
"grad_norm": 1.853551983833313,
|
| 967 |
+
"learning_rate": 2.9930539792665767e-06,
|
| 968 |
+
"loss": 0.3683,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.3047619047619046,
|
| 973 |
+
"grad_norm": 1.001577615737915,
|
| 974 |
+
"learning_rate": 2.8653866634184e-06,
|
| 975 |
+
"loss": 0.3728,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.3216931216931216,
|
| 980 |
+
"grad_norm": 1.1002743244171143,
|
| 981 |
+
"learning_rate": 2.740045080768694e-06,
|
| 982 |
+
"loss": 0.3481,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.3386243386243386,
|
| 987 |
+
"grad_norm": 0.878426730632782,
|
| 988 |
+
"learning_rate": 2.6170700900250146e-06,
|
| 989 |
+
"loss": 0.3716,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.3555555555555556,
|
| 994 |
+
"grad_norm": 0.9544874429702759,
|
| 995 |
+
"learning_rate": 2.496501778435977e-06,
|
| 996 |
+
"loss": 0.3689,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 2.3724867724867726,
|
| 1001 |
+
"grad_norm": 1.055256724357605,
|
| 1002 |
+
"learning_rate": 2.3783794487236367e-06,
|
| 1003 |
+
"loss": 0.3583,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.389417989417989,
|
| 1008 |
+
"grad_norm": 1.0352602005004883,
|
| 1009 |
+
"learning_rate": 2.2627416062716366e-06,
|
| 1010 |
+
"loss": 0.3813,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.4063492063492062,
|
| 1015 |
+
"grad_norm": 0.9158893823623657,
|
| 1016 |
+
"learning_rate": 2.1496259465732783e-06,
|
| 1017 |
+
"loss": 0.3503,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.4232804232804233,
|
| 1022 |
+
"grad_norm": 1.4428284168243408,
|
| 1023 |
+
"learning_rate": 2.0390693429435626e-06,
|
| 1024 |
+
"loss": 0.3597,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.4402116402116403,
|
| 1029 |
+
"grad_norm": 0.8209134936332703,
|
| 1030 |
+
"learning_rate": 1.931107834499296e-06,
|
| 1031 |
+
"loss": 0.3683,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 2.4571428571428573,
|
| 1036 |
+
"grad_norm": 0.8735495805740356,
|
| 1037 |
+
"learning_rate": 1.8257766144110823e-06,
|
| 1038 |
+
"loss": 0.3736,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.474074074074074,
|
| 1043 |
+
"grad_norm": 1.0254844427108765,
|
| 1044 |
+
"learning_rate": 1.7231100184310955e-06,
|
| 1045 |
+
"loss": 0.3507,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.491005291005291,
|
| 1050 |
+
"grad_norm": 0.9373979568481445,
|
| 1051 |
+
"learning_rate": 1.6231415137003536e-06,
|
| 1052 |
+
"loss": 0.3456,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.507936507936508,
|
| 1057 |
+
"grad_norm": 0.8155479431152344,
|
| 1058 |
+
"learning_rate": 1.5259036878391342e-06,
|
| 1059 |
+
"loss": 0.3857,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.524867724867725,
|
| 1064 |
+
"grad_norm": 0.9397179484367371,
|
| 1065 |
+
"learning_rate": 1.4314282383241097e-06,
|
| 1066 |
+
"loss": 0.3469,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.541798941798942,
|
| 1071 |
+
"grad_norm": 0.8838076591491699,
|
| 1072 |
+
"learning_rate": 1.339745962155613e-06,
|
| 1073 |
+
"loss": 0.332,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.5587301587301585,
|
| 1078 |
+
"grad_norm": 0.8838992714881897,
|
| 1079 |
+
"learning_rate": 1.2508867458185037e-06,
|
| 1080 |
+
"loss": 0.3616,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.5756613756613755,
|
| 1085 |
+
"grad_norm": 0.833113968372345,
|
| 1086 |
+
"learning_rate": 1.1648795555397719e-06,
|
| 1087 |
+
"loss": 0.3652,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.5925925925925926,
|
| 1092 |
+
"grad_norm": 0.9157512187957764,
|
| 1093 |
+
"learning_rate": 1.0817524278461777e-06,
|
| 1094 |
+
"loss": 0.3633,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.6095238095238096,
|
| 1099 |
+
"grad_norm": 0.9280597567558289,
|
| 1100 |
+
"learning_rate": 1.0015324604249343e-06,
|
| 1101 |
+
"loss": 0.3639,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.6264550264550266,
|
| 1106 |
+
"grad_norm": 0.9176546931266785,
|
| 1107 |
+
