upload simnpo_Olmo-3-1025-7B_20260428_231931
Browse files- checkpoint-200/config.json +69 -0
- checkpoint-200/generation_config.json +8 -0
- checkpoint-200/model.safetensors +3 -0
- checkpoint-200/optimizer.pt +3 -0
- checkpoint-200/rng_state.pth +3 -0
- checkpoint-200/scheduler.pt +3 -0
- checkpoint-200/tokenizer.json +0 -0
- checkpoint-200/tokenizer_config.json +14 -0
- checkpoint-200/trainer_state.json +661 -0
- checkpoint-200/training_args.bin +3 -0
- checkpoint-400/config.json +69 -0
- checkpoint-400/generation_config.json +8 -0
- checkpoint-400/model.safetensors +3 -0
- checkpoint-400/optimizer.pt +3 -0
- checkpoint-400/rng_state.pth +3 -0
- checkpoint-400/scheduler.pt +3 -0
- checkpoint-400/tokenizer.json +0 -0
- checkpoint-400/tokenizer_config.json +14 -0
- checkpoint-400/trainer_state.json +1281 -0
- checkpoint-400/training_args.bin +3 -0
- checkpoint-506/config.json +69 -0
- checkpoint-506/generation_config.json +8 -0
- checkpoint-506/model.safetensors +3 -0
- checkpoint-506/optimizer.pt +3 -0
- checkpoint-506/rng_state.pth +3 -0
- checkpoint-506/scheduler.pt +3 -0
- checkpoint-506/tokenizer.json +0 -0
- checkpoint-506/tokenizer_config.json +14 -0
- checkpoint-506/trainer_state.json +1615 -0
- checkpoint-506/training_args.bin +3 -0
- config.json +69 -0
- config.yaml +35 -0
- generation_config.json +8 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +14 -0
- train.log +5 -0
- train_summary.json +48 -0
- training_args.bin +3 -0
checkpoint-200/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Olmo3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"sliding_attention",
|
| 16 |
+
"sliding_attention",
|
| 17 |
+
"sliding_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"sliding_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"full_attention"
|
| 47 |
+
],
|
| 48 |
+
"max_position_embeddings": 65536,
|
| 49 |
+
"model_type": "olmo3",
|
| 50 |
+
"num_attention_heads": 32,
|
| 51 |
+
"num_hidden_layers": 32,
|
| 52 |
+
"num_key_value_heads": 32,
|
| 53 |
+
"pad_token_id": 100277,
|
| 54 |
+
"rms_norm_eps": 1e-06,
|
| 55 |
+
"rope_parameters": {
|
| 56 |
+
"attention_factor": 1.2079441541679836,
|
| 57 |
+
"beta_fast": 32.0,
|
| 58 |
+
"beta_slow": 1.0,
|
| 59 |
+
"factor": 8.0,
|
| 60 |
+
"original_max_position_embeddings": 8192,
|
| 61 |
+
"rope_theta": 500000,
|
| 62 |
+
"rope_type": "yarn"
|
| 63 |
+
},
|
| 64 |
+
"sliding_window": 4096,
|
| 65 |
+
"tie_word_embeddings": false,
|
| 66 |
+
"transformers_version": "5.6.0",
|
| 67 |
+
"use_cache": false,
|
| 68 |
+
"vocab_size": 100278
|
| 69 |
+
}
|
checkpoint-200/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
100257
|
| 5 |
+
],
|
| 6 |
+
"pad_token_id": 100277,
|
| 7 |
+
"transformers_version": "5.6.0"
|
| 8 |
+
}
|
checkpoint-200/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:22e7933bc2419ca45ad3d23bd46f4a5db4f1f6205a5fc69ce6948cd0687d9e79
|
| 3 |
+
size 14596063960
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b11e1174beb06b6755e29b292482143b34855370084db9e254f105e6a9de2bfe
|
| 3 |
+
size 29192355324
|
checkpoint-200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91317c5e4abc67d24eaa48e06aae01d8e24c1621d2d7b287b5317f05ead1b119
|
| 3 |
+
size 14645
|
checkpoint-200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d40399ea280ba96b20c6d0a2ef0bfc64a76a6a1d6f356021c001829456985cb
|
| 3 |
+
size 1465
|
checkpoint-200/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-200/tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": false,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"model_max_length": 65536,
|
| 11 |
+
"pad_token": "<|pad|>",
|
| 12 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 13 |
+
"unk_token": "<|endoftext|>"
|
| 14 |
+
}
|
checkpoint-200/trainer_state.json
ADDED
|
@@ -0,0 +1,661 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7912957467853611,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 200,
|
| 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,
|
| 14 |
+
"forget_loss": 0.14035749435424805,
|
| 15 |
+
"retain_loss": 2.6653778553009033,
|
| 16 |
+
"step": 0
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0,
|
| 20 |
+
"forget_loss": 0.19487237930297852,
|
| 21 |
+
"retain_loss": 2.794126033782959,
|
| 22 |
+
"step": 0
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0,
|
| 26 |
+
"forget_loss": 0.1652039885520935,
|
| 27 |
+
"retain_loss": 2.7992446422576904,
|
| 28 |
+
"step": 0
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0,
|
| 32 |
+
"forget_loss": 0.25970637798309326,
|
| 33 |
+
"retain_loss": 2.7407283782958984,
|
| 34 |
+
"step": 0
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.003956478733926805,
|
| 38 |
+
"grad_norm": 10.1875,
|
| 39 |
+
"learning_rate": 0.0,
|
| 40 |
+
"loss": 3.700044631958008,
|
| 41 |
+
"step": 1
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.03956478733926805,
|
| 45 |
+
"grad_norm": 2.390625,
|
| 46 |
+
"learning_rate": 4.5e-05,
|
| 47 |
+
"loss": 2.9271229637993708,
|
| 48 |
+
"step": 10
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.03956478733926805,
|
| 52 |
+
"forget_loss": 0.0006051036179997027,
|
| 53 |
+
"retain_loss": 2.075515031814575,
|
| 54 |
+
"step": 10
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.03956478733926805,
|
| 58 |
+
"forget_loss": 0.0002671501424629241,
|
| 59 |
+
"retain_loss": 2.2641794681549072,
|
| 60 |
+
"step": 10
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.03956478733926805,
|
| 64 |
+
"forget_loss": 0.00017286122601944953,
|
| 65 |
+
"retain_loss": 2.1814846992492676,
|
| 66 |
+
"step": 10
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.03956478733926805,
|
| 70 |
+
"forget_loss": 0.0006279755616560578,
|
| 71 |
+
"retain_loss": 2.482621669769287,
|
| 72 |
+
"step": 10
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0791295746785361,
|
| 76 |
+
"grad_norm": 2.21875,
|
| 77 |
+
"learning_rate": 4.909274193548387e-05,
|
| 78 |
+
"loss": 2.182495880126953,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0791295746785361,
|
| 83 |
+
"forget_loss": 3.0431343475356698e-05,
|
| 84 |
+
"retain_loss": 2.0565364360809326,
|
| 85 |
+
"step": 20
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.0791295746785361,
|
| 89 |
+
"forget_loss": 1.2637827239814214e-05,
|
| 90 |
+
"retain_loss": 1.9916024208068848,
|
| 91 |
+
"step": 20
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.0791295746785361,
|
| 95 |
+
"forget_loss": 8.099855767795816e-05,
|
| 96 |
+
"retain_loss": 2.1353280544281006,
|
| 97 |
+
"step": 20
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.0791295746785361,
|
| 101 |
+
"forget_loss": 4.038449696963653e-05,
|
| 102 |
+
"retain_loss": 1.7972193956375122,
|
| 103 |
+
"step": 20
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.11869436201780416,
|
| 107 |
+
"grad_norm": 2.015625,
|
| 108 |
+
"learning_rate": 4.808467741935484e-05,
|
| 109 |
+
"loss": 1.9499595642089844,
|
| 110 |
+
"step": 30
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.11869436201780416,
|
| 114 |
+
"forget_loss": 2.020488636844675e-06,
|
| 115 |
+
"retain_loss": 1.9730969667434692,
|
| 116 |
+
"step": 30
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.11869436201780416,
|
| 120 |
+
"forget_loss": 8.556620514355018e-07,
|
| 121 |
+
"retain_loss": 2.1347737312316895,
|
| 122 |
+
"step": 30
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.11869436201780416,
|
| 126 |
+
"forget_loss": 1.441345830244245e-05,
|
| 127 |
+
"retain_loss": 1.753809928894043,
|
| 128 |
+
"step": 30
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.11869436201780416,
|
| 132 |
+
"forget_loss": 2.9243692551972345e-05,
|
| 133 |
+
"retain_loss": 2.3272459506988525,
|
| 134 |
+
"step": 30
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.1582591493570722,
|
| 138 |
+
"grad_norm": 1.9453125,
|
| 139 |
+
"learning_rate": 4.7076612903225806e-05,
|
| 140 |
+
"loss": 1.789834213256836,
|
| 141 |
+
"step": 40
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.1582591493570722,
|
| 145 |
+
"forget_loss": 2.2786582121625543e-05,
|
| 146 |
+
"retain_loss": 1.5727999210357666,
|
| 147 |
+
"step": 40
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.1582591493570722,
|
| 151 |
+
"forget_loss": 2.68079929810483e-05,
|
| 152 |
+
"retain_loss": 1.0978410243988037,
|
| 153 |
+
"step": 40
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.1582591493570722,
|
| 157 |
+
"forget_loss": 2.065206535917241e-05,
|
| 158 |
+
"retain_loss": 2.0460541248321533,
|
| 159 |
+
"step": 40
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.1582591493570722,
|
| 163 |
+
"forget_loss": 5.7086062952294014e-06,
|
| 164 |
+
"retain_loss": 1.6670787334442139,
|
| 165 |
+
"step": 40
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.19782393669634027,
|
| 169 |
+
"grad_norm": 1.9609375,
|
| 170 |
+
"learning_rate": 4.606854838709678e-05,
|
| 171 |
+
"loss": 1.5417665481567382,
|
| 172 |
+
"step": 50
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.19782393669634027,
|
| 176 |
+
"forget_loss": 1.4016513887327164e-05,
|
| 177 |
+
"retain_loss": 1.7037866115570068,
|
| 178 |
+
"step": 50
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.19782393669634027,
|
| 182 |
+
"forget_loss": 5.568679171119584e-06,
|
| 183 |
+
"retain_loss": 1.2811342477798462,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.19782393669634027,
|
| 188 |
+
"forget_loss": 1.4726042536494788e-06,
|
| 189 |
+
"retain_loss": 1.7753159999847412,
|
| 190 |
+
"step": 50
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.19782393669634027,
|
| 194 |
+
"forget_loss": 1.6467790828755824e-06,
|
| 195 |
+
"retain_loss": 1.40712571144104,
|
| 196 |
+
"step": 50
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.23738872403560832,
|
| 200 |
+
"grad_norm": 2.28125,
|
| 201 |
+
"learning_rate": 4.506048387096775e-05,
|
| 202 |
+
"loss": 1.460409927368164,
|
| 203 |
+
"step": 60
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.23738872403560832,
|
| 207 |
+
"forget_loss": 8.811715815681964e-06,
|
| 208 |
+
"retain_loss": 1.8770829439163208,
|
| 209 |
+
"step": 60
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.23738872403560832,
|
| 213 |
+
"forget_loss": 9.250835319107864e-06,
|
| 214 |
+
"retain_loss": 1.1297162771224976,
|
| 215 |
+
"step": 60
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.23738872403560832,
|
| 219 |
+
"forget_loss": 5.8820231060963124e-05,
|
| 220 |
+
"retain_loss": 1.0866577625274658,
|
| 221 |
+
"step": 60
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.23738872403560832,
|
| 225 |
+
"forget_loss": 3.214211119484389e-06,
|
| 226 |
+
"retain_loss": 1.241797924041748,
|
| 227 |
+
"step": 60
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.27695351137487634,
|
| 231 |
+
"grad_norm": 2.09375,
|
| 232 |
+
"learning_rate": 4.4052419354838714e-05,
|
| 233 |
+
"loss": 1.3480111122131349,
|
| 234 |
+
"step": 70
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.27695351137487634,
|
| 238 |
+
"forget_loss": 2.020563988480717e-05,
|
| 239 |
+
"retain_loss": 1.2503434419631958,
|
| 240 |
+
"step": 70
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.27695351137487634,
|
| 244 |
+
"forget_loss": 1.9923185391235165e-05,
|
| 245 |
+
"retain_loss": 1.423868179321289,
|
| 246 |
+
"step": 70
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.27695351137487634,
|
| 250 |
+
"forget_loss": 1.3452325902107987e-06,
|
| 251 |
+
"retain_loss": 0.9821794629096985,
|
| 252 |
+
"step": 70
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.27695351137487634,
|
| 256 |
+
"forget_loss": 1.3409412531473208e-06,
|
| 257 |
+
"retain_loss": 1.3942550420761108,
|
| 258 |
+
"step": 70
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.3165182987141444,
|
| 262 |
+
"grad_norm": 2.40625,
|
| 263 |
+
"learning_rate": 4.3044354838709674e-05,
|
| 264 |
+
"loss": 1.2137460708618164,
|
| 265 |
+
"step": 80
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.3165182987141444,
|
| 269 |
+
"forget_loss": 1.4205611478246283e-06,
|
| 270 |
+
"retain_loss": 1.0372614860534668,
|
| 271 |
+
"step": 80
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.3165182987141444,
|
| 275 |
+
"forget_loss": 1.3158517504052725e-05,
|
| 276 |
+
"retain_loss": 1.0091803073883057,
|
| 277 |
+
"step": 80
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.3165182987141444,
|
| 281 |
+
"forget_loss": 1.1485619324957952e-05,
|
| 282 |
+
"retain_loss": 0.8734372854232788,
|
| 283 |
+
"step": 80
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3165182987141444,
|
| 287 |
+
"forget_loss": 3.980534017955506e-07,
|
| 288 |
+
"retain_loss": 0.8553104996681213,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.3560830860534125,
|
| 293 |
+
"grad_norm": 2.40625,
|
| 294 |
+
"learning_rate": 4.203629032258065e-05,
|
| 295 |
+
"loss": 1.1432867050170898,
|
| 296 |
+
"step": 90
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3560830860534125,
|
| 300 |
+
"forget_loss": 2.3974775103852153e-05,
|
| 301 |
+
"retain_loss": 0.8748829364776611,
|
| 302 |
+
"step": 90
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.3560830860534125,
|
| 306 |
+
"forget_loss": 1.9512895960360765e-05,
|
| 307 |
+
"retain_loss": 0.9700671434402466,
|
| 308 |
+
"step": 90
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.3560830860534125,
|
| 312 |
+
"forget_loss": 1.995826096390374e-06,
|
| 313 |
+
"retain_loss": 0.8315430879592896,
|
| 314 |
+
"step": 90
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3560830860534125,
|
| 318 |
+
"forget_loss": 1.571322718518786e-05,
|
| 319 |
+
"retain_loss": 1.208274245262146,
|
| 320 |
+
"step": 90
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.39564787339268054,
|
| 324 |
+
"grad_norm": 2.71875,
|
| 325 |
+
"learning_rate": 4.1028225806451615e-05,
|
| 326 |
+
"loss": 0.944522476196289,
|
| 327 |
+
"step": 100
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.39564787339268054,
|
| 331 |
+
"forget_loss": 4.782319820151315e-07,
|
| 332 |
+
"retain_loss": 0.9833241105079651,
|
| 333 |
+
"step": 100
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.39564787339268054,
|
| 337 |
+
"forget_loss": 2.0109225715714274e-06,
|
| 338 |
+
"retain_loss": 1.0341448783874512,
|
| 339 |
+
"step": 100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.39564787339268054,
|
| 343 |
+
"forget_loss": 6.43863177174353e-06,
|
| 344 |
+
"retain_loss": 1.2469282150268555,
|
| 345 |
+
"step": 100
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.39564787339268054,
|
| 349 |
+
"forget_loss": 1.7480209862696938e-05,
|
| 350 |
+
"retain_loss": 0.5960159301757812,
|
| 351 |
+
"step": 100