"learning_rate": 9.242458032904311e-07,
|
| 1108 |
+
"loss": 0.3684,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.643386243386243,
|
| 1113 |
+
"grad_norm": 0.9126737713813782,
|
| 1114 |
+
"learning_rate": 8.499176502598783e-07,
|
| 1115 |
+
"loss": 0.3725,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.66031746031746,
|
| 1120 |
+
"grad_norm": 0.8442249298095703,
|
| 1121 |
+
"learning_rate": 7.785722307406685e-07,
|
| 1122 |
+
"loss": 0.359,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.677248677248677,
|
| 1127 |
+
"grad_norm": 0.8220723271369934,
|
| 1128 |
+
"learning_rate": 7.102328018320859e-07,
|
| 1129 |
+
"loss": 0.3799,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.6941798941798942,
|
| 1134 |
+
"grad_norm": 0.8401052951812744,
|
| 1135 |
+
"learning_rate": 6.449216407439906e-07,
|
| 1136 |
+
"loss": 0.3462,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.7111111111111112,
|
| 1141 |
+
"grad_norm": 0.8923698663711548,
|
| 1142 |
+
"learning_rate": 5.826600375349201e-07,
|
| 1143 |
+
"loss": 0.3763,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.728042328042328,
|
| 1148 |
+
"grad_norm": 0.9540568590164185,
|
| 1149 |
+
"learning_rate": 5.234682881719766e-07,
|
| 1150 |
+
"loss": 0.3546,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.744973544973545,
|
| 1155 |
+
"grad_norm": 323.1459655761719,
|
| 1156 |
+
"learning_rate": 4.6736568791477367e-07,
|
| 1157 |
+
"loss": 0.3602,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.761904761904762,
|
| 1162 |
+
"grad_norm": 0.8727107644081116,
|
| 1163 |
+
"learning_rate": 4.1437052502558693e-07,
|
| 1164 |
+
"loss": 0.3777,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
}
|
| 1167 |
+
],
|
| 1168 |
+
"logging_steps": 1.0,
|
| 1169 |
+
"max_steps": 180,
|
| 1170 |
+
"num_input_tokens_seen": 0,
|
| 1171 |
+
"num_train_epochs": 3,
|
| 1172 |
+
"save_steps": 5,
|
| 1173 |
+
"stateful_callbacks": {
|
| 1174 |
+
"TrainerControl": {
|
| 1175 |
+
"args": {
|
| 1176 |
+
"should_epoch_stop": false,
|
| 1177 |
+
"should_evaluate": false,
|
| 1178 |
+
"should_log": false,
|
| 1179 |
+
"should_save": true,
|
| 1180 |
+
"should_training_stop": false
|
| 1181 |
+
},
|
| 1182 |
+
"attributes": {}
|
| 1183 |
+
}
|
| 1184 |
+
},
|
| 1185 |
+
"total_flos": 1.163631073258845e+19,
|
| 1186 |
+
"train_batch_size": 2,
|
| 1187 |
+
"trial_name": null,
|
| 1188 |
+
"trial_params": null
|
| 1189 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b996c8098915cad6fa9df62a7aab8dddb39e01a831c3862bb508864ada80ef4
|
| 3 |
+
size 7288
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
zero_to_fp32.py
ADDED
|
@@ -0,0 +1,760 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example:
|
| 14 |
+
# python zero_to_fp32.py . output_dir/
|
| 15 |
+
# or
|
| 16 |
+
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
+
|
| 18 |
+
import argparse
|
| 19 |
+
import torch
|
| 20 |
+
import glob
|
| 21 |
+
import math
|
| 22 |
+
import os
|
| 23 |
+
import re
|
| 24 |
+
import gc
|
| 25 |
+
import json
|
| 26 |
+
import numpy as np
|
| 27 |
+
from tqdm import tqdm
|
| 28 |
+
from collections import OrderedDict
|
| 29 |
+
from dataclasses import dataclass
|
| 30 |
+
|
| 31 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 32 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 33 |
+
from deepspeed.utils import logger
|
| 34 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 35 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 36 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
@dataclass
|
| 40 |
+
class zero_model_state:
|
| 41 |
+
buffers: dict()
|
| 42 |
+
param_shapes: dict()
|
| 43 |
+
shared_params: list
|
| 44 |
+
ds_version: int
|
| 45 |
+
frozen_param_shapes: dict()
|
| 46 |
+
frozen_param_fragments: dict()
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
debug = 0
|
| 50 |
+
|
| 51 |
+
# load to cpu
|
| 52 |
+
device = torch.device('cpu')
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
def atoi(text):
|
| 56 |
+
return int(text) if text.isdigit() else text