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.4352126607319486,
|
| 355 |
+
"grad_norm": 2.4375,
|
| 356 |
+
"learning_rate": 4.002016129032258e-05,
|
| 357 |
+
"loss": 0.8602962493896484,
|
| 358 |
+
"step": 110
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.4352126607319486,
|
| 362 |
+
"forget_loss": 1.1823936802102253e-05,
|
| 363 |
+
"retain_loss": 0.5339686274528503,
|
| 364 |
+
"step": 110
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.4352126607319486,
|
| 368 |
+
"forget_loss": 6.597866075708225e-08,
|
| 369 |
+
"retain_loss": 1.056380033493042,
|
| 370 |
+
"step": 110
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.4352126607319486,
|
| 374 |
+
"forget_loss": 1.9910299670300446e-05,
|
| 375 |
+
"retain_loss": 1.1451334953308105,
|
| 376 |
+
"step": 110
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.4352126607319486,
|
| 380 |
+
"forget_loss": 2.293188572366489e-07,
|
| 381 |
+
"retain_loss": 0.8453196883201599,
|
| 382 |
+
"step": 110
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.47477744807121663,
|
| 386 |
+
"grad_norm": 2.53125,
|
| 387 |
+
"learning_rate": 3.901209677419355e-05,
|
| 388 |
+
"loss": 0.7744930267333985,
|
| 389 |
+
"step": 120
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.47477744807121663,
|
| 393 |
+
"forget_loss": 3.562010078894673e-06,
|
| 394 |
+
"retain_loss": 0.3454712927341461,
|
| 395 |
+
"step": 120
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.47477744807121663,
|
| 399 |
+
"forget_loss": 2.3657979909330606e-05,
|
| 400 |
+
"retain_loss": 0.6900008916854858,
|
| 401 |
+
"step": 120
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.47477744807121663,
|
| 405 |
+
"forget_loss": 7.935936082503758e-06,
|
| 406 |
+
"retain_loss": 1.2215301990509033,
|
| 407 |
+
"step": 120
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.47477744807121663,
|
| 411 |
+
"forget_loss": 3.603380719141569e-06,
|
| 412 |
+
"retain_loss": 0.7156633734703064,
|
| 413 |
+
"step": 120
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.5143422354104846,
|
| 417 |
+
"grad_norm": 2.65625,
|
| 418 |
+
"learning_rate": 3.800403225806452e-05,
|
| 419 |
+
"loss": 0.6265434265136719,
|
| 420 |
+
"step": 130
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.5143422354104846,
|
| 424 |
+
"forget_loss": 3.966476015193621e-06,
|
| 425 |
+
"retain_loss": 0.9189122319221497,
|
| 426 |
+
"step": 130
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.5143422354104846,
|
| 430 |
+
"forget_loss": 1.971156962099485e-07,
|
| 431 |
+
"retain_loss": 0.9686411023139954,
|
| 432 |
+
"step": 130
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.5143422354104846,
|
| 436 |
+
"forget_loss": 7.189528332673945e-07,
|
| 437 |
+
"retain_loss": 0.6004481315612793,
|
| 438 |
+
"step": 130
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.5143422354104846,
|
| 442 |
+
"forget_loss": 6.318293890217319e-05,
|
| 443 |
+
"retain_loss": 0.8465902805328369,
|
| 444 |
+
"step": 130
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5539070227497527,
|
| 448 |
+
"grad_norm": 2.203125,
|
| 449 |
+
"learning_rate": 3.6995967741935484e-05,
|
| 450 |
+
"loss": 0.5954203128814697,
|
| 451 |
+
"step": 140
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5539070227497527,
|
| 455 |
+
"forget_loss": 1.9906601664843038e-06,
|
| 456 |
+
"retain_loss": 0.3101722300052643,
|
| 457 |
+
"step": 140
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5539070227497527,
|
| 461 |
+
"forget_loss": 1.541334859211929e-05,
|
| 462 |
+
"retain_loss": 0.7035630941390991,
|
| 463 |
+
"step": 140
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.5539070227497527,
|
| 467 |
+
"forget_loss": 1.0654130164766684e-06,
|
| 468 |
+
"retain_loss": 0.4943649470806122,
|
| 469 |
+
"step": 140
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.5539070227497527,
|
| 473 |
+
"forget_loss": 7.423601573464111e-07,
|
| 474 |
+
"retain_loss": 0.4140494167804718,
|
| 475 |
+
"step": 140
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.5934718100890207,
|
| 479 |
+
"grad_norm": 1.9453125,
|
| 480 |
+
"learning_rate": 3.598790322580645e-05,
|
| 481 |
+
"loss": 0.5855343818664551,
|
| 482 |
+
"step": 150
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.5934718100890207,
|
| 486 |
+
"forget_loss": 1.361437256264253e-07,
|
| 487 |
+
"retain_loss": 0.4642321467399597,
|
| 488 |
+
"step": 150
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.5934718100890207,
|
| 492 |
+
"forget_loss": 8.585838031649473e-07,
|
| 493 |
+
"retain_loss": 0.27303439378738403,
|
| 494 |
+
"step": 150
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.5934718100890207,
|
| 498 |
+
"forget_loss": 8.958835678640753e-06,
|
| 499 |
+
"retain_loss": 0.8398749828338623,
|
| 500 |
+
"step": 150
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.5934718100890207,
|
| 504 |
+
"forget_loss": 7.379357498393802e-07,
|
| 505 |
+
"retain_loss": 0.1644805520772934,
|
| 506 |
+
"step": 150
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.6330365974282888,
|
| 510 |
+
"grad_norm": 1.9296875,
|
| 511 |
+
"learning_rate": 3.497983870967742e-05,
|
| 512 |
+
"loss": 0.40769476890563966,
|
| 513 |
+
"step": 160
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6330365974282888,
|
| 517 |
+
"forget_loss": 4.321451797295595e-06,
|
| 518 |
+
"retain_loss": 0.6735343337059021,
|
| 519 |
+
"step": 160
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.6330365974282888,
|
| 523 |
+
"forget_loss": 1.2234904716024175e-06,
|
| 524 |
+
"retain_loss": 0.2956700921058655,
|
| 525 |
+
"step": 160
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.6330365974282888,
|
| 529 |
+
"forget_loss": 7.72880184740643e-07,
|
| 530 |
+
"retain_loss": 0.35303422808647156,
|
| 531 |
+
"step": 160
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.6330365974282888,
|
| 535 |
+
"forget_loss": 3.859570369968424e-06,
|
| 536 |
+
"retain_loss": 0.3457622230052948,
|
| 537 |
+
"step": 160
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.6726013847675568,
|
| 541 |
+
"grad_norm": 2.15625,
|
| 542 |
+
"learning_rate": 3.397177419354839e-05,
|
| 543 |
+
"loss": 0.39554681777954104,
|
| 544 |
+
"step": 170
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.6726013847675568,
|
| 548 |
+
"forget_loss": 7.689478138672712e-07,
|
| 549 |
+
"retain_loss": 0.45961564779281616,
|
| 550 |
+
"step": 170
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.6726013847675568,
|
| 554 |
+
"forget_loss": 4.003181288680935e-07,
|
| 555 |
+
"retain_loss": 0.4355284571647644,
|
| 556 |
+
"step": 170
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6726013847675568,
|
| 560 |
+
"forget_loss": 1.2844781167586916e-06,
|
| 561 |
+
"retain_loss": 0.18292923271656036,
|
| 562 |
+
"step": 170
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.6726013847675568,
|
| 566 |
+
"forget_loss": 6.100489372329321e-06,
|
| 567 |
+
"retain_loss": 1.1629327535629272,
|
| 568 |
+
"step": 170
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.712166172106825,
|
| 572 |
+
"grad_norm": 2.21875,
|
| 573 |
+
"learning_rate": 3.296370967741936e-05,
|
| 574 |
+
"loss": 0.37566747665405276,
|
| 575 |
+
"step": 180
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.712166172106825,
|
| 579 |
+
"forget_loss": 1.7554750684212195e-06,
|
| 580 |
+
"retain_loss": 0.2597223222255707,
|
| 581 |
+
"step": 180
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.712166172106825,
|
| 585 |
+
"forget_loss": 3.428482386880205e-07,
|
| 586 |
+
"retain_loss": 0.2552041709423065,
|
| 587 |
+
"step": 180
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.712166172106825,
|
| 591 |
+
"forget_loss": 5.250699359748978e-06,
|
| 592 |
+
"retain_loss": 0.24067796766757965,
|
| 593 |
+
"step": 180
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.712166172106825,
|
| 597 |
+
"forget_loss": 4.978801371180452e-06,
|
| 598 |
+
"retain_loss": 0.3246007561683655,
|
| 599 |
+
"step": 180
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.751730959446093,
|
| 603 |
+
"grad_norm": 2.25,
|
| 604 |
+
"learning_rate": 3.1955645161290326e-05,
|
| 605 |
+
"loss": 0.3259316921234131,
|
| 606 |
+
"step": 190
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.751730959446093,
|
| 610 |
+
"forget_loss": 2.234717385363183e-06,
|
| 611 |
+
"retain_loss": 0.2883687913417816,
|
| 612 |
+
"step": 190
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.751730959446093,
|
| 616 |
+
"forget_loss": 1.0489970009075478e-05,
|
| 617 |
+
"retain_loss": 0.3649686872959137,
|
| 618 |
+
"step": 190
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.751730959446093,
|
| 622 |
+
"forget_loss": 4.861570346292865e-07,
|
| 623 |
+
"retain_loss": 0.08664171397686005,
|
| 624 |
+
"step": 190
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.751730959446093,
|
| 628 |
+
"forget_loss": 1.7122434314842394e-07,
|
| 629 |
+
"retain_loss": 0.5161219835281372,
|
| 630 |
+
"step": 190
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.7912957467853611,
|
| 634 |
+
"grad_norm": 2.046875,
|
| 635 |
+
"learning_rate": 3.0947580645161286e-05,
|
| 636 |
+
"loss": 0.3275477170944214,
|
| 637 |
+
"step": 200
|
| 638 |
+
}
|
| 639 |
+
],
|
| 640 |
+
"logging_steps": 10,
|
| 641 |
+
"max_steps": 506,
|
| 642 |
+
"num_input_tokens_seen": 0,
|
| 643 |
+
"num_train_epochs": 2,
|
| 644 |
+
"save_steps": 200,
|
| 645 |
+
"stateful_callbacks": {
|
| 646 |
+
"TrainerControl": {
|
| 647 |
+
"args": {
|
| 648 |
+
"should_epoch_stop": false,
|
| 649 |
+
"should_evaluate": false,
|
| 650 |
+
"should_log": false,
|
| 651 |
+
"should_save": true,
|
| 652 |
+
"should_training_stop": false
|
| 653 |
+
},
|
| 654 |
+
"attributes": {}
|
| 655 |
+
}
|
| 656 |
+
},
|
| 657 |
+
"total_flos": 0.0,
|
| 658 |
+
"train_batch_size": 8,
|
| 659 |
+
"trial_name": null,
|
| 660 |
+
"trial_params": null
|
| 661 |
+
}
|
checkpoint-200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7587f27094c5b0d28888635edb5fb75b1840350b6c54434f3d8d48a5fdd7e2f
|
| 3 |
+
size 5329
|
checkpoint-400/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Olmo3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"sliding_attention",
|
| 16 |
+
"sliding_attention",
|
| 17 |
+
"sliding_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"sliding_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"full_attention"
|
| 47 |
+
],
|
| 48 |
+
"max_position_embeddings": 65536,
|
| 49 |
+
"model_type": "olmo3",
|
| 50 |
+
"num_attention_heads": 32,
|
| 51 |
+
"num_hidden_layers": 32,
|
| 52 |
+
"num_key_value_heads": 32,
|
| 53 |
+
"pad_token_id": 100277,
|
| 54 |
+
"rms_norm_eps": 1e-06,
|
| 55 |
+
"rope_parameters": {
|
| 56 |
+
"attention_factor": 1.2079441541679836,
|
| 57 |
+
"beta_fast": 32.0,
|
| 58 |
+
"beta_slow": 1.0,
|
| 59 |
+
"factor": 8.0,
|
| 60 |
+
"original_max_position_embeddings": 8192,
|
| 61 |
+
"rope_theta": 500000,
|
| 62 |
+
"rope_type": "yarn"
|
| 63 |
+
},
|
| 64 |
+
"sliding_window": 4096,
|
| 65 |
+
"tie_word_embeddings": false,
|
| 66 |
+
"transformers_version": "5.6.0",
|
| 67 |
+
"use_cache": false,
|
| 68 |
+
"vocab_size": 100278
|
| 69 |
+
}
|
checkpoint-400/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
100257
|
| 5 |
+
],
|
| 6 |
+
"pad_token_id": 100277,
|
| 7 |
+
"transformers_version": "5.6.0"
|
| 8 |
+
}
|
checkpoint-400/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6c9419954d5bfab27896f378e9c7189bc88d6214530e3c6b26b5e97626dcd32
|
| 3 |
+
size 14596063960
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7db37a42a8b29ca6445540cb3559e8335febd4674ebf2f9801cbcbd522b5a0eb
|
| 3 |
+
size 29192355324
|
checkpoint-400/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81aa11c5bbf3890f9c00f9113a3ff5909cc04030779c27ab5030c18c22fcb43d
|
| 3 |
+
size 14645
|
checkpoint-400/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e324b101585ff5707e10076b3759fbb761740196becc755c6980bfe58784642
|
| 3 |
+
size 1465
|
checkpoint-400/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-400/tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": false,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"model_max_length": 65536,
|
| 11 |
+
"pad_token": "<|pad|>",
|
| 12 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 13 |
+
"unk_token": "<|endoftext|>"
|
| 14 |
+
}
|
checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,1281 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.5816023738872405,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 400,
|
| 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,
|
| 14 |
+
"forget_loss": 0.14035749435424805,
|
| 15 |
+
"retain_loss": 2.6653778553009033,
|
| 16 |
+
"step": 0
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0,
|
| 20 |
+
"forget_loss": 0.19487237930297852,
|
| 21 |
+
"retain_loss": 2.794126033782959,
|
| 22 |
+
"step": 0
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0,
|
| 26 |
+
"forget_loss": 0.1652039885520935,
|
| 27 |
+
"retain_loss": 2.7992446422576904,
|
| 28 |
+
"step": 0
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0,
|
| 32 |
+
"forget_loss": 0.25970637798309326,
|
| 33 |
+
"retain_loss": 2.7407283782958984,
|
| 34 |
+
"step": 0
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.003956478733926805,
|
| 38 |
+
"grad_norm": 10.1875,
|
| 39 |
+
"learning_rate": 0.0,
|
| 40 |
+
"loss": 3.700044631958008,
|
| 41 |
+
"step": 1
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.03956478733926805,
|
| 45 |
+
"grad_norm": 2.390625,
|
| 46 |
+
"learning_rate": 4.5e-05,
|
| 47 |
+
"loss": 2.9271229637993708,
|
| 48 |
+
"step": 10
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.03956478733926805,
|
| 52 |
+
"forget_loss": 0.0006051036179997027,
|
| 53 |
+
"retain_loss": 2.075515031814575,
|
| 54 |
+
"step": 10
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.03956478733926805,
|
| 58 |
+
"forget_loss": 0.0002671501424629241,
|
| 59 |
+
"retain_loss": 2.2641794681549072,
|
| 60 |
+
"step": 10
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.03956478733926805,
|
| 64 |
+
"forget_loss": 0.00017286122601944953,
|
| 65 |
+
"retain_loss": 2.1814846992492676,
|
| 66 |
+
"step": 10
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.03956478733926805,
|
| 70 |
+
"forget_loss": 0.0006279755616560578,
|
| 71 |
+
"retain_loss": 2.482621669769287,
|
| 72 |
+
"step": 10
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0791295746785361,
|
| 76 |
+
"grad_norm": 2.21875,
|
| 77 |
+
"learning_rate": 4.909274193548387e-05,
|
| 78 |
+
"loss": 2.182495880126953,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0791295746785361,
|
| 83 |
+
"forget_loss": 3.0431343475356698e-05,