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
def natural_keys(text):
|
| 60 |
+
'''
|
| 61 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 62 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 63 |
+
(See Toothy's implementation in the comments)
|
| 64 |
+
'''
|
| 65 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 69 |
+
if not os.path.isdir(checkpoint_dir):
|
| 70 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 71 |
+
|
| 72 |
+
# there should be only one file
|
| 73 |
+
if zero_stage <= 2:
|
| 74 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 75 |
+
elif zero_stage == 3:
|
| 76 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 77 |
+
|
| 78 |
+
if not os.path.exists(file):
|
| 79 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 80 |
+
|
| 81 |
+
return file
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 85 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 86 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 87 |
+
|
| 88 |
+
if len(ckpt_files) == 0:
|
| 89 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 90 |
+
|
| 91 |
+
return ckpt_files
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
def get_optim_files(checkpoint_dir):
|
| 95 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
def get_model_state_files(checkpoint_dir):
|
| 99 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
def parse_model_states(files):
|
| 103 |
+
zero_model_states = []
|
| 104 |
+
for file in files:
|
| 105 |
+
state_dict = torch.load(file, map_location=device, weights_only=False)
|
| 106 |
+
|
| 107 |
+
if BUFFER_NAMES not in state_dict:
|
| 108 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 109 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 110 |
+
if debug:
|
| 111 |
+
print("Found buffers:", buffer_names)
|
| 112 |
+
|
| 113 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 114 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 115 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 116 |
+
|
| 117 |
+
# collect parameters that are included in param_shapes
|
| 118 |
+
param_names = []
|
| 119 |
+
for s in param_shapes:
|
| 120 |
+
for name in s.keys():
|
| 121 |
+
param_names.append(name)
|
| 122 |
+
|
| 123 |
+
# update with frozen parameters
|
| 124 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 125 |
+
if frozen_param_shapes is not None:
|
| 126 |
+
if debug:
|
| 127 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 128 |
+
param_names += list(frozen_param_shapes.keys())
|
| 129 |
+
|
| 130 |
+
# handle shared params
|
| 131 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 132 |
+
|
| 133 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 134 |
+
|
| 135 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 136 |
+
|
| 137 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 138 |
+
param_shapes=param_shapes,
|
| 139 |
+
shared_params=shared_params,
|
| 140 |
+
ds_version=ds_version,
|
| 141 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 142 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 143 |
+
zero_model_states.append(z_model_state)
|
| 144 |
+
|
| 145 |
+
return zero_model_states
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 149 |
+
total_files = len(files)
|
| 150 |
+
state_dicts = []
|
| 151 |
+
for f in tqdm(files, desc='Loading checkpoint shards'):
|
| 152 |
+
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
| 153 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 154 |
+
# and also handle the case where it was already removed by another helper script
|
| 155 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 156 |
+
state_dicts.append(state_dict)
|
| 157 |
+
|
| 158 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 159 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 160 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 161 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 162 |
+
|
| 163 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 164 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 165 |
+
# use the max of the partition_count to get the dp world_size.
|
| 166 |
+
|
| 167 |
+
if type(world_size) is list:
|
| 168 |
+
world_size = max(world_size)
|
| 169 |
+
|
| 170 |
+
if world_size != total_files:
|
| 171 |
+
raise ValueError(
|
| 172 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 173 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 174 |
+
)
|
| 175 |
+
|
| 176 |
+
# the groups are named differently in each stage
|
| 177 |
+
if zero_stage <= 2:
|
| 178 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 179 |
+
elif zero_stage == 3:
|
| 180 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 181 |
+
else:
|
| 182 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 183 |
+
|
| 184 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 185 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 186 |
+
|
| 187 |
+
|
| 188 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 189 |
+
"""
|
| 190 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 191 |
+
|
| 192 |
+
Args:
|
| 193 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 194 |
+
|
| 195 |
+
"""
|
| 196 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 197 |
+
|
| 198 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 199 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 200 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 201 |
+
|
| 202 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 203 |
+
|
| 204 |
+
zero_model_states = parse_model_states(model_files)
|
| 205 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 206 |
+
|
| 207 |
+
if zero_stage <= 2:
|
| 208 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 209 |
+
exclude_frozen_parameters)
|
| 210 |
+
elif zero_stage == 3:
|
| 211 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 212 |
+
exclude_frozen_parameters)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 216 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 217 |
+
return
|
| 218 |
+
|
| 219 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 220 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 221 |
+
|
| 222 |
+
if debug:
|
| 223 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 224 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 225 |
+
|
| 226 |
+
wanted_params = len(frozen_param_shapes)
|
| 227 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 228 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 229 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 230 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 231 |
+
|
| 232 |
+
total_params = 0
|
| 233 |
+
total_numel = 0
|
| 234 |
+
for name, shape in frozen_param_shapes.items():
|
| 235 |
+
total_params += 1
|
| 236 |
+
unpartitioned_numel = shape.numel()
|
| 237 |
+
total_numel += unpartitioned_numel
|
| 238 |
+
|
| 239 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 240 |
+
|
| 241 |
+
if debug:
|
| 242 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 243 |
+
|
| 244 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
def _has_callable(obj, fn):
|
| 248 |
+
attr = getattr(obj, fn, None)
|
| 249 |
+
return callable(attr)
|
| 250 |
+
|
| 251 |
+
|
| 252 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 253 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 254 |
+
|
| 255 |
+
# Reconstruction protocol:
|
| 256 |
+
#
|
| 257 |
+
# XXX: document this
|
| 258 |
+
|
| 259 |
+
if debug:
|
| 260 |
+
for i in range(world_size):
|
| 261 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 262 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 263 |
+
|
| 264 |
+
# XXX: memory usage doubles here (zero2)
|
| 265 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 266 |
+
merged_single_partition_of_fp32_groups = []
|
| 267 |
+
for i in range(num_param_groups):
|
| 268 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 269 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 270 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 271 |
+
avail_numel = sum(
|
| 272 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 273 |
+
|
| 274 |
+
if debug:
|
| 275 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 276 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 277 |
+
# not asserting if there is a mismatch due to possible padding
|
| 278 |
+
print(f"Have {avail_numel} numels to process.")