|
| 84 |
+
"retain_loss": 2.0565364360809326,
|
| 85 |
+
"step": 20
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.0791295746785361,
|
| 89 |
+
"forget_loss": 1.2637827239814214e-05,
|
| 90 |
+
"retain_loss": 1.9916024208068848,
|
| 91 |
+
"step": 20
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.0791295746785361,
|
| 95 |
+
"forget_loss": 8.099855767795816e-05,
|
| 96 |
+
"retain_loss": 2.1353280544281006,
|
| 97 |
+
"step": 20
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.0791295746785361,
|
| 101 |
+
"forget_loss": 4.038449696963653e-05,
|
| 102 |
+
"retain_loss": 1.7972193956375122,
|
| 103 |
+
"step": 20
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.11869436201780416,
|
| 107 |
+
"grad_norm": 2.015625,
|
| 108 |
+
"learning_rate": 4.808467741935484e-05,
|
| 109 |
+
"loss": 1.9499595642089844,
|
| 110 |
+
"step": 30
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.11869436201780416,
|
| 114 |
+
"forget_loss": 2.020488636844675e-06,
|
| 115 |
+
"retain_loss": 1.9730969667434692,
|
| 116 |
+
"step": 30
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.11869436201780416,
|
| 120 |
+
"forget_loss": 8.556620514355018e-07,
|
| 121 |
+
"retain_loss": 2.1347737312316895,
|
| 122 |
+
"step": 30
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.11869436201780416,
|
| 126 |
+
"forget_loss": 1.441345830244245e-05,
|
| 127 |
+
"retain_loss": 1.753809928894043,
|
| 128 |
+
"step": 30
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.11869436201780416,
|
| 132 |
+
"forget_loss": 2.9243692551972345e-05,
|
| 133 |
+
"retain_loss": 2.3272459506988525,
|
| 134 |
+
"step": 30
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.1582591493570722,
|
| 138 |
+
"grad_norm": 1.9453125,
|
| 139 |
+
"learning_rate": 4.7076612903225806e-05,
|
| 140 |
+
"loss": 1.789834213256836,
|
| 141 |
+
"step": 40
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.1582591493570722,
|
| 145 |
+
"forget_loss": 2.2786582121625543e-05,
|
| 146 |
+
"retain_loss": 1.5727999210357666,
|
| 147 |
+
"step": 40
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.1582591493570722,
|
| 151 |
+
"forget_loss": 2.68079929810483e-05,
|
| 152 |
+
"retain_loss": 1.0978410243988037,
|
| 153 |
+
"step": 40
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.1582591493570722,
|
| 157 |
+
"forget_loss": 2.065206535917241e-05,
|
| 158 |
+
"retain_loss": 2.0460541248321533,
|
| 159 |
+
"step": 40
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.1582591493570722,
|
| 163 |
+
"forget_loss": 5.7086062952294014e-06,
|
| 164 |
+
"retain_loss": 1.6670787334442139,
|
| 165 |
+
"step": 40
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.19782393669634027,
|
| 169 |
+
"grad_norm": 1.9609375,
|
| 170 |
+
"learning_rate": 4.606854838709678e-05,
|
| 171 |
+
"loss": 1.5417665481567382,
|
| 172 |
+
"step": 50
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.19782393669634027,
|
| 176 |
+
"forget_loss": 1.4016513887327164e-05,
|
| 177 |
+
"retain_loss": 1.7037866115570068,
|
| 178 |
+
"step": 50
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.19782393669634027,
|
| 182 |
+
"forget_loss": 5.568679171119584e-06,
|
| 183 |
+
"retain_loss": 1.2811342477798462,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.19782393669634027,
|
| 188 |
+
"forget_loss": 1.4726042536494788e-06,
|
| 189 |
+
"retain_loss": 1.7753159999847412,
|
| 190 |
+
"step": 50
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.19782393669634027,
|
| 194 |
+
"forget_loss": 1.6467790828755824e-06,
|
| 195 |
+
"retain_loss": 1.40712571144104,
|
| 196 |
+
"step": 50
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.23738872403560832,
|
| 200 |
+
"grad_norm": 2.28125,
|
| 201 |
+
"learning_rate": 4.506048387096775e-05,
|
| 202 |
+
"loss": 1.460409927368164,
|
| 203 |
+
"step": 60
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.23738872403560832,
|
| 207 |
+
"forget_loss": 8.811715815681964e-06,
|
| 208 |
+
"retain_loss": 1.8770829439163208,
|
| 209 |
+
"step": 60
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.23738872403560832,
|
| 213 |
+
"forget_loss": 9.250835319107864e-06,
|
| 214 |
+
"retain_loss": 1.1297162771224976,
|
| 215 |
+
"step": 60
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.23738872403560832,
|
| 219 |
+
"forget_loss": 5.8820231060963124e-05,
|
| 220 |
+
"retain_loss": 1.0866577625274658,
|
| 221 |
+
"step": 60
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.23738872403560832,
|
| 225 |
+
"forget_loss": 3.214211119484389e-06,
|
| 226 |
+
"retain_loss": 1.241797924041748,
|
| 227 |
+
"step": 60
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.27695351137487634,
|
| 231 |
+
"grad_norm": 2.09375,
|
| 232 |
+
"learning_rate": 4.4052419354838714e-05,
|
| 233 |
+
"loss": 1.3480111122131349,
|
| 234 |
+
"step": 70
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.27695351137487634,
|
| 238 |
+
"forget_loss": 2.020563988480717e-05,
|
| 239 |
+
"retain_loss": 1.2503434419631958,
|
| 240 |
+
"step": 70
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.27695351137487634,
|
| 244 |
+
"forget_loss": 1.9923185391235165e-05,
|
| 245 |
+
"retain_loss": 1.423868179321289,
|
| 246 |
+
"step": 70
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.27695351137487634,
|
| 250 |
+
"forget_loss": 1.3452325902107987e-06,
|
| 251 |
+
"retain_loss": 0.9821794629096985,
|
| 252 |
+
"step": 70
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.27695351137487634,
|
| 256 |
+
"forget_loss": 1.3409412531473208e-06,
|
| 257 |
+
"retain_loss": 1.3942550420761108,
|
| 258 |
+
"step": 70
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.3165182987141444,
|
| 262 |
+
"grad_norm": 2.40625,
|
| 263 |
+
"learning_rate": 4.3044354838709674e-05,
|
| 264 |
+
"loss": 1.2137460708618164,
|
| 265 |
+
"step": 80
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.3165182987141444,
|
| 269 |
+
"forget_loss": 1.4205611478246283e-06,
|
| 270 |
+
"retain_loss": 1.0372614860534668,
|
| 271 |
+
"step": 80
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.3165182987141444,
|
| 275 |
+
"forget_loss": 1.3158517504052725e-05,
|
| 276 |
+
"retain_loss": 1.0091803073883057,
|
| 277 |
+
"step": 80
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.3165182987141444,
|
| 281 |
+
"forget_loss": 1.1485619324957952e-05,
|
| 282 |
+
"retain_loss": 0.8734372854232788,
|
| 283 |
+
"step": 80
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3165182987141444,
|
| 287 |
+
"forget_loss": 3.980534017955506e-07,
|
| 288 |
+
"retain_loss": 0.8553104996681213,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.3560830860534125,
|
| 293 |
+
"grad_norm": 2.40625,
|
| 294 |
+
"learning_rate": 4.203629032258065e-05,
|
| 295 |
+
"loss": 1.1432867050170898,
|
| 296 |
+
"step": 90
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3560830860534125,
|
| 300 |
+
"forget_loss": 2.3974775103852153e-05,
|
| 301 |
+
"retain_loss": 0.8748829364776611,
|
| 302 |
+
"step": 90
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.3560830860534125,
|
| 306 |
+
"forget_loss": 1.9512895960360765e-05,
|
| 307 |
+
"retain_loss": 0.9700671434402466,
|
| 308 |
+
"step": 90
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.3560830860534125,
|
| 312 |
+
"forget_loss": 1.995826096390374e-06,
|
| 313 |
+
"retain_loss": 0.8315430879592896,
|
| 314 |
+
"step": 90
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3560830860534125,
|
| 318 |
+
"forget_loss": 1.571322718518786e-05,
|
| 319 |
+
"retain_loss": 1.208274245262146,
|
| 320 |
+
"step": 90
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.39564787339268054,
|
| 324 |
+
"grad_norm": 2.71875,
|
| 325 |
+
"learning_rate": 4.1028225806451615e-05,
|
| 326 |
+
"loss": 0.944522476196289,
|
| 327 |
+
"step": 100
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.39564787339268054,
|
| 331 |
+
"forget_loss": 4.782319820151315e-07,
|
| 332 |
+
"retain_loss": 0.9833241105079651,
|
| 333 |
+
"step": 100
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.39564787339268054,
|
| 337 |
+
"forget_loss": 2.0109225715714274e-06,
|
| 338 |
+
"retain_loss": 1.0341448783874512,
|
| 339 |
+
"step": 100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.39564787339268054,
|
| 343 |
+
"forget_loss": 6.43863177174353e-06,
|
| 344 |
+
"retain_loss": 1.2469282150268555,
|
| 345 |
+
"step": 100
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.39564787339268054,
|
| 349 |
+
"forget_loss": 1.7480209862696938e-05,
|
| 350 |
+
"retain_loss": 0.5960159301757812,
|
| 351 |
+
"step": 100
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.4352126607319486,
|
| 355 |
+
"grad_norm": 2.4375,
|
| 356 |
+
"learning_rate": 4.002016129032258e-05,
|
| 357 |
+
"loss": 0.8602962493896484,
|
| 358 |
+
"step": 110
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.4352126607319486,
|
| 362 |
+
"forget_loss": 1.1823936802102253e-05,
|
| 363 |
+
"retain_loss": 0.5339686274528503,
|
| 364 |
+
"step": 110
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.4352126607319486,
|
| 368 |
+
"forget_loss": 6.597866075708225e-08,
|
| 369 |
+
"retain_loss": 1.056380033493042,
|
| 370 |
+
"step": 110
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.4352126607319486,
|
| 374 |
+
"forget_loss": 1.9910299670300446e-05,
|
| 375 |
+
"retain_loss": 1.1451334953308105,
|
| 376 |
+
"step": 110
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.4352126607319486,
|
| 380 |
+
"forget_loss": 2.293188572366489e-07,
|
| 381 |
+
"retain_loss": 0.8453196883201599,
|
| 382 |
+
"step": 110
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.47477744807121663,
|
| 386 |
+
"grad_norm": 2.53125,
|
| 387 |
+
"learning_rate": 3.901209677419355e-05,
|
| 388 |
+
"loss": 0.7744930267333985,
|
| 389 |
+
"step": 120
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.47477744807121663,
|
| 393 |
+
"forget_loss": 3.562010078894673e-06,
|
| 394 |
+
"retain_loss": 0.3454712927341461,
|
| 395 |
+
"step": 120
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.47477744807121663,
|
| 399 |
+
"forget_loss": 2.3657979909330606e-05,
|
| 400 |
+
"retain_loss": 0.6900008916854858,
|
| 401 |
+
"step": 120
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.47477744807121663,
|
| 405 |
+
"forget_loss": 7.935936082503758e-06,
|
| 406 |
+
"retain_loss": 1.2215301990509033,
|
| 407 |
+
"step": 120
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.47477744807121663,
|
| 411 |
+
"forget_loss": 3.603380719141569e-06,
|
| 412 |
+
"retain_loss": 0.7156633734703064,
|
| 413 |
+
"step": 120
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.5143422354104846,
|
| 417 |
+
"grad_norm": 2.65625,
|
| 418 |
+
"learning_rate": 3.800403225806452e-05,
|
| 419 |
+
"loss": 0.6265434265136719,
|
| 420 |
+
"step": 130
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.5143422354104846,
|
| 424 |
+
"forget_loss": 3.966476015193621e-06,
|
| 425 |
+
"retain_loss": 0.9189122319221497,
|
| 426 |
+
"step": 130
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.5143422354104846,
|
| 430 |
+
"forget_loss": 1.971156962099485e-07,
|
| 431 |
+
"retain_loss": 0.9686411023139954,
|
| 432 |
+
"step": 130
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.5143422354104846,
|
| 436 |
+
"forget_loss": 7.189528332673945e-07,
|
| 437 |
+
"retain_loss": 0.6004481315612793,
|
| 438 |
+
"step": 130
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.5143422354104846,
|
| 442 |
+
"forget_loss": 6.318293890217319e-05,
|
| 443 |
+
"retain_loss": 0.8465902805328369,
|
| 444 |
+
"step": 130
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5539070227497527,
|
| 448 |
+
"grad_norm": 2.203125,
|
| 449 |
+
"learning_rate": 3.6995967741935484e-05,
|
| 450 |
+
"loss": 0.5954203128814697,
|
| 451 |
+
"step": 140
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5539070227497527,
|
| 455 |
+
"forget_loss": 1.9906601664843038e-06,
|
| 456 |
+
"retain_loss": 0.3101722300052643,
|
| 457 |
+
"step": 140
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5539070227497527,
|
| 461 |
+
"forget_loss": 1.541334859211929e-05,
|
| 462 |
+
"retain_loss": 0.7035630941390991,
|
| 463 |
+
"step": 140
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.5539070227497527,
|
| 467 |
+
"forget_loss": 1.0654130164766684e-06,
|
| 468 |
+
"retain_loss": 0.4943649470806122,
|
| 469 |
+
"step": 140
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.5539070227497527,
|
| 473 |
+
"forget_loss": 7.423601573464111e-07,
|
| 474 |
+
"retain_loss": 0.4140494167804718,
|
| 475 |
+
"step": 140
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.5934718100890207,
|
| 479 |
+
"grad_norm": 1.9453125,
|
| 480 |
+
"learning_rate": 3.598790322580645e-05,
|
| 481 |
+
"loss": 0.5855343818664551,
|
| 482 |
+
"step": 150
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.5934718100890207,
|
| 486 |
+
"forget_loss": 1.361437256264253e-07,
|
| 487 |
+
"retain_loss": 0.4642321467399597,
|
| 488 |
+
"step": 150
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.5934718100890207,
|
| 492 |
+
"forget_loss": 8.585838031649473e-07,
|
| 493 |
+
"retain_loss": 0.27303439378738403,
|
| 494 |
+
"step": 150
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.5934718100890207,
|
| 498 |
+
"forget_loss": 8.958835678640753e-06,
|
| 499 |
+
"retain_loss": 0.8398749828338623,
|
| 500 |
+
"step": 150
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.5934718100890207,
|
| 504 |
+
"forget_loss": 7.379357498393802e-07,
|
| 505 |
+
"retain_loss": 0.1644805520772934,
|
| 506 |
+
"step": 150
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.6330365974282888,
|
| 510 |
+
"grad_norm": 1.9296875,
|
| 511 |
+
"learning_rate": 3.497983870967742e-05,
|
| 512 |
+
"loss": 0.40769476890563966,
|
| 513 |
+
"step": 160
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6330365974282888,
|
| 517 |
+
"forget_loss": 4.321451797295595e-06,
|
| 518 |
+
"retain_loss": 0.6735343337059021,
|
| 519 |
+
"step": 160
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.6330365974282888,
|
| 523 |
+
"forget_loss": 1.2234904716024175e-06,
|
| 524 |
+
"retain_loss": 0.2956700921058655,
|
| 525 |
+
"step": 160
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.6330365974282888,
|
| 529 |
+
"forget_loss": 7.72880184740643e-07,
|
| 530 |
+
"retain_loss": 0.35303422808647156,
|
| 531 |
+
"step": 160
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.6330365974282888,
|
| 535 |
+
"forget_loss": 3.859570369968424e-06,
|
| 536 |
+
"retain_loss": 0.3457622230052948,
|
| 537 |
+
"step": 160
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.6726013847675568,
|
| 541 |
+
"grad_norm": 2.15625,
|
| 542 |
+
"learning_rate": 3.397177419354839e-05,
|
| 543 |
+
"loss": 0.39554681777954104,
|
| 544 |
+
"step": 170
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.6726013847675568,
|
| 548 |
+
"forget_loss": 7.689478138672712e-07,
|
| 549 |
+
"retain_loss": 0.45961564779281616,
|
| 550 |
+
"step": 170
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.6726013847675568,
|
| 554 |
+
"forget_loss": 4.003181288680935e-07,
|
| 555 |
+
"retain_loss": 0.4355284571647644,
|
| 556 |
+
"step": 170
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6726013847675568,
|
| 560 |
+
"forget_loss": 1.2844781167586916e-06,
|
| 561 |
+
"retain_loss": 0.18292923271656036,
|
| 562 |
+
"step": 170
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.6726013847675568,
|
| 566 |
+
"forget_loss": 6.100489372329321e-06,
|
| 567 |
+
"retain_loss": 1.1629327535629272,
|
| 568 |
+
"step": 170
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.712166172106825,
|
| 572 |
+
"grad_norm": 2.21875,
|
| 573 |
+
"learning_rate": 3.296370967741936e-05,
|
| 574 |
+
"loss": 0.37566747665405276,
|
| 575 |
+
"step": 180
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.712166172106825,
|
| 579 |
+
"forget_loss": 1.7554750684212195e-06,
|
| 580 |
+
"retain_loss": 0.2597223222255707,
|
| 581 |
+
"step": 180
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.712166172106825,
|
| 585 |
+
"forget_loss": 3.428482386880205e-07,
|
| 586 |
+
"retain_loss": 0.2552041709423065,
|
| 587 |
+
"step": 180
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.712166172106825,
|
| 591 |
+
"forget_loss": 5.250699359748978e-06,
|
| 592 |
+
"retain_loss": 0.24067796766757965,
|
| 593 |
+
"step": 180
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.712166172106825,
|
| 597 |
+
"forget_loss": 4.978801371180452e-06,
|
| 598 |
+
"retain_loss": 0.3246007561683655,
|
| 599 |
+
"step": 180
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.751730959446093,
|
| 603 |
+
"grad_norm": 2.25,
|
| 604 |
+
"learning_rate": 3.1955645161290326e-05,
|
| 605 |
+
"loss": 0.3259316921234131,
|
| 606 |
+
"step": 190
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.751730959446093,
|
| 610 |
+
"forget_loss": 2.234717385363183e-06,
|
| 611 |
+
"retain_loss": 0.2883687913417816,
|
| 612 |
+
"step": 190
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.751730959446093,
|
| 616 |
+
"forget_loss": 1.0489970009075478e-05,
|
| 617 |
+
"retain_loss": 0.3649686872959137,
|
| 618 |
+
"step": 190
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.751730959446093,
|
| 622 |
+
"forget_loss": 4.861570346292865e-07,
|
| 623 |
+
"retain_loss": 0.08664171397686005,
|
| 624 |
+
"step": 190
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.751730959446093,
|
| 628 |
+
"forget_loss": 1.7122434314842394e-07,
|
| 629 |
+
"retain_loss": 0.5161219835281372,
|
| 630 |
+
"step": 190
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.7912957467853611,
|
| 634 |
+
"grad_norm": 2.046875,
|
| 635 |
+
"learning_rate": 3.0947580645161286e-05,
|
| 636 |
+
"loss": 0.3275477170944214,
|
| 637 |
+
"step": 200
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.7912957467853611,
|
| 641 |
+
"forget_loss": 4.812917268282035e-06,
|
| 642 |
+
"retain_loss": 0.1327330470085144,
|
| 643 |
+
"step": 200
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.7912957467853611,
|
| 647 |
+
"forget_loss": 1.2788243111572228e-05,
|
| 648 |
+
"retain_loss": 0.10285186767578125,
|
| 649 |
+
"step": 200
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.7912957467853611,
|
| 653 |
+
"forget_loss": 1.759683641466836e-06,
|
| 654 |
+
"retain_loss": 0.08815877139568329,
|
| 655 |
+
"step": 200
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.7912957467853611,
|
| 659 |
+
"forget_loss": 1.2591119684657315e-06,
|
| 660 |
+
"retain_loss": 0.21271497011184692,
|
| 661 |
+
"step": 200
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.8308605341246291,
|
| 665 |
+
"grad_norm": 1.671875,
|
| 666 |
+
"learning_rate": 2.9939516129032256e-05,
|
| 667 |
+
"loss": 0.24050042629241944,
|
| 668 |
+
"step": 210
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.8308605341246291,
|
| 672 |
+
"forget_loss": 3.42119274137076e-05,
|
| 673 |
+
"retain_loss": 0.191277414560318,
|
| 674 |
+
"step": 210
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.8308605341246291,
|
| 678 |
+
"forget_loss": 1.4605574278903077e-06,
|
| 679 |
+
"retain_loss": 0.1759226769208908,
|
| 680 |
+
"step": 210
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.8308605341246291,
|
| 684 |
+
"forget_loss": 1.6217817346841912e-06,
|
| 685 |
+
"retain_loss": 0.11556903272867203,
|
| 686 |
+
"step": 210
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.8308605341246291,
|
| 690 |
+
"forget_loss": 5.36894560809742e-07,
|
| 691 |
+
"retain_loss": 0.09534405171871185,
|
| 692 |
+
"step": 210
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.8704253214638972,
|
| 696 |
+
"grad_norm": 1.4375,
|
| 697 |
+
"learning_rate": 2.8931451612903227e-05,
|
| 698 |
+
"loss": 0.21134119033813475,
|
| 699 |
+
"step": 220
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.8704253214638972,
|
| 703 |
+
"forget_loss": 5.595671836999827e-07,
|
| 704 |
+
"retain_loss": 0.06919872760772705,
|
| 705 |
+
"step": 220
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.8704253214638972,
|
| 709 |
+
"forget_loss": 1.3810227983412915e-06,
|
| 710 |
+
"retain_loss": 0.3623019754886627,
|
| 711 |
+
"step": 220
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.8704253214638972,
|
| 715 |
+
"forget_loss": 2.7275791580905207e-07,
|
| 716 |
+
"retain_loss": 0.0580284558236599,
|
| 717 |
+
"step": 220
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.8704253214638972,
|
| 721 |
+
"forget_loss": 2.2396357053366955e-06,
|
| 722 |
+
"retain_loss": 0.07191744446754456,
|
| 723 |
+
"step": 220
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.9099901088031652,
|
| 727 |
+
"grad_norm": 2.015625,
|
| 728 |
+
"learning_rate": 2.7923387096774194e-05,
|
| 729 |
+
"loss": 0.19377652406692505,
|
| 730 |
+
"step": 230
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.9099901088031652,
|
| 734 |
+
"forget_loss": 1.5686964616179466e-06,
|
| 735 |
+
"retain_loss": 0.10832444578409195,
|
| 736 |
+
"step": 230
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.9099901088031652,
|
| 740 |
+
"forget_loss": 1.3601317050415673e-06,
|
| 741 |
+
"retain_loss": 0.09787821769714355,
|
| 742 |
+
"step": 230
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.9099901088031652,
|
| 746 |
+
"forget_loss": 9.028633485286264e-07,
|
| 747 |
+
"retain_loss": 0.26772671937942505,
|
| 748 |
+
"step": 230
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.9099901088031652,
|
| 752 |
+
"forget_loss": 1.0231609621769167e-06,
|
| 753 |
+
"retain_loss": 0.09736587852239609,
|
| 754 |
+
"step": 230
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.9495548961424333,
|
| 758 |
+
"grad_norm": 1.90625,
|
| 759 |
+
"learning_rate": 2.6915322580645164e-05,
|
| 760 |
+
"loss": 0.19356629848480225,
|
| 761 |
+
"step": 240
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.9495548961424333,
|
| 765 |
+
"forget_loss": 4.033423920191126e-06,
|
| 766 |
+
"retain_loss": 0.06074934080243111,
|
| 767 |
+
"step": 240
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.9495548961424333,
|
| 771 |
+
"forget_loss": 3.436478436924517e-06,
|
| 772 |
+
"retain_loss": 0.1828729808330536,
|
| 773 |
+
"step": 240
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.9495548961424333,
|
| 777 |
+
"forget_loss": 1.2162026052919828e-07,
|
| 778 |
+
"retain_loss": 0.05229510739445686,
|
| 779 |
+
"step": 240
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.9495548961424333,
|
| 783 |
+
"forget_loss": 2.5671818093542242e-06,
|
| 784 |
+
"retain_loss": 0.05694460868835449,
|
| 785 |
+
"step": 240
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.9891196834817013,
|
| 789 |
+
"grad_norm": 1.3515625,
|
| 790 |
+
"learning_rate": 2.590725806451613e-05,
|
| 791 |
+
"loss": 0.173517906665802,
|
| 792 |
+
"step": 250
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.9891196834817013,
|
| 796 |
+
"forget_loss": 2.22346602640755e-06,
|
| 797 |
+
"retain_loss": 0.0835813581943512,
|
| 798 |
+
"step": 250
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.9891196834817013,
|
| 802 |
+
"forget_loss": 5.302557838149369e-06,
|
| 803 |
+
"retain_loss": 0.2273225635290146,
|
| 804 |
+
"step": 250
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.9891196834817013,
|
| 808 |
+
"forget_loss": 7.574280061817262e-06,
|
| 809 |
+
"retain_loss": 0.41572776436805725,
|
| 810 |
+
"step": 250
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.9891196834817013,
|
| 814 |
+
"forget_loss": 4.923841743220692e-07,
|
| 815 |
+
"retain_loss": 0.05759130418300629,
|
| 816 |
+
"step": 250
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 1.0276953511374876,
|
| 820 |
+
"grad_norm": 2.078125,
|
| 821 |
+
"learning_rate": 2.48991935483871e-05,
|
| 822 |
+
"loss": 0.14332621097564696,
|
| 823 |
+
"step": 260
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 1.0276953511374876,
|
| 827 |
+
"forget_loss": 2.022331273110467e-06,
|
| 828 |
+
"retain_loss": 0.05112220719456673,
|
| 829 |
+
"step": 260
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.0276953511374876,
|
| 833 |
+
"forget_loss": 1.7422898963559419e-06,
|
| 834 |
+
"retain_loss": 0.15385369956493378,
|
| 835 |
+
"step": 260
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.0276953511374876,
|
| 839 |
+
"forget_loss": 3.312950980216556e-07,
|
| 840 |
+
"retain_loss": 0.19912393391132355,
|
| 841 |
+
"step": 260
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.0276953511374876,
|
| 845 |
+
"forget_loss": 6.443568736358429e-07,
|
| 846 |
+
"retain_loss": 0.055204521864652634,
|
| 847 |
+
"step": 260
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.0672601384767557,
|
| 851 |
+
"grad_norm": 1.46875,
|
| 852 |
+
"learning_rate": 2.3891129032258066e-05,
|
| 853 |
+
"loss": 0.1235049843788147,
|
| 854 |
+
"step": 270
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.0672601384767557,
|
| 858 |
+
"forget_loss": 6.121961177996127e-07,
|
| 859 |
+
"retain_loss": 0.25304123759269714,
|
| 860 |
+
"step": 270
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.0672601384767557,
|
| 864 |
+
"forget_loss": 8.218993343689363e-07,
|
| 865 |
+
"retain_loss": 0.14983095228672028,
|
| 866 |
+
"step": 270
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.0672601384767557,
|
| 870 |
+
"forget_loss": 1.1419467682571849e-06,
|
| 871 |
+
"retain_loss": 0.04056330397725105,
|
| 872 |
+
"step": 270
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.0672601384767557,
|
| 876 |
+
"forget_loss": 1.5871705727477092e-06,
|
| 877 |
+
"retain_loss": 0.03402575105428696,
|
| 878 |
+
"step": 270
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.1068249258160237,
|
| 882 |
+
"grad_norm": 0.98046875,
|
| 883 |
+
"learning_rate": 2.2883064516129033e-05,
|
| 884 |
+
"loss": 0.12284862995147705,
|
| 885 |
+
"step": 280
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.1068249258160237,
|
| 889 |
+
"forget_loss": 2.4364621253880614e-07,
|
| 890 |
+
"retain_loss": 0.039372384548187256,
|
| 891 |
+
"step": 280
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.1068249258160237,
|
| 895 |
+
"forget_loss": 2.9535872272390407e-06,
|
| 896 |
+
"retain_loss": 0.06493150442838669,
|
| 897 |
+
"step": 280
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.1068249258160237,
|
| 901 |
+
"forget_loss": 3.736472535820212e-07,
|
| 902 |
+
"retain_loss": 0.09616785496473312,
|
| 903 |
+
"step": 280
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.1068249258160237,
|
| 907 |
+
"forget_loss": 1.1166291002950857e-08,
|
| 908 |
+
"retain_loss": 0.12201965600252151,
|
| 909 |
+
"step": 280
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.1463897131552918,
|
| 913 |
+
"grad_norm": 1.0703125,
|
| 914 |
+
"learning_rate": 2.1875e-05,
|
| 915 |
+
"loss": 0.09197805523872375,
|
| 916 |
+
"step": 290
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.1463897131552918,
|
| 920 |
+
"forget_loss": 4.085670298081823e-06,
|
| 921 |
+
"retain_loss": 0.0720362663269043,
|
| 922 |
+
"step": 290
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.1463897131552918,
|
| 926 |
+
"forget_loss": 9.525655286779511e-08,
|
| 927 |
+
"retain_loss": 0.05113707482814789,
|
| 928 |
+
"step": 290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 1.1463897131552918,
|
| 932 |
+
"forget_loss": 1.6031831364671234e-06,
|
| 933 |
+
"retain_loss": 0.0687340646982193,
|
| 934 |
+
"step": 290
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.1463897131552918,
|
| 938 |
+
"forget_loss": 2.0602558379323455e-06,
|
| 939 |
+
"retain_loss": 0.21625281870365143,
|
| 940 |
+
"step": 290
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.1859545004945597,
|
| 944 |
+
"grad_norm": 1.2734375,
|
| 945 |
+
"learning_rate": 2.086693548387097e-05,
|
| 946 |
+
"loss": 0.0918435275554657,
|
| 947 |
+
"step": 300
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.1859545004945597,
|
| 951 |
+
"forget_loss": 1.1522879503900185e-06,
|
| 952 |
+
"retain_loss": 0.025093382224440575,
|
| 953 |
+
"step": 300
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.1859545004945597,
|
| 957 |
+
"forget_loss": 2.639731633280462e-07,
|
| 958 |
+
"retain_loss": 0.04188269376754761,
|
| 959 |
+
"step": 300
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.1859545004945597,
|
| 963 |
+
"forget_loss": 3.575230493879644e-06,
|
| 964 |
+
"retain_loss": 0.058530498296022415,
|
| 965 |
+
"step": 300
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.1859545004945597,
|
| 969 |
+
"forget_loss": 4.680264851231186e-07,
|
| 970 |
+
"retain_loss": 0.036610353738069534,
|
| 971 |
+
"step": 300
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.225519287833828,
|
| 975 |
+
"grad_norm": 0.80859375,
|
| 976 |
+
"learning_rate": 1.9858870967741934e-05,
|
| 977 |
+
"loss": 0.07977721691131592,
|
| 978 |
+
"step": 310
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 1.225519287833828,
|
| 982 |
+
"forget_loss": 1.9944478424349654e-07,
|
| 983 |
+
"retain_loss": 0.14079155027866364,
|
| 984 |
+
"step": 310
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.225519287833828,
|
| 988 |
+
"forget_loss": 1.7728395960148191e-06,
|
| 989 |
+
"retain_loss": 0.09404411911964417,
|
| 990 |
+
"step": 310
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.225519287833828,
|
| 994 |
+