|
| 279 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 280 |
+
|
| 281 |
+
# params
|
| 282 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 283 |
+
# out-of-core computing solution
|
| 284 |
+
total_numel = 0
|
| 285 |
+
total_params = 0
|
| 286 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 287 |
+
offset = 0
|
| 288 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 289 |
+
for name, shape in shapes.items():
|
| 290 |
+
|
| 291 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 292 |
+
total_numel += unpartitioned_numel
|
| 293 |
+
total_params += 1
|
| 294 |
+
|
| 295 |
+
if debug:
|
| 296 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 297 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 298 |
+
offset += unpartitioned_numel
|
| 299 |
+
|
| 300 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 301 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 302 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 303 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 304 |
+
align_to = 2 * world_size
|
| 305 |
+
|
| 306 |
+
def zero2_align(x):
|
| 307 |
+
return align_to * math.ceil(x / align_to)
|
| 308 |
+
|
| 309 |
+
if debug:
|
| 310 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 311 |
+
|
| 312 |
+
offset = zero2_align(offset)
|
| 313 |
+
avail_numel = zero2_align(avail_numel)
|
| 314 |
+
|
| 315 |
+
if debug:
|
| 316 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 317 |
+
|
| 318 |
+
# Sanity check
|
| 319 |
+
if offset != avail_numel:
|
| 320 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 321 |
+
|
| 322 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 323 |
+
|
| 324 |
+
|
| 325 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 326 |
+
exclude_frozen_parameters):
|
| 327 |
+
state_dict = OrderedDict()
|
| 328 |
+
|
| 329 |
+
# buffers
|
| 330 |
+
buffers = zero_model_states[0].buffers
|
| 331 |
+
state_dict.update(buffers)
|
| 332 |
+
if debug:
|
| 333 |
+
print(f"added {len(buffers)} buffers")
|
| 334 |
+
|
| 335 |
+
if not exclude_frozen_parameters:
|
| 336 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 337 |
+
|
| 338 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 339 |
+
|
| 340 |
+
# recover shared parameters
|
| 341 |
+
for pair in zero_model_states[0].shared_params:
|
| 342 |
+
if pair[1] in state_dict:
|
| 343 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 344 |
+
|
| 345 |
+
return state_dict
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 349 |
+
remainder = unpartitioned_numel % world_size
|
| 350 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 351 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 352 |
+
return partitioned_numel, padding_numel
|
| 353 |
+
|
| 354 |
+
|
| 355 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 356 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 357 |
+
return
|
| 358 |
+
|
| 359 |
+
if debug:
|
| 360 |
+
for i in range(world_size):
|
| 361 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 362 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 363 |
+
|
| 364 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 365 |
+
wanted_params = len(frozen_param_shapes)
|
| 366 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 367 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 368 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 369 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 370 |
+
|
| 371 |
+
total_params = 0
|
| 372 |
+
total_numel = 0
|
| 373 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 374 |
+
total_params += 1
|
| 375 |
+
unpartitioned_numel = shape.numel()
|
| 376 |
+
total_numel += unpartitioned_numel
|
| 377 |
+
|
| 378 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 379 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 380 |
+
|
| 381 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 382 |
+
|
| 383 |
+
if debug:
|
| 384 |
+
print(
|
| 385 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 386 |
+
)
|
| 387 |
+
|
| 388 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 389 |
+
|
| 390 |
+
|
| 391 |
+
class GatheredTensor:
|
| 392 |
+
"""
|
| 393 |
+
A pseudo tensor that collects partitioned weights.
|
| 394 |
+
It is more memory efficient when there are multiple groups.
|
| 395 |
+
"""
|
| 396 |
+
|
| 397 |
+
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
| 398 |
+
self.flat_groups = flat_groups
|
| 399 |
+
self.flat_groups_offset = flat_groups_offset
|
| 400 |
+
self.offset = offset
|
| 401 |
+
self.partitioned_numel = partitioned_numel
|
| 402 |
+
self.shape = shape
|
| 403 |
+
self.dtype = self.flat_groups[0][0].dtype
|
| 404 |
+
|
| 405 |
+
def contiguous(self):
|
| 406 |
+
"""
|
| 407 |
+
Merge partitioned weights from flat_groups into a single tensor.