"forget_loss": 1.1807240980488132e-06,
|
| 995 |
+
"retain_loss": 0.11878670006990433,
|
| 996 |
+
"step": 310
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.225519287833828,
|
| 1000 |
+
"forget_loss": 6.993744250394229e-07,
|
| 1001 |
+
"retain_loss": 0.08564583957195282,
|
| 1002 |
+
"step": 310
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.265084075173096,
|
| 1006 |
+
"grad_norm": 2.1875,
|
| 1007 |
+
"learning_rate": 1.8850806451612904e-05,
|
| 1008 |
+
"loss": 0.10100387334823609,
|
| 1009 |
+
"step": 320
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.265084075173096,
|
| 1013 |
+
"forget_loss": 9.910125299938954e-06,
|
| 1014 |
+
"retain_loss": 0.06925372779369354,
|
| 1015 |
+
"step": 320
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 1.265084075173096,
|
| 1019 |
+
"forget_loss": 2.2465580968855647e-06,
|
| 1020 |
+
"retain_loss": 0.03531289100646973,
|
| 1021 |
+
"step": 320
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.265084075173096,
|
| 1025 |
+
"forget_loss": 1.5962227450927458e-07,
|
| 1026 |
+
"retain_loss": 0.044194359332323074,
|
| 1027 |
+
"step": 320
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 1.265084075173096,
|
| 1031 |
+
"forget_loss": 4.942241957905935e-07,
|
| 1032 |
+
"retain_loss": 0.062409959733486176,
|
| 1033 |
+
"step": 320
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.304648862512364,
|
| 1037 |
+
"grad_norm": 1.2890625,
|
| 1038 |
+
"learning_rate": 1.784274193548387e-05,
|
| 1039 |
+
"loss": 0.06902462244033813,
|
| 1040 |
+
"step": 330
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.304648862512364,
|
| 1044 |
+
"forget_loss": 6.602442681469256e-07,
|
| 1045 |
+
"retain_loss": 0.04397878423333168,
|
| 1046 |
+
"step": 330
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.304648862512364,
|
| 1050 |
+
"forget_loss": 9.583651490174816e-07,
|
| 1051 |
+
"retain_loss": 0.056344836950302124,
|
| 1052 |
+
"step": 330
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.304648862512364,
|
| 1056 |
+
"forget_loss": 3.47790461319164e-07,
|
| 1057 |
+
"retain_loss": 0.04283231496810913,
|
| 1058 |
+
"step": 330
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.304648862512364,
|
| 1062 |
+
"forget_loss": 7.383774232039286e-07,
|
| 1063 |
+
"retain_loss": 0.2884156107902527,
|
| 1064 |
+
"step": 330
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.344213649851632,
|
| 1068 |
+
"grad_norm": 0.5546875,
|
| 1069 |
+
"learning_rate": 1.683467741935484e-05,
|
| 1070 |
+
"loss": 0.07270175218582153,
|
| 1071 |
+
"step": 340
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 1.344213649851632,
|
| 1075 |
+
"forget_loss": 1.4138665846985532e-06,
|
| 1076 |
+
"retain_loss": 0.030446356162428856,
|
| 1077 |
+
"step": 340
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.344213649851632,
|
| 1081 |
+
"forget_loss": 4.400314992381027e-07,
|
| 1082 |
+
"retain_loss": 0.041316572576761246,
|
| 1083 |
+
"step": 340
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 1.344213649851632,
|
| 1087 |
+
"forget_loss": 8.035279392970551e-07,
|
| 1088 |
+
"retain_loss": 0.4023597836494446,
|
| 1089 |
+
"step": 340
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.344213649851632,
|
| 1093 |
+
"forget_loss": 3.161345887292555e-07,
|
| 1094 |
+
"retain_loss": 0.028397783637046814,
|
| 1095 |
+
"step": 340
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.3837784371909,
|
| 1099 |
+
"grad_norm": 1.484375,
|
| 1100 |
+
"learning_rate": 1.5826612903225806e-05,
|
| 1101 |
+
"loss": 0.07099369764328003,
|
| 1102 |
+
"step": 350
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.3837784371909,
|
| 1106 |
+
"forget_loss": 8.570134468754986e-07,
|
| 1107 |
+
"retain_loss": 0.026840655133128166,
|
| 1108 |
+
"step": 350
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.3837784371909,
|
| 1112 |
+
"forget_loss": 4.2903576513708686e-07,
|
| 1113 |
+
"retain_loss": 0.045387767255306244,
|
| 1114 |
+
"step": 350
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.3837784371909,
|
| 1118 |
+
"forget_loss": 8.26216322025175e-08,
|
| 1119 |
+
"retain_loss": 0.06860622763633728,
|
| 1120 |
+
"step": 350
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 1.3837784371909,
|
| 1124 |
+
"forget_loss": 8.852501309775107e-08,
|
| 1125 |
+
"retain_loss": 0.21477188169956207,
|
| 1126 |
+
"step": 350
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.4233432245301683,
|
| 1130 |
+
"grad_norm": 1.953125,
|
| 1131 |
+
"learning_rate": 1.4818548387096776e-05,
|
| 1132 |
+
"loss": 0.07751677036285401,
|
| 1133 |
+
"step": 360
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.4233432245301683,
|
| 1137 |
+
"forget_loss": 1.4736333469045348e-06,
|
| 1138 |
+
"retain_loss": 0.049729909747838974,
|
| 1139 |
+
"step": 360
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 1.4233432245301683,
|
| 1143 |
+
"forget_loss": 2.1971384001062688e-07,
|
| 1144 |
+
"retain_loss": 0.023645324632525444,
|
| 1145 |
+
"step": 360
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.4233432245301683,
|
| 1149 |
+
"forget_loss": 6.915368544468947e-07,
|
| 1150 |
+
"retain_loss": 0.04990541562438011,
|
| 1151 |
+
"step": 360
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.4233432245301683,
|
| 1155 |
+
"forget_loss": 1.2885877254120714e-07,
|
| 1156 |
+
"retain_loss": 0.02339594066143036,
|
| 1157 |
+
"step": 360
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.4629080118694362,
|
| 1161 |
+
"grad_norm": 0.73828125,
|
| 1162 |
+
"learning_rate": 1.3810483870967741e-05,
|
| 1163 |
+
"loss": 0.0555726408958435,
|
| 1164 |
+
"step": 370
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.4629080118694362,
|
| 1168 |
+
"forget_loss": 1.0162235639654682e-06,
|
| 1169 |
+
"retain_loss": 0.039157990366220474,
|
| 1170 |
+
"step": 370
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.4629080118694362,
|
| 1174 |
+
"forget_loss": 2.873887865462166e-07,
|
| 1175 |
+
"retain_loss": 0.043322984129190445,
|
| 1176 |
+
"step": 370
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 1.4629080118694362,
|
| 1180 |
+
"forget_loss": 1.5368651702374336e-06,
|
| 1181 |
+
"retain_loss": 0.027565972879529,
|
| 1182 |
+
"step": 370
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.4629080118694362,
|
| 1186 |
+
"forget_loss": 1.5365935723821167e-06,
|
| 1187 |
+
"retain_loss": 0.11519625037908554,
|
| 1188 |
+
"step": 370
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 1.5024727992087041,
|
| 1192 |
+
"grad_norm": 0.859375,
|
| 1193 |
+
"learning_rate": 1.280241935483871e-05,
|
| 1194 |
+
"loss": 0.05110462307929993,
|
| 1195 |
+
"step": 380
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 1.5024727992087041,
|
| 1199 |
+
"forget_loss": 7.83655764280411e-07,
|
| 1200 |
+
"retain_loss": 0.05130387097597122,
|
| 1201 |
+
"step": 380
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 1.5024727992087041,
|
| 1205 |
+
"forget_loss": 5.978235094517004e-06,
|
| 1206 |
+
"retain_loss": 0.027177350595593452,
|
| 1207 |
+
"step": 380
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.5024727992087041,
|
| 1211 |
+
"forget_loss": 3.0234426162678574e-07,
|
| 1212 |
+
"retain_loss": 0.024828054010868073,
|
| 1213 |
+
"step": 380
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.5024727992087041,
|
| 1217 |
+
"forget_loss": 1.2347620703678786e-08,
|
| 1218 |
+
"retain_loss": 0.04538526013493538,
|
| 1219 |
+
"step": 380
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 1.5420375865479723,
|
| 1223 |
+
"grad_norm": 0.55859375,
|
| 1224 |
+
"learning_rate": 1.1794354838709679e-05,
|
| 1225 |
+
"loss": 0.057669293880462644,
|
| 1226 |
+
"step": 390
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 1.5420375865479723,
|
| 1230 |
+
"forget_loss": 8.569641067879274e-07,
|
| 1231 |
+
"retain_loss": 0.03606370836496353,
|
| 1232 |
+
"step": 390
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.5420375865479723,
|
| 1236 |
+
"forget_loss": 6.569359811692266e-07,
|
| 1237 |
+
"retain_loss": 0.03508085012435913,
|
| 1238 |
+
"step": 390
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.5420375865479723,
|
| 1242 |
+
"forget_loss": 1.5997493107988703e-07,
|
| 1243 |
+
"retain_loss": 0.042272500693798065,
|
| 1244 |
+
"step": 390
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 1.5420375865479723,
|
| 1248 |
+
"forget_loss": 2.9301961035343993e-07,
|
| 1249 |
+
"retain_loss": 0.022033188492059708,
|
| 1250 |
+
"step": 390
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.5816023738872405,
|
| 1254 |
+
"grad_norm": 0.95703125,
|
| 1255 |
+
"learning_rate": 1.0786290322580646e-05,
|
| 1256 |
+
"loss": 0.050089681148529054,
|
| 1257 |
+
"step": 400
|
| 1258 |
+
}
|
| 1259 |
+
],
|
| 1260 |
+
"logging_steps": 10,
|
| 1261 |
+
"max_steps": 506,
|
| 1262 |
+
"num_input_tokens_seen": 0,
|
| 1263 |
+
"num_train_epochs": 2,
|
| 1264 |
+
"save_steps": 200,
|
| 1265 |
+
"stateful_callbacks": {
|
| 1266 |
+
"TrainerControl": {
|
| 1267 |
+
"args": {
|
| 1268 |
+
"should_epoch_stop": false,
|
| 1269 |
+
"should_evaluate": false,
|
| 1270 |
+
"should_log": false,
|
| 1271 |
+
"should_save": true,
|
| 1272 |
+
"should_training_stop": false
|
| 1273 |
+
},
|
| 1274 |
+
"attributes": {}
|
| 1275 |
+
}
|
| 1276 |
+
},
|
| 1277 |
+
"total_flos": 0.0,
|
| 1278 |
+
"train_batch_size": 8,
|
| 1279 |
+
"trial_name": null,
|
| 1280 |
+
"trial_params": null
|
| 1281 |
+
}
|
checkpoint-400/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7587f27094c5b0d28888635edb5fb75b1840350b6c54434f3d8d48a5fdd7e2f
|
| 3 |
+
size 5329
|
checkpoint-506/config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Olmo3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"sliding_attention",
|
| 16 |
+
"sliding_attention",
|
| 17 |
+
"sliding_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"sliding_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"full_attention"
|
| 47 |
+
],
|
| 48 |
+
"max_position_embeddings": 65536,
|
| 49 |
+
"model_type": "olmo3",
|
| 50 |
+
"num_attention_heads": 32,
|
| 51 |
+
"num_hidden_layers": 32,
|
| 52 |
+
"num_key_value_heads": 32,
|
| 53 |
+
"pad_token_id": 100277,
|
| 54 |
+
"rms_norm_eps": 1e-06,
|
| 55 |
+
"rope_parameters": {
|
| 56 |
+
"attention_factor": 1.2079441541679836,
|
| 57 |
+
"beta_fast": 32.0,
|
| 58 |
+
"beta_slow": 1.0,
|
| 59 |
+
"factor": 8.0,
|
| 60 |
+
"original_max_position_embeddings": 8192,
|
| 61 |
+
"rope_theta": 500000,
|
| 62 |
+
"rope_type": "yarn"
|
| 63 |
+
},
|
| 64 |
+
"sliding_window": 4096,
|
| 65 |
+
"tie_word_embeddings": false,
|
| 66 |
+
"transformers_version": "5.6.0",
|
| 67 |
+
"use_cache": false,
|
| 68 |
+
"vocab_size": 100278
|
| 69 |
+
}
|
checkpoint-506/generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
100257
|
| 5 |
+
],
|
| 6 |
+
"pad_token_id": 100277,
|
| 7 |
+
"transformers_version": "5.6.0"
|
| 8 |
+
}
|
checkpoint-506/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8df81fd1ff28a8bc31b9efb605fa4d68414a7ae5451dc8224d2782cca686bbd6
|
| 3 |
+
size 14596063960
|
checkpoint-506/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3df67fd47b0f7c6ad3270a9e3fd0478ef13b4c5f79cd7b2ba1b4176f3a952324
|
| 3 |
+
size 29192355324
|
checkpoint-506/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8956475db3ce7477fd0463f0e9641574185340f14311790dc13e892a643a795f
|
| 3 |
+
size 14645
|
checkpoint-506/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a3ac4ea8061380d85ab8e69881cdfd78bf53079961fa435202cd24caa05efe1c
|
| 3 |
+
size 1465
|
checkpoint-506/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-506/tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": false,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"model_max_length": 65536,
|
| 11 |
+
"pad_token": "<|pad|>",
|
| 12 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 13 |
+
"unk_token": "<|endoftext|>"
|
| 14 |
+
}
|
checkpoint-506/trainer_state.json
ADDED
|
@@ -0,0 +1,1615 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 506,
|
| 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,
|
| 14 |
+
"forget_loss": 0.14035749435424805,
|
| 15 |
+
"retain_loss": 2.6653778553009033,
|
| 16 |
+
"step": 0
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0,
|
| 20 |
+
"forget_loss": 0.19487237930297852,
|
| 21 |
+
"retain_loss": 2.794126033782959,
|
| 22 |
+
"step": 0
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0,
|
| 26 |
+
"forget_loss": 0.1652039885520935,
|
| 27 |
+
"retain_loss": 2.7992446422576904,
|
| 28 |
+
"step": 0
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0,
|
| 32 |
+
"forget_loss": 0.25970637798309326,
|
| 33 |
+
"retain_loss": 2.7407283782958984,
|
| 34 |
+
"step": 0
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.003956478733926805,
|
| 38 |
+
"grad_norm": 10.1875,
|
| 39 |
+
"learning_rate": 0.0,
|
| 40 |
+
"loss": 3.700044631958008,
|
| 41 |
+
"step": 1
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.03956478733926805,
|
| 45 |
+
"grad_norm": 2.390625,
|
| 46 |
+
"learning_rate": 4.5e-05,
|
| 47 |
+
"loss": 2.9271229637993708,
|
| 48 |
+
"step": 10
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.03956478733926805,
|
| 52 |
+
"forget_loss": 0.0006051036179997027,
|
| 53 |
+
"retain_loss": 2.075515031814575,
|
| 54 |
+
"step": 10
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.03956478733926805,
|
| 58 |
+
"forget_loss": 0.0002671501424629241,
|
| 59 |
+
"retain_loss": 2.2641794681549072,
|
| 60 |
+
"step": 10
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.03956478733926805,
|
| 64 |
+
"forget_loss": 0.00017286122601944953,
|
| 65 |
+
"retain_loss": 2.1814846992492676,
|
| 66 |
+
"step": 10
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.03956478733926805,
|
| 70 |
+
"forget_loss": 0.0006279755616560578,
|
| 71 |
+
"retain_loss": 2.482621669769287,
|
| 72 |
+
"step": 10
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.0791295746785361,
|
| 76 |
+
"grad_norm": 2.21875,
|
| 77 |
+
"learning_rate": 4.909274193548387e-05,
|
| 78 |
+
"loss": 2.182495880126953,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0791295746785361,
|
| 83 |
+
"forget_loss": 3.0431343475356698e-05,
|
| 84 |
+
"retain_loss": 2.0565364360809326,
|
| 85 |
+
"step": 20
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.0791295746785361,
|
| 89 |
+
"forget_loss": 1.2637827239814214e-05,
|
| 90 |
+
"retain_loss": 1.9916024208068848,
|
| 91 |
+
"step": 20
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.0791295746785361,
|
| 95 |
+
"forget_loss": 8.099855767795816e-05,
|
| 96 |
+
"retain_loss": 2.1353280544281006,
|
| 97 |
+
"step": 20
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.0791295746785361,