|
| 408 |
+
"""
|
| 409 |
+
end_idx = self.offset + self.partitioned_numel
|
| 410 |
+
world_size = len(self.flat_groups)
|
| 411 |
+
pad_flat_param_chunks = []
|
| 412 |
+
|
| 413 |
+
for rank_i in range(world_size):
|
| 414 |
+
# for each rank, we need to collect weights from related group/groups
|
| 415 |
+
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
| 416 |
+
start_group_id = None
|
| 417 |
+
end_group_id = None
|
| 418 |
+
for group_id in range(len(self.flat_groups_offset)):
|
| 419 |
+
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
| 420 |
+
start_group_id = group_id
|
| 421 |
+
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
| 422 |
+
end_group_id = group_id
|
| 423 |
+
break
|
| 424 |
+
# collect weights from related group/groups
|
| 425 |
+
for group_id in range(start_group_id, end_group_id + 1):
|
| 426 |
+
flat_tensor = flat_groups_at_rank_i[group_id]
|
| 427 |
+
start_offset = self.offset - self.flat_groups_offset[group_id]
|
| 428 |
+
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
| 429 |
+
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
| 430 |
+
|
| 431 |
+
# collect weights from all ranks
|
| 432 |
+
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
| 433 |
+
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
| 434 |
+
return param
|
| 435 |
+
|
| 436 |
+
|
| 437 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 438 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 439 |
+
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
| 440 |
+
|
| 441 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 442 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 443 |
+
|
| 444 |
+
# merge list of dicts, preserving order
|
| 445 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 446 |
+
|
| 447 |
+
if debug:
|
| 448 |
+
for i in range(world_size):
|
| 449 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 450 |
+
|
| 451 |
+
wanted_params = len(param_shapes)
|
| 452 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 453 |
+
# not asserting if there is a mismatch due to possible padding
|
| 454 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 455 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 456 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 457 |
+
|
| 458 |
+
# params
|
| 459 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 460 |
+
# out-of-core computing solution
|
| 461 |
+
offset = 0
|
| 462 |
+
total_numel = 0
|
| 463 |
+
total_params = 0
|
| 464 |
+
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
| 465 |
+
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
| 466 |
+
unpartitioned_numel = shape.numel()
|
| 467 |
+
total_numel += unpartitioned_numel
|
| 468 |
+
total_params += 1
|
| 469 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 470 |
+
|
| 471 |
+
if debug:
|
| 472 |
+
print(
|
| 473 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 474 |
+
)
|
| 475 |
+
|
| 476 |
+
# memory efficient tensor
|
| 477 |
+
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
| 478 |
+
state_dict[name] = tensor
|
| 479 |
+
offset += partitioned_numel
|
| 480 |
+
|
| 481 |
+
offset *= world_size
|
| 482 |
+
|
| 483 |
+
# Sanity check
|
| 484 |
+
if offset != avail_numel:
|
| 485 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 486 |
+
|
| 487 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 488 |
+
|
| 489 |
+
|
| 490 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 491 |
+
exclude_frozen_parameters):
|
| 492 |
+
state_dict = OrderedDict()
|
| 493 |
+
|
| 494 |
+
# buffers
|
| 495 |
+
buffers = zero_model_states[0].buffers
|
| 496 |
+
state_dict.update(buffers)
|
| 497 |
+
if debug:
|
| 498 |
+
print(f"added {len(buffers)} buffers")
|
| 499 |
+
|
| 500 |
+
if not exclude_frozen_parameters:
|
| 501 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 502 |
+
|
| 503 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 504 |
+
|
| 505 |
+
# recover shared parameters
|
| 506 |
+
for pair in zero_model_states[0].shared_params:
|
| 507 |
+
if pair[1] in state_dict:
|
| 508 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 509 |
+
|
| 510 |
+
return state_dict
|
| 511 |
+
|
| 512 |
+
|
| 513 |
+
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
| 514 |
+
"""
|
| 515 |
+
Convert state_dict of GatheredTensor to torch tensor
|
| 516 |
+
"""
|
| 517 |
+
torch_state_dict = {}
|
| 518 |
+
converted_tensors = {}
|
| 519 |
+
for name, tensor in state_dict.items():
|
| 520 |
+
tensor_id = id(tensor)
|
| 521 |
+
if tensor_id in converted_tensors: # shared tensors
|
| 522 |
+
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
| 523 |
+
torch_state_dict[name] = shared_tensor
|
| 524 |
+
else:
|
| 525 |
+
converted_tensors[tensor_id] = name
|
| 526 |
+
if return_empty_tensor:
|
| 527 |
+
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
| 528 |
+
else:
|
| 529 |
+
torch_state_dict[name] = tensor.contiguous()
|
| 530 |
+
return torch_state_dict
|
| 531 |
+
|
| 532 |
+
|
| 533 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 534 |
+
tag=None,
|
| 535 |
+
exclude_frozen_parameters=False,
|
| 536 |
+
lazy_mode=False):
|
| 537 |
+
"""
|
| 538 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 539 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 540 |
+
via a model hub.