|
| 101 |
+
"forget_loss": 4.038449696963653e-05,
|
| 102 |
+
"retain_loss": 1.7972193956375122,
|
| 103 |
+
"step": 20
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.11869436201780416,
|
| 107 |
+
"grad_norm": 2.015625,
|
| 108 |
+
"learning_rate": 4.808467741935484e-05,
|
| 109 |
+
"loss": 1.9499595642089844,
|
| 110 |
+
"step": 30
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.11869436201780416,
|
| 114 |
+
"forget_loss": 2.020488636844675e-06,
|
| 115 |
+
"retain_loss": 1.9730969667434692,
|
| 116 |
+
"step": 30
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.11869436201780416,
|
| 120 |
+
"forget_loss": 8.556620514355018e-07,
|
| 121 |
+
"retain_loss": 2.1347737312316895,
|
| 122 |
+
"step": 30
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.11869436201780416,
|
| 126 |
+
"forget_loss": 1.441345830244245e-05,
|
| 127 |
+
"retain_loss": 1.753809928894043,
|
| 128 |
+
"step": 30
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.11869436201780416,
|
| 132 |
+
"forget_loss": 2.9243692551972345e-05,
|
| 133 |
+
"retain_loss": 2.3272459506988525,
|
| 134 |
+
"step": 30
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.1582591493570722,
|
| 138 |
+
"grad_norm": 1.9453125,
|
| 139 |
+
"learning_rate": 4.7076612903225806e-05,
|
| 140 |
+
"loss": 1.789834213256836,
|
| 141 |
+
"step": 40
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.1582591493570722,
|
| 145 |
+
"forget_loss": 2.2786582121625543e-05,
|
| 146 |
+
"retain_loss": 1.5727999210357666,
|
| 147 |
+
"step": 40
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.1582591493570722,
|
| 151 |
+
"forget_loss": 2.68079929810483e-05,
|
| 152 |
+
"retain_loss": 1.0978410243988037,
|
| 153 |
+
"step": 40
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.1582591493570722,
|
| 157 |
+
"forget_loss": 2.065206535917241e-05,
|
| 158 |
+
"retain_loss": 2.0460541248321533,
|
| 159 |
+
"step": 40
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.1582591493570722,
|
| 163 |
+
"forget_loss": 5.7086062952294014e-06,
|
| 164 |
+
"retain_loss": 1.6670787334442139,
|
| 165 |
+
"step": 40
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.19782393669634027,
|
| 169 |
+
"grad_norm": 1.9609375,
|
| 170 |
+
"learning_rate": 4.606854838709678e-05,
|
| 171 |
+
"loss": 1.5417665481567382,
|
| 172 |
+
"step": 50
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.19782393669634027,
|
| 176 |
+
"forget_loss": 1.4016513887327164e-05,
|
| 177 |
+
"retain_loss": 1.7037866115570068,
|
| 178 |
+
"step": 50
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.19782393669634027,
|
| 182 |
+
"forget_loss": 5.568679171119584e-06,
|
| 183 |
+
"retain_loss": 1.2811342477798462,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.19782393669634027,
|
| 188 |
+
"forget_loss": 1.4726042536494788e-06,
|
| 189 |
+
"retain_loss": 1.7753159999847412,
|
| 190 |
+
"step": 50
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.19782393669634027,
|
| 194 |
+
"forget_loss": 1.6467790828755824e-06,
|
| 195 |
+
"retain_loss": 1.40712571144104,
|
| 196 |
+
"step": 50
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.23738872403560832,
|
| 200 |
+
"grad_norm": 2.28125,
|
| 201 |
+
"learning_rate": 4.506048387096775e-05,
|
| 202 |
+
"loss": 1.460409927368164,
|
| 203 |
+
"step": 60
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.23738872403560832,
|
| 207 |
+
"forget_loss": 8.811715815681964e-06,
|
| 208 |
+
"retain_loss": 1.8770829439163208,
|
| 209 |
+
"step": 60
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.23738872403560832,
|
| 213 |
+
"forget_loss": 9.250835319107864e-06,
|
| 214 |
+
"retain_loss": 1.1297162771224976,
|
| 215 |
+
"step": 60
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.23738872403560832,
|
| 219 |
+
"forget_loss": 5.8820231060963124e-05,
|
| 220 |
+
"retain_loss": 1.0866577625274658,
|
| 221 |
+
"step": 60
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.23738872403560832,
|
| 225 |
+
"forget_loss": 3.214211119484389e-06,
|
| 226 |
+
"retain_loss": 1.241797924041748,
|
| 227 |
+
"step": 60
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.27695351137487634,
|
| 231 |
+
"grad_norm": 2.09375,
|
| 232 |
+
"learning_rate": 4.4052419354838714e-05,
|
| 233 |
+
"loss": 1.3480111122131349,
|
| 234 |
+
"step": 70
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.27695351137487634,
|
| 238 |
+
"forget_loss": 2.020563988480717e-05,
|
| 239 |
+
"retain_loss": 1.2503434419631958,
|
| 240 |
+
"step": 70
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.27695351137487634,
|
| 244 |
+
"forget_loss": 1.9923185391235165e-05,
|
| 245 |
+
"retain_loss": 1.423868179321289,
|
| 246 |
+
"step": 70
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.27695351137487634,
|
| 250 |
+
"forget_loss": 1.3452325902107987e-06,
|
| 251 |
+
"retain_loss": 0.9821794629096985,
|
| 252 |
+
"step": 70
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.27695351137487634,
|
| 256 |
+
"forget_loss": 1.3409412531473208e-06,
|
| 257 |
+
"retain_loss": 1.3942550420761108,
|
| 258 |
+
"step": 70
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.3165182987141444,
|
| 262 |
+
"grad_norm": 2.40625,
|
| 263 |
+
"learning_rate": 4.3044354838709674e-05,
|
| 264 |
+
"loss": 1.2137460708618164,
|
| 265 |
+
"step": 80
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.3165182987141444,
|
| 269 |
+
"forget_loss": 1.4205611478246283e-06,
|
| 270 |
+
"retain_loss": 1.0372614860534668,
|
| 271 |
+
"step": 80
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.3165182987141444,
|
| 275 |
+
"forget_loss": 1.3158517504052725e-05,
|
| 276 |
+
"retain_loss": 1.0091803073883057,
|
| 277 |
+
"step": 80
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.3165182987141444,
|
| 281 |
+
"forget_loss": 1.1485619324957952e-05,
|
| 282 |
+
"retain_loss": 0.8734372854232788,
|
| 283 |
+
"step": 80
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3165182987141444,
|
| 287 |
+
"forget_loss": 3.980534017955506e-07,
|
| 288 |
+
"retain_loss": 0.8553104996681213,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.3560830860534125,
|
| 293 |
+
"grad_norm": 2.40625,
|
| 294 |
+
"learning_rate": 4.203629032258065e-05,
|
| 295 |
+
"loss": 1.1432867050170898,
|
| 296 |
+
"step": 90
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3560830860534125,
|
| 300 |
+
"forget_loss": 2.3974775103852153e-05,
|
| 301 |
+
"retain_loss": 0.8748829364776611,
|
| 302 |
+
"step": 90
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.3560830860534125,
|
| 306 |
+
"forget_loss": 1.9512895960360765e-05,
|
| 307 |
+
"retain_loss": 0.9700671434402466,
|
| 308 |
+
"step": 90
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.3560830860534125,
|
| 312 |
+
"forget_loss": 1.995826096390374e-06,
|
| 313 |
+
"retain_loss": 0.8315430879592896,
|
| 314 |
+
"step": 90
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3560830860534125,
|
| 318 |
+
"forget_loss": 1.571322718518786e-05,
|
| 319 |
+
"retain_loss": 1.208274245262146,
|
| 320 |
+
"step": 90
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.39564787339268054,
|
| 324 |
+
"grad_norm": 2.71875,
|
| 325 |
+
"learning_rate": 4.1028225806451615e-05,
|
| 326 |
+
"loss": 0.944522476196289,
|
| 327 |
+
"step": 100
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.39564787339268054,
|
| 331 |
+
"forget_loss": 4.782319820151315e-07,
|
| 332 |
+
"retain_loss": 0.9833241105079651,
|
| 333 |
+
"step": 100
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.39564787339268054,
|
| 337 |
+
"forget_loss": 2.0109225715714274e-06,
|
| 338 |
+
"retain_loss": 1.0341448783874512,
|
| 339 |
+
"step": 100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.39564787339268054,
|
| 343 |
+
"forget_loss": 6.43863177174353e-06,
|
| 344 |
+
"retain_loss": 1.2469282150268555,
|
| 345 |
+
"step": 100
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.39564787339268054,
|
| 349 |
+
"forget_loss": 1.7480209862696938e-05,
|
| 350 |
+
"retain_loss": 0.5960159301757812,
|
| 351 |
+
"step": 100
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.4352126607319486,
|
| 355 |
+
"grad_norm": 2.4375,
|
| 356 |
+
"learning_rate": 4.002016129032258e-05,
|
| 357 |
+
"loss": 0.8602962493896484,
|
| 358 |
+
"step": 110
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.4352126607319486,
|
| 362 |
+
"forget_loss": 1.1823936802102253e-05,
|
| 363 |
+
"retain_loss": 0.5339686274528503,
|
| 364 |
+
"step": 110
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.4352126607319486,
|
| 368 |
+
"forget_loss": 6.597866075708225e-08,
|
| 369 |
+
"retain_loss": 1.056380033493042,
|
| 370 |
+
"step": 110
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.4352126607319486,
|
| 374 |
+
"forget_loss": 1.9910299670300446e-05,
|
| 375 |
+
"retain_loss": 1.1451334953308105,
|
| 376 |
+
"step": 110
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.4352126607319486,
|
| 380 |
+
"forget_loss": 2.293188572366489e-07,
|
| 381 |
+
"retain_loss": 0.8453196883201599,
|
| 382 |
+
"step": 110
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.47477744807121663,
|
| 386 |
+
"grad_norm": 2.53125,
|
| 387 |
+
"learning_rate": 3.901209677419355e-05,
|
| 388 |
+
"loss": 0.7744930267333985,
|
| 389 |
+
"step": 120
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.47477744807121663,
|
| 393 |
+
"forget_loss": 3.562010078894673e-06,
|
| 394 |
+
"retain_loss": 0.3454712927341461,
|
| 395 |
+
"step": 120
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.47477744807121663,
|
| 399 |
+
"forget_loss": 2.3657979909330606e-05,
|
| 400 |
+
"retain_loss": 0.6900008916854858,
|
| 401 |
+
"step": 120
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.47477744807121663,
|
| 405 |
+
"forget_loss": 7.935936082503758e-06,
|
| 406 |
+
"retain_loss": 1.2215301990509033,
|
| 407 |
+
"step": 120
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.47477744807121663,
|
| 411 |
+
"forget_loss": 3.603380719141569e-06,
|
| 412 |
+
"retain_loss": 0.7156633734703064,
|
| 413 |
+
"step": 120
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.5143422354104846,
|
| 417 |
+
"grad_norm": 2.65625,
|
| 418 |
+
"learning_rate": 3.800403225806452e-05,
|
| 419 |
+
"loss": 0.6265434265136719,
|
| 420 |
+
"step": 130
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.5143422354104846,
|
| 424 |
+
"forget_loss": 3.966476015193621e-06,
|
| 425 |
+
"retain_loss": 0.9189122319221497,
|
| 426 |
+
"step": 130
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.5143422354104846,
|
| 430 |
+
"forget_loss": 1.971156962099485e-07,
|
| 431 |
+
"retain_loss": 0.9686411023139954,
|
| 432 |
+
"step": 130
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.5143422354104846,
|
| 436 |
+
"forget_loss": 7.189528332673945e-07,
|
| 437 |
+
"retain_loss": 0.6004481315612793,
|
| 438 |
+
"step": 130
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.5143422354104846,
|
| 442 |
+
"forget_loss": 6.318293890217319e-05,
|
| 443 |
+
"retain_loss": 0.8465902805328369,
|
| 444 |
+
"step": 130
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5539070227497527,
|
| 448 |
+
"grad_norm": 2.203125,
|
| 449 |
+
"learning_rate": 3.6995967741935484e-05,
|
| 450 |
+
"loss": 0.5954203128814697,
|
| 451 |
+
"step": 140
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5539070227497527,
|
| 455 |
+
"forget_loss": 1.9906601664843038e-06,
|
| 456 |
+
"retain_loss": 0.3101722300052643,
|
| 457 |
+
"step": 140
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5539070227497527,
|
| 461 |
+
"forget_loss": 1.541334859211929e-05,
|
| 462 |
+
"retain_loss": 0.7035630941390991,
|
| 463 |
+
"step": 140
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.5539070227497527,
|
| 467 |
+
"forget_loss": 1.0654130164766684e-06,
|
| 468 |
+
"retain_loss": 0.4943649470806122,
|
| 469 |
+
"step": 140
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.5539070227497527,
|
| 473 |
+
"forget_loss": 7.423601573464111e-07,
|
| 474 |
+
"retain_loss": 0.4140494167804718,
|
| 475 |
+
"step": 140
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.5934718100890207,
|
| 479 |
+
"grad_norm": 1.9453125,
|
| 480 |
+
"learning_rate": 3.598790322580645e-05,
|
| 481 |
+
"loss": 0.5855343818664551,
|
| 482 |
+
"step": 150
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.5934718100890207,
|
| 486 |
+
"forget_loss": 1.361437256264253e-07,
|
| 487 |
+
"retain_loss": 0.4642321467399597,
|
| 488 |
+
"step": 150
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.5934718100890207,
|
| 492 |
+
"forget_loss": 8.585838031649473e-07,
|
| 493 |
+
"retain_loss": 0.27303439378738403,
|
| 494 |
+
"step": 150
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.5934718100890207,
|
| 498 |
+
"forget_loss": 8.958835678640753e-06,
|
| 499 |
+
"retain_loss": 0.8398749828338623,
|
| 500 |
+
"step": 150
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.5934718100890207,
|
| 504 |
+
"forget_loss": 7.379357498393802e-07,
|
| 505 |
+
"retain_loss": 0.1644805520772934,
|
| 506 |
+
"step": 150
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.6330365974282888,
|
| 510 |
+
"grad_norm": 1.9296875,
|
| 511 |
+
"learning_rate": 3.497983870967742e-05,
|
| 512 |
+
"loss": 0.40769476890563966,
|
| 513 |
+
"step": 160
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6330365974282888,
|
| 517 |
+
"forget_loss": 4.321451797295595e-06,
|
| 518 |
+
"retain_loss": 0.6735343337059021,
|
| 519 |
+
"step": 160
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.6330365974282888,
|
| 523 |
+
"forget_loss": 1.2234904716024175e-06,
|
| 524 |
+
"retain_loss": 0.2956700921058655,
|
| 525 |
+
"step": 160
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.6330365974282888,
|
| 529 |
+
"forget_loss": 7.72880184740643e-07,
|
| 530 |
+
"retain_loss": 0.35303422808647156,
|
| 531 |
+
"step": 160
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.6330365974282888,
|
| 535 |
+
"forget_loss": 3.859570369968424e-06,
|
| 536 |
+
"retain_loss": 0.3457622230052948,
|
| 537 |
+
"step": 160
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.6726013847675568,
|
| 541 |
+
"grad_norm": 2.15625,
|
| 542 |
+
"learning_rate": 3.397177419354839e-05,
|
| 543 |
+
"loss": 0.39554681777954104,
|
| 544 |
+
"step": 170
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.6726013847675568,
|
| 548 |
+
"forget_loss": 7.689478138672712e-07,
|
| 549 |
+
"retain_loss": 0.45961564779281616,
|
| 550 |
+
"step": 170
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.6726013847675568,
|
| 554 |
+
"forget_loss": 4.003181288680935e-07,
|
| 555 |
+
"retain_loss": 0.4355284571647644,