|
| 541 |
+
|
| 542 |
+
Args:
|
| 543 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 544 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 545 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 546 |
+
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
| 547 |
+
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
| 548 |
+
|
| 549 |
+
Returns:
|
| 550 |
+
- pytorch ``state_dict``
|
| 551 |
+
|
| 552 |
+
A typical usage might be ::
|
| 553 |
+
|
| 554 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 555 |
+
# do the training and checkpoint saving
|
| 556 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 557 |
+
model = model.cpu() # move to cpu
|
| 558 |
+
model.load_state_dict(state_dict)
|
| 559 |
+
# submit to model hub or save the model to share with others
|
| 560 |
+
|
| 561 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 562 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 563 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 564 |
+
|
| 565 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 566 |
+
|
| 567 |
+
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
| 568 |
+
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 569 |
+
the checkpoint. Or you can load state_dict in lazy mode ::
|
| 570 |
+
|
| 571 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 572 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
| 573 |
+
for name, lazy_tensor in state_dict.item():
|
| 574 |
+
tensor = lazy_tensor.contiguous() # to cpu
|
| 575 |
+
print(name, tensor)
|
| 576 |
+
# del tensor to release memory if it no longer in use
|
| 577 |
+
"""
|
| 578 |
+
if tag is None:
|
| 579 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 580 |
+
if os.path.isfile(latest_path):
|
| 581 |
+
with open(latest_path, 'r') as fd:
|
| 582 |
+
tag = fd.read().strip()
|
| 583 |
+
else:
|
| 584 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 585 |
+
|
| 586 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 587 |
+
|
| 588 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 589 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 590 |
+
|
| 591 |
+
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 592 |
+
if lazy_mode:
|
| 593 |
+
return state_dict
|
| 594 |
+
else:
|
| 595 |
+
return to_torch_tensor(state_dict)
|
| 596 |
+
|
| 597 |
+
|
| 598 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 599 |
+
output_dir,
|
| 600 |
+
max_shard_size="5GB",
|
| 601 |
+
safe_serialization=False,
|
| 602 |
+
tag=None,
|
| 603 |
+
exclude_frozen_parameters=False):
|
| 604 |
+
"""
|
| 605 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 606 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 607 |
+
|
| 608 |
+
Args:
|
| 609 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 610 |
+
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 611 |
+
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 612 |
+
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 613 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 614 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 615 |
+
"""
|
| 616 |
+
|
| 617 |
+
# Dependency pre-check
|
| 618 |
+
if safe_serialization:
|
| 619 |
+
try:
|
| 620 |
+
from safetensors.torch import save_file
|
| 621 |
+
except ImportError:
|
| 622 |
+
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 623 |
+
raise
|
| 624 |
+
if max_shard_size is not None:
|
| 625 |
+
try:
|
| 626 |
+
from huggingface_hub import split_torch_state_dict_into_shards
|
| 627 |
+
except ImportError:
|
| 628 |
+
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 629 |
+
raise
|
| 630 |
+
|
| 631 |
+
# Convert zero checkpoint to state_dict
|
| 632 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 633 |
+
tag,
|
| 634 |
+
exclude_frozen_parameters,
|
| 635 |
+
lazy_mode=True)
|
| 636 |
+
|
| 637 |
+
# Shard the model if it is too big.
|
| 638 |
+
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 639 |
+
if max_shard_size is not None:
|
| 640 |
+
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 641 |
+
# an memory-efficient approach for sharding
|
| 642 |
+
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
| 643 |
+
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
| 644 |
+
filename_pattern=filename_pattern,
|
| 645 |
+
max_shard_size=max_shard_size)
|
| 646 |
+
else:
|
| 647 |
+
from collections import namedtuple
|
| 648 |
+
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 649 |
+
state_dict_split = StateDictSplit(is_sharded=False,
|
| 650 |
+
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 651 |
+
|
| 652 |
+
# Save the model by shard
|
| 653 |
+
os.makedirs(output_dir, exist_ok=True)
|
| 654 |
+
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 655 |
+
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 656 |
+
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
| 657 |
+
shard_state_dict = to_torch_tensor(shard_state_dict)
|
| 658 |
+
output_path = os.path.join(output_dir, shard_file)
|
| 659 |
+
if safe_serialization:
|
| 660 |
+
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
| 661 |
+
else:
|
| 662 |
+
torch.save(shard_state_dict, output_path)
|
| 663 |
+
# release the memory of current shard
|
| 664 |
+
for tensor_name in list(shard_state_dict.keys()):
|
| 665 |
+
del state_dict[tensor_name]
|
| 666 |
+
del shard_state_dict[tensor_name]
|
| 667 |
+
del shard_state_dict
|
| 668 |
+
gc.collect()
|
| 669 |
+
|
| 670 |
+
# Save index if sharded
|
| 671 |
+
if state_dict_split.is_sharded:
|
| 672 |
+
index = {
|
| 673 |
+
"metadata": state_dict_split.metadata,
|
| 674 |
+
"weight_map": state_dict_split.tensor_to_filename,
|
| 675 |
+
}
|
| 676 |
+
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 677 |
+
save_index_file = os.path.join(output_dir, save_index_file)
|
| 678 |
+
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 679 |
+
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 680 |
+
f.write(content)
|
| 681 |
+
|
| 682 |
+
|
| 683 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 684 |
+
"""
|
| 685 |
+
1. Put the provided model to cpu
|
| 686 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 687 |
+
3. Load it into the provided model
|
| 688 |
+
|
| 689 |
+
Args:
|
| 690 |
+
- ``model``: the model object to update
|
| 691 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 692 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 693 |
+
|
| 694 |
+
Returns:
|
| 695 |
+
- ``model`: modified model
|
| 696 |
+
|
| 697 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 698 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 699 |
+
conveniently placed for you in the checkpoint folder.
|
| 700 |
+
|
| 701 |
+
A typical usage might be ::
|
| 702 |
+
|
| 703 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 704 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 705 |
+
# submit to model hub or save the model to share with others
|
| 706 |
+
|
| 707 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 708 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 709 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 710 |
+
|
| 711 |
+
"""
|
| 712 |
+
logger.info(f"Extracting fp32 weights")
|
| 713 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 714 |
+
|
| 715 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 716 |
+
model = model.cpu()
|
| 717 |
+
model.load_state_dict(state_dict, strict=False)
|
| 718 |
+
|
| 719 |
+
return model
|
| 720 |
+
|
| 721 |
+
|
| 722 |
+
if __name__ == "__main__":
|
| 723 |
+
parser = argparse.ArgumentParser()
|
| 724 |
+
parser.add_argument("checkpoint_dir",
|
| 725 |
+
type=str,
|
| 726 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 727 |
+
parser.add_argument("output_dir",
|
| 728 |
+
type=str,
|
| 729 |
+
help="directory to the pytorch fp32 state_dict output files"
|
| 730 |
+
"(e.g. path/checkpoint-12-output/)")
|
| 731 |
+
parser.add_argument(
|
| 732 |
+
"--max_shard_size",
|
| 733 |
+
type=str,
|
| 734 |
+
default="5GB",
|
| 735 |
+
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 736 |
+
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 737 |
+
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 738 |
+
"without CPU OOM issues.")
|
| 739 |
+
parser.add_argument(
|
| 740 |
+
"--safe_serialization",
|
| 741 |
+
default=False,
|
| 742 |
+
action='store_true',
|
| 743 |
+
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 744 |
+
parser.add_argument("-t",
|
| 745 |
+
"--tag",
|
| 746 |
+
type=str,
|
| 747 |
+
default=None,
|
| 748 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 749 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 750 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 751 |
+
args = parser.parse_args()
|
| 752 |
+
|
| 753 |
+
debug = args.debug
|
| 754 |
+
|
| 755 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 756 |
+
args.output_dir,
|
| 757 |
+
max_shard_size=args.max_shard_size,
|
| 758 |
+
safe_serialization=args.safe_serialization,
|
| 759 |
+
tag=args.tag,
|
| 760 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|