|
| 556 |
+
"step": 170
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6726013847675568,
|
| 560 |
+
"forget_loss": 1.2844781167586916e-06,
|
| 561 |
+
"retain_loss": 0.18292923271656036,
|
| 562 |
+
"step": 170
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.6726013847675568,
|
| 566 |
+
"forget_loss": 6.100489372329321e-06,
|
| 567 |
+
"retain_loss": 1.1629327535629272,
|
| 568 |
+
"step": 170
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.712166172106825,
|
| 572 |
+
"grad_norm": 2.21875,
|
| 573 |
+
"learning_rate": 3.296370967741936e-05,
|
| 574 |
+
"loss": 0.37566747665405276,
|
| 575 |
+
"step": 180
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.712166172106825,
|
| 579 |
+
"forget_loss": 1.7554750684212195e-06,
|
| 580 |
+
"retain_loss": 0.2597223222255707,
|
| 581 |
+
"step": 180
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.712166172106825,
|
| 585 |
+
"forget_loss": 3.428482386880205e-07,
|
| 586 |
+
"retain_loss": 0.2552041709423065,
|
| 587 |
+
"step": 180
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.712166172106825,
|
| 591 |
+
"forget_loss": 5.250699359748978e-06,
|
| 592 |
+
"retain_loss": 0.24067796766757965,
|
| 593 |
+
"step": 180
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.712166172106825,
|
| 597 |
+
"forget_loss": 4.978801371180452e-06,
|
| 598 |
+
"retain_loss": 0.3246007561683655,
|
| 599 |
+
"step": 180
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.751730959446093,
|
| 603 |
+
"grad_norm": 2.25,
|
| 604 |
+
"learning_rate": 3.1955645161290326e-05,
|
| 605 |
+
"loss": 0.3259316921234131,
|
| 606 |
+
"step": 190
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.751730959446093,
|
| 610 |
+
"forget_loss": 2.234717385363183e-06,
|
| 611 |
+
"retain_loss": 0.2883687913417816,
|
| 612 |
+
"step": 190
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.751730959446093,
|
| 616 |
+
"forget_loss": 1.0489970009075478e-05,
|
| 617 |
+
"retain_loss": 0.3649686872959137,
|
| 618 |
+
"step": 190
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.751730959446093,
|
| 622 |
+
"forget_loss": 4.861570346292865e-07,
|
| 623 |
+
"retain_loss": 0.08664171397686005,
|
| 624 |
+
"step": 190
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.751730959446093,
|
| 628 |
+
"forget_loss": 1.7122434314842394e-07,
|
| 629 |
+
"retain_loss": 0.5161219835281372,
|
| 630 |
+
"step": 190
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.7912957467853611,
|
| 634 |
+
"grad_norm": 2.046875,
|
| 635 |
+
"learning_rate": 3.0947580645161286e-05,
|
| 636 |
+
"loss": 0.3275477170944214,
|
| 637 |
+
"step": 200
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.7912957467853611,
|
| 641 |
+
"forget_loss": 4.812917268282035e-06,
|
| 642 |
+
"retain_loss": 0.1327330470085144,
|
| 643 |
+
"step": 200
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.7912957467853611,
|
| 647 |
+
"forget_loss": 1.2788243111572228e-05,
|
| 648 |
+
"retain_loss": 0.10285186767578125,
|
| 649 |
+
"step": 200
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.7912957467853611,
|
| 653 |
+
"forget_loss": 1.759683641466836e-06,
|
| 654 |
+
"retain_loss": 0.08815877139568329,
|
| 655 |
+
"step": 200
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.7912957467853611,
|
| 659 |
+
"forget_loss": 1.2591119684657315e-06,
|
| 660 |
+
"retain_loss": 0.21271497011184692,
|
| 661 |
+
"step": 200
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.8308605341246291,
|
| 665 |
+
"grad_norm": 1.671875,
|
| 666 |
+
"learning_rate": 2.9939516129032256e-05,
|
| 667 |
+
"loss": 0.24050042629241944,
|
| 668 |
+
"step": 210
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.8308605341246291,
|
| 672 |
+
"forget_loss": 3.42119274137076e-05,
|
| 673 |
+
"retain_loss": 0.191277414560318,
|
| 674 |
+
"step": 210
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.8308605341246291,
|
| 678 |
+
"forget_loss": 1.4605574278903077e-06,
|
| 679 |
+
"retain_loss": 0.1759226769208908,
|
| 680 |
+
"step": 210
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.8308605341246291,
|
| 684 |
+
"forget_loss": 1.6217817346841912e-06,
|
| 685 |
+
"retain_loss": 0.11556903272867203,
|
| 686 |
+
"step": 210
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.8308605341246291,
|
| 690 |
+
"forget_loss": 5.36894560809742e-07,
|
| 691 |
+
"retain_loss": 0.09534405171871185,
|
| 692 |
+
"step": 210
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.8704253214638972,
|
| 696 |
+
"grad_norm": 1.4375,
|
| 697 |
+
"learning_rate": 2.8931451612903227e-05,
|
| 698 |
+
"loss": 0.21134119033813475,
|
| 699 |
+
"step": 220
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.8704253214638972,
|
| 703 |
+
"forget_loss": 5.595671836999827e-07,
|
| 704 |
+
"retain_loss": 0.06919872760772705,
|
| 705 |
+
"step": 220
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.8704253214638972,
|
| 709 |
+
"forget_loss": 1.3810227983412915e-06,
|
| 710 |
+
"retain_loss": 0.3623019754886627,
|
| 711 |
+
"step": 220
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.8704253214638972,
|
| 715 |
+
"forget_loss": 2.7275791580905207e-07,
|
| 716 |
+
"retain_loss": 0.0580284558236599,
|
| 717 |
+
"step": 220
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.8704253214638972,
|
| 721 |
+
"forget_loss": 2.2396357053366955e-06,
|
| 722 |
+
"retain_loss": 0.07191744446754456,
|
| 723 |
+
"step": 220
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.9099901088031652,
|
| 727 |
+
"grad_norm": 2.015625,
|
| 728 |
+
"learning_rate": 2.7923387096774194e-05,
|
| 729 |
+
"loss": 0.19377652406692505,
|
| 730 |
+
"step": 230
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.9099901088031652,
|
| 734 |
+
"forget_loss": 1.5686964616179466e-06,
|
| 735 |
+
"retain_loss": 0.10832444578409195,
|
| 736 |
+
"step": 230
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.9099901088031652,
|
| 740 |
+
"forget_loss": 1.3601317050415673e-06,
|
| 741 |
+
"retain_loss": 0.09787821769714355,
|
| 742 |
+
"step": 230
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.9099901088031652,
|
| 746 |
+
"forget_loss": 9.028633485286264e-07,
|
| 747 |
+
"retain_loss": 0.26772671937942505,
|
| 748 |
+
"step": 230
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.9099901088031652,
|
| 752 |
+
"forget_loss": 1.0231609621769167e-06,
|
| 753 |
+
"retain_loss": 0.09736587852239609,
|
| 754 |
+
"step": 230
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.9495548961424333,
|
| 758 |
+
"grad_norm": 1.90625,
|
| 759 |
+
"learning_rate": 2.6915322580645164e-05,
|
| 760 |
+
"loss": 0.19356629848480225,
|
| 761 |
+
"step": 240
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.9495548961424333,
|
| 765 |
+
"forget_loss": 4.033423920191126e-06,
|
| 766 |
+
"retain_loss": 0.06074934080243111,
|
| 767 |
+
"step": 240
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.9495548961424333,
|
| 771 |
+
"forget_loss": 3.436478436924517e-06,
|
| 772 |
+
"retain_loss": 0.1828729808330536,
|
| 773 |
+
"step": 240
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.9495548961424333,
|
| 777 |
+
"forget_loss": 1.2162026052919828e-07,
|
| 778 |
+
"retain_loss": 0.05229510739445686,
|
| 779 |
+
"step": 240
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.9495548961424333,
|
| 783 |
+
"forget_loss": 2.5671818093542242e-06,
|
| 784 |
+
"retain_loss": 0.05694460868835449,
|
| 785 |
+
"step": 240
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.9891196834817013,
|
| 789 |
+
"grad_norm": 1.3515625,
|
| 790 |
+
"learning_rate": 2.590725806451613e-05,
|
| 791 |
+
"loss": 0.173517906665802,
|
| 792 |
+
"step": 250
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.9891196834817013,
|
| 796 |
+
"forget_loss": 2.22346602640755e-06,
|
| 797 |
+
"retain_loss": 0.0835813581943512,
|
| 798 |
+
"step": 250
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.9891196834817013,
|
| 802 |
+
"forget_loss": 5.302557838149369e-06,
|
| 803 |
+
"retain_loss": 0.2273225635290146,
|
| 804 |
+
"step": 250
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.9891196834817013,
|
| 808 |
+
"forget_loss": 7.574280061817262e-06,
|
| 809 |
+
"retain_loss": 0.41572776436805725,
|
| 810 |
+
"step": 250
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.9891196834817013,
|
| 814 |
+
"forget_loss": 4.923841743220692e-07,
|
| 815 |
+
"retain_loss": 0.05759130418300629,
|
| 816 |
+
"step": 250
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 1.0276953511374876,
|
| 820 |
+
"grad_norm": 2.078125,
|
| 821 |
+
"learning_rate": 2.48991935483871e-05,
|
| 822 |
+
"loss": 0.14332621097564696,
|
| 823 |
+
"step": 260
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 1.0276953511374876,
|
| 827 |
+
"forget_loss": 2.022331273110467e-06,
|
| 828 |
+
"retain_loss": 0.05112220719456673,
|
| 829 |
+
"step": 260
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.0276953511374876,
|
| 833 |
+
"forget_loss": 1.7422898963559419e-06,
|
| 834 |
+
"retain_loss": 0.15385369956493378,
|
| 835 |
+
"step": 260
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.0276953511374876,
|
| 839 |
+
"forget_loss": 3.312950980216556e-07,
|
| 840 |
+
"retain_loss": 0.19912393391132355,
|
| 841 |
+
"step": 260
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.0276953511374876,
|
| 845 |
+
"forget_loss": 6.443568736358429e-07,
|
| 846 |
+
"retain_loss": 0.055204521864652634,
|
| 847 |
+
"step": 260
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.0672601384767557,
|
| 851 |
+
"grad_norm": 1.46875,
|
| 852 |
+
"learning_rate": 2.3891129032258066e-05,
|
| 853 |
+
"loss": 0.1235049843788147,
|
| 854 |
+
"step": 270
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.0672601384767557,
|
| 858 |
+
"forget_loss": 6.121961177996127e-07,
|
| 859 |
+
"retain_loss": 0.25304123759269714,
|
| 860 |
+
"step": 270
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.0672601384767557,
|
| 864 |
+
"forget_loss": 8.218993343689363e-07,
|
| 865 |
+
"retain_loss": 0.14983095228672028,
|
| 866 |
+
"step": 270
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.0672601384767557,
|
| 870 |
+
"forget_loss": 1.1419467682571849e-06,
|
| 871 |
+
"retain_loss": 0.04056330397725105,
|
| 872 |
+
"step": 270
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.0672601384767557,
|
| 876 |
+
"forget_loss": 1.5871705727477092e-06,
|
| 877 |
+
"retain_loss": 0.03402575105428696,
|
| 878 |
+
"step": 270
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.1068249258160237,
|
| 882 |
+
"grad_norm": 0.98046875,
|
| 883 |
+
"learning_rate": 2.2883064516129033e-05,
|
| 884 |
+
"loss": 0.12284862995147705,
|
| 885 |
+
"step": 280
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.1068249258160237,
|
| 889 |
+
"forget_loss": 2.4364621253880614e-07,
|
| 890 |
+
"retain_loss": 0.039372384548187256,
|
| 891 |
+
"step": 280
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.1068249258160237,
|
| 895 |
+
"forget_loss": 2.9535872272390407e-06,
|
| 896 |
+
"retain_loss": 0.06493150442838669,
|
| 897 |
+
"step": 280
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.1068249258160237,
|
| 901 |
+
"forget_loss": 3.736472535820212e-07,
|
| 902 |
+
"retain_loss": 0.09616785496473312,
|
| 903 |
+
"step": 280
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.1068249258160237,
|
| 907 |
+
"forget_loss": 1.1166291002950857e-08,
|
| 908 |
+
"retain_loss": 0.12201965600252151,
|
| 909 |
+
"step": 280
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.1463897131552918,
|
| 913 |
+
"grad_norm": 1.0703125,
|
| 914 |
+
"learning_rate": 2.1875e-05,
|
| 915 |
+
"loss": 0.09197805523872375,
|
| 916 |
+
"step": 290
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.1463897131552918,
|
| 920 |
+
"forget_loss": 4.085670298081823e-06,
|
| 921 |
+
"retain_loss": 0.0720362663269043,
|
| 922 |
+
"step": 290
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.1463897131552918,
|
| 926 |
+
"forget_loss": 9.525655286779511e-08,
|
| 927 |
+
"retain_loss": 0.05113707482814789,
|
| 928 |
+
"step": 290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 1.1463897131552918,
|
| 932 |
+
"forget_loss": 1.6031831364671234e-06,
|
| 933 |
+
"retain_loss": 0.0687340646982193,
|
| 934 |
+
"step": 290
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.1463897131552918,
|
| 938 |
+
"forget_loss": 2.0602558379323455e-06,
|
| 939 |
+
"retain_loss": 0.21625281870365143,
|
| 940 |
+
"step": 290
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.1859545004945597,
|
| 944 |
+
"grad_norm": 1.2734375,
|
| 945 |
+
"learning_rate": 2.086693548387097e-05,
|
| 946 |
+
"loss": 0.0918435275554657,
|
| 947 |
+
"step": 300
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.1859545004945597,
|
| 951 |
+
"forget_loss": 1.1522879503900185e-06,
|
| 952 |
+
"retain_loss": 0.025093382224440575,
|
| 953 |
+
"step": 300
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.1859545004945597,
|
| 957 |
+
"forget_loss": 2.639731633280462e-07,
|
| 958 |
+
"retain_loss": 0.04188269376754761,
|
| 959 |
+
"step": 300
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.1859545004945597,
|
| 963 |
+
"forget_loss": 3.575230493879644e-06,
|
| 964 |
+
"retain_loss": 0.058530498296022415,
|
| 965 |
+
"step": 300
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.1859545004945597,
|
| 969 |
+
"forget_loss": 4.680264851231186e-07,
|
| 970 |
+
"retain_loss": 0.036610353738069534,
|
| 971 |
+
"step": 300
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.225519287833828,
|
| 975 |
+
"grad_norm": 0.80859375,
|
| 976 |
+
"learning_rate": 1.9858870967741934e-05,
|
| 977 |
+
"loss": 0.07977721691131592,
|
| 978 |
+
"step": 310
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 1.225519287833828,
|
| 982 |
+
"forget_loss": 1.9944478424349654e-07,
|
| 983 |
+
"retain_loss": 0.14079155027866364,
|
| 984 |
+
"step": 310
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.225519287833828,
|
| 988 |
+
"forget_loss": 1.7728395960148191e-06,
|
| 989 |
+
"retain_loss": 0.09404411911964417,
|
| 990 |
+
"step": 310
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.225519287833828,
|
| 994 |
+
"forget_loss": 1.1807240980488132e-06,
|
| 995 |
+
"retain_loss": 0.11878670006990433,
|
| 996 |
+
"step": 310
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.225519287833828,
|
| 1000 |
+
"forget_loss": 6.993744250394229e-07,
|
| 1001 |
+
"retain_loss": 0.08564583957195282,
|
| 1002 |
+
"step": 310
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.265084075173096,
|
| 1006 |
+
"grad_norm": 2.1875,
|
| 1007 |
+
"learning_rate": 1.8850806451612904e-05,
|
| 1008 |
+
"loss": 0.10100387334823609,
|
| 1009 |
+
"step": 320
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.265084075173096,
|
| 1013 |
+
"forget_loss": 9.910125299938954e-06,
|
| 1014 |
+
"retain_loss": 0.06925372779369354,
|
| 1015 |
+
"step": 320
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 1.265084075173096,
|
| 1019 |
+
"forget_loss": 2.2465580968855647e-06,
|
| 1020 |
+
"retain_loss": 0.03531289100646973,
|
| 1021 |
+
"step": 320
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.265084075173096,
|
| 1025 |
+
"forget_loss": 1.5962227450927458e-07,
|
| 1026 |
+
"retain_loss": 0.044194359332323074,
|
| 1027 |
+
"step": 320
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 1.265084075173096,
|
| 1031 |
+
"forget_loss": 4.942241957905935e-07,
|
| 1032 |
+
"retain_loss": 0.062409959733486176,
|
| 1033 |
+
"step": 320
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.304648862512364,
|
| 1037 |
+
"grad_norm": 1.2890625,
|
| 1038 |
+
"learning_rate": 1.784274193548387e-05,
|
| 1039 |
+
"loss": 0.06902462244033813,
|
| 1040 |
+
"step": 330
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.304648862512364,
|
| 1044 |
+
"forget_loss": 6.602442681469256e-07,
|
| 1045 |
+
"retain_loss": 0.04397878423333168,
|
| 1046 |
+
"step": 330
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.304648862512364,
|
| 1050 |
+
"forget_loss": 9.583651490174816e-07,
|
| 1051 |
+
"retain_loss": 0.056344836950302124,
|
| 1052 |
+
"step": 330
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.304648862512364,
|
| 1056 |
+
"forget_loss": 3.47790461319164e-07,
|
| 1057 |
+
"retain_loss": 0.04283231496810913,
|
| 1058 |
+
"step": 330
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.304648862512364,
|
| 1062 |
+
"forget_loss": 7.383774232039286e-07,
|
| 1063 |
+
"retain_loss": 0.2884156107902527,
|
| 1064 |
+
"step": 330
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.344213649851632,
|
| 1068 |
+
"grad_norm": 0.5546875,
|
| 1069 |
+
"learning_rate": 1.683467741935484e-05,
|
| 1070 |
+
"loss": 0.07270175218582153,
|
| 1071 |
+
"step": 340
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 1.344213649851632,
|
| 1075 |
+
"forget_loss": 1.4138665846985532e-06,
|
| 1076 |
+
"retain_loss": 0.030446356162428856,
|
| 1077 |
+
"step": 340
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.344213649851632,
|
| 1081 |
+
"forget_loss": 4.400314992381027e-07,
|
| 1082 |
+
"retain_loss": 0.041316572576761246,
|
| 1083 |
+
"step": 340
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 1.344213649851632,
|
| 1087 |
+
"forget_loss": 8.035279392970551e-07,
|
| 1088 |
+
"retain_loss": 0.4023597836494446,
|
| 1089 |
+
"step": 340
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.344213649851632,
|
| 1093 |
+
"forget_loss": 3.161345887292555e-07,
|
| 1094 |
+
"retain_loss": 0.028397783637046814,
|
| 1095 |
+
"step": 340
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.3837784371909,
|
| 1099 |
+
"grad_norm": 1.484375,
|
| 1100 |
+
"learning_rate": 1.5826612903225806e-05,
|
| 1101 |
+
"loss": 0.07099369764328003,
|
| 1102 |
+
"step": 350
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.3837784371909,
|
| 1106 |
+
"forget_loss": 8.570134468754986e-07,
|
| 1107 |
+
"retain_loss": 0.026840655133128166,
|
| 1108 |
+
"step": 350
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.3837784371909,
|
| 1112 |
+
"forget_loss": 4.2903576513708686e-07,
|
| 1113 |
+
"retain_loss": 0.045387767255306244,
|
| 1114 |
+
"step": 350
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.3837784371909,
|
| 1118 |
+
"forget_loss": 8.26216322025175e-08,
|
| 1119 |
+
"retain_loss": 0.06860622763633728,
|
| 1120 |
+
"step": 350
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 1.3837784371909,
|
| 1124 |
+
"forget_loss": 8.852501309775107e-08,
|
| 1125 |
+
"retain_loss": 0.21477188169956207,
|
| 1126 |
+
"step": 350
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.4233432245301683,
|
| 1130 |
+
"grad_norm": 1.953125,
|
| 1131 |
+
"learning_rate": 1.4818548387096776e-05,
|
| 1132 |
+
"loss": 0.07751677036285401,
|
| 1133 |
+
"step": 360
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.4233432245301683,
|
| 1137 |
+
"forget_loss": 1.4736333469045348e-06,
|
| 1138 |
+
"retain_loss": 0.049729909747838974,
|
| 1139 |
+
"step": 360
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 1.4233432245301683,
|
| 1143 |
+
"forget_loss": 2.1971384001062688e-07,
|
| 1144 |
+
"retain_loss": 0.023645324632525444,
|
| 1145 |
+
"step": 360
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.4233432245301683,
|
| 1149 |
+
"forget_loss": 6.915368544468947e-07,
|
| 1150 |
+
"retain_loss": 0.04990541562438011,
|
| 1151 |
+
"step": 360
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.4233432245301683,
|
| 1155 |
+
"forget_loss": 1.2885877254120714e-07,
|
| 1156 |
+
"retain_loss": 0.02339594066143036,
|
| 1157 |
+
"step": 360
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.4629080118694362,
|
| 1161 |
+
"grad_norm": 0.73828125,
|
| 1162 |
+
"learning_rate": 1.3810483870967741e-05,
|
| 1163 |
+
"loss": 0.0555726408958435,
|
| 1164 |
+
"step": 370
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.4629080118694362,
|
| 1168 |
+
"forget_loss": 1.0162235639654682e-06,
|
| 1169 |
+
"retain_loss": 0.039157990366220474,
|
| 1170 |
+
"step": 370
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.4629080118694362,
|
| 1174 |
+
"forget_loss": 2.873887865462166e-07,
|
| 1175 |
+
"retain_loss": 0.043322984129190445,
|
| 1176 |
+
"step": 370
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 1.4629080118694362,
|
| 1180 |
+
"forget_loss": 1.5368651702374336e-06,
|
| 1181 |
+
"retain_loss": 0.027565972879529,
|
| 1182 |
+
"step": 370
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.4629080118694362,
|
| 1186 |
+
"forget_loss": 1.5365935723821167e-06,
|
| 1187 |
+
"retain_loss": 0.11519625037908554,
|
| 1188 |
+
"step": 370
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 1.5024727992087041,
|
| 1192 |
+
"grad_norm": 0.859375,
|
| 1193 |
+
"learning_rate": 1.280241935483871e-05,
|
| 1194 |
+
"loss": 0.05110462307929993,
|
| 1195 |
+
"step": 380
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 1.5024727992087041,
|
| 1199 |
+
"forget_loss": 7.83655764280411e-07,
|
| 1200 |
+
"retain_loss": 0.05130387097597122,
|
| 1201 |
+
"step": 380
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 1.5024727992087041,
|
| 1205 |
+
"forget_loss": 5.978235094517004e-06,
|
| 1206 |
+
"retain_loss": 0.027177350595593452,
|
| 1207 |
+
"step": 380
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.5024727992087041,
|
| 1211 |
+
"forget_loss": 3.0234426162678574e-07,
|
| 1212 |
+
"retain_loss": 0.024828054010868073,
|
| 1213 |
+
"step": 380
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.5024727992087041,
|
| 1217 |
+
"forget_loss": 1.2347620703678786e-08,
|
| 1218 |
+
"retain_loss": 0.04538526013493538,
|
| 1219 |
+
"step": 380
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 1.5420375865479723,
|
| 1223 |
+
"grad_norm": 0.55859375,
|
| 1224 |
+
"learning_rate": 1.1794354838709679e-05,
|
| 1225 |
+
"loss": 0.057669293880462644,
|
| 1226 |
+
"step": 390
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 1.5420375865479723,
|
| 1230 |
+
"forget_loss": 8.569641067879274e-07,
|
| 1231 |
+
"retain_loss": 0.03606370836496353,
|
| 1232 |
+
"step": 390
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.5420375865479723,
|
| 1236 |
+
"forget_loss": 6.569359811692266e-07,
|
| 1237 |
+
"retain_loss": 0.03508085012435913,
|
| 1238 |
+
"step": 390
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.5420375865479723,
|
| 1242 |
+
"forget_loss": 1.5997493107988703e-07,
|
| 1243 |
+
"retain_loss": 0.042272500693798065,
|
| 1244 |
+
"step": 390
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 1.5420375865479723,
|
| 1248 |
+
"forget_loss": 2.9301961035343993e-07,
|
| 1249 |
+
"retain_loss": 0.022033188492059708,
|
| 1250 |
+
"step": 390
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.5816023738872405,
|
| 1254 |
+
"grad_norm": 0.95703125,
|
| 1255 |
+
"learning_rate": 1.0786290322580646e-05,
|
| 1256 |
+
"loss": 0.050089681148529054,
|
| 1257 |
+
"step": 400
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.5816023738872405,
|
| 1261 |
+
"forget_loss": 1.3866008430341026e-07,
|
| 1262 |
+
"retain_loss": 0.09683580696582794,
|
| 1263 |
+
"step": 400
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.5816023738872405,
|
| 1267 |
+
"forget_loss": 2.750243588423018e-08,
|
| 1268 |
+
"retain_loss": 0.02329876273870468,
|
| 1269 |
+
"step": 400
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.5816023738872405,
|
| 1273 |
+
"forget_loss": 9.818218131840695e-06,
|
| 1274 |
+
"retain_loss": 0.03960738331079483,
|
| 1275 |
+
"step": 400
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.5816023738872405,
|
| 1279 |
+
"forget_loss": 5.704383738702745e-07,
|
| 1280 |
+
"retain_loss": 0.01846085488796234,
|
| 1281 |
+
"step": 400
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 1.6211671612265084,
|
| 1285 |
+
"grad_norm": 0.4296875,
|
| 1286 |
+
"learning_rate": 9.778225806451613e-06,
|
| 1287 |
+
"loss": 0.05209760069847107,
|
| 1288 |
+
"step": 410
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 1.6211671612265084,
|
| 1292 |
+
"forget_loss": 1.1604224710026756e-06,
|
| 1293 |
+
"retain_loss": 0.03962882235646248,
|
| 1294 |
+
"step": 410
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 1.6211671612265084,
|
| 1298 |
+
"forget_loss": 5.507745868271741e-07,
|
| 1299 |
+
"retain_loss": 0.04976373910903931,
|
| 1300 |
+
"step": 410
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 1.6211671612265084,
|
| 1304 |
+
"forget_loss": 2.3774734927428653e-06,
|
| 1305 |
+
"retain_loss": 0.04256688430905342,
|
| 1306 |
+
"step": 410
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.6211671612265084,
|
| 1310 |
+
"forget_loss": 4.576730816552299e-08,
|
| 1311 |
+
"retain_loss": 0.15119299292564392,
|
| 1312 |
+
"step": 410
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.6607319485657763,
|
| 1316 |
+
"grad_norm": 0.59765625,
|
| 1317 |
+
"learning_rate": 8.770161290322582e-06,
|
| 1318 |
+
"loss": 0.049598729610443114,
|
| 1319 |
+
"step": 420
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.6607319485657763,
|
| 1323 |
+
"forget_loss": 2.0336298689471732e-07,
|
| 1324 |
+
"retain_loss": 0.0471678227186203,
|
| 1325 |
+
"step": 420
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.6607319485657763,
|
| 1329 |
+
"forget_loss": 1.7267917428398505e-05,
|
| 1330 |
+
"retain_loss": 0.040639519691467285,
|
| 1331 |
+
"step": 420
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 1.6607319485657763,
|
| 1335 |
+
"forget_loss": 4.817159151571104e-07,
|
| 1336 |
+
"retain_loss": 0.02267388068139553,
|
| 1337 |
+
"step": 420
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 1.6607319485657763,
|
| 1341 |
+
"forget_loss": 2.7222637299928465e-07,
|
| 1342 |
+
"retain_loss": 0.021710213273763657,
|
| 1343 |
+
"step": 420
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 1.7002967359050445,
|
| 1347 |
+
"grad_norm": 0.52734375,
|
| 1348 |
+
"learning_rate": 7.762096774193549e-06,
|
| 1349 |
+
"loss": 0.045286208391189575,
|
| 1350 |
+
"step": 430
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 1.7002967359050445,
|
| 1354 |
+
"forget_loss": 7.776943675708026e-07,
|
| 1355 |
+
"retain_loss": 0.05673515796661377,
|
| 1356 |
+
"step": 430
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 1.7002967359050445,
|
| 1360 |
+
"forget_loss": 2.0699600611351343e-07,
|
| 1361 |
+
"retain_loss": 0.023737620562314987,
|
| 1362 |
+
"step": 430
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 1.7002967359050445,
|
| 1366 |
+
"forget_loss": 2.6618576498549373e-07,
|
| 1367 |
+
"retain_loss": 0.027188653126358986,
|
| 1368 |
+
"step": 430
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.7002967359050445,
|
| 1372 |
+
"forget_loss": 1.3067615611817018e-07,
|
| 1373 |
+
"retain_loss": 0.05579356476664543,
|
| 1374 |
+
"step": 430
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.7398615232443126,
|
| 1378 |
+
"grad_norm": 0.9921875,
|
| 1379 |
+
"learning_rate": 6.754032258064516e-06,
|
| 1380 |
+
"loss": 0.04463993012905121,
|
| 1381 |
+
"step": 440
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.7398615232443126,
|
| 1385 |
+
"forget_loss": 2.5087867925321916e-06,
|
| 1386 |
+
"retain_loss": 0.05026588961482048,
|
| 1387 |
+
"step": 440
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 1.7398615232443126,
|
| 1391 |
+
"forget_loss": 6.727441927978361e-07,
|
| 1392 |
+
"retain_loss": 0.02630964294075966,
|
| 1393 |
+
"step": 440
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 1.7398615232443126,
|
| 1397 |
+
"forget_loss": 5.018938864509437e-08,
|
| 1398 |
+
"retain_loss": 0.03725261241197586,
|
| 1399 |
+
"step": 440
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.7398615232443126,
|
| 1403 |
+
"forget_loss": 1.4030342754267622e-07,
|
| 1404 |
+
"retain_loss": 0.029558738693594933,
|
| 1405 |
+
"step": 440
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 1.7794263105835806,
|
| 1409 |
+
"grad_norm": 0.4375,
|
| 1410 |
+
"learning_rate": 5.745967741935484e-06,
|
| 1411 |
+
"loss": 0.05203538537025452,
|
| 1412 |
+
"step": 450
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 1.7794263105835806,
|
| 1416 |
+
"forget_loss": 7.623576038895408e-06,
|
| 1417 |
+
"retain_loss": 0.02868250384926796,
|
| 1418 |
+
"step": 450
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.7794263105835806,
|
| 1422 |
+
"forget_loss": 6.238550440684776e-07,
|
| 1423 |
+
"retain_loss": 0.03208765387535095,
|
| 1424 |
+
"step": 450
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.7794263105835806,
|
| 1428 |
+
"forget_loss": 1.7789380990507198e-07,
|
| 1429 |
+
"retain_loss": 0.03081919252872467,
|
| 1430 |
+
"step": 450
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.7794263105835806,
|
| 1434 |
+
"forget_loss": 4.8167414945510245e-08,
|
| 1435 |
+
"retain_loss": 0.02771441824734211,
|
| 1436 |
+
"step": 450
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 1.8189910979228485,
|
| 1440 |
+
"grad_norm": 0.5625,
|
| 1441 |
+
"learning_rate": 4.737903225806452e-06,
|
| 1442 |
+
"loss": 0.03996638655662536,
|
| 1443 |
+
"step": 460
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 1.8189910979228485,
|
| 1447 |
+
"forget_loss": 6.715895892739354e-07,
|
| 1448 |
+
"retain_loss": 0.04693002253770828,
|
| 1449 |
+
"step": 460
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.8189910979228485,
|
| 1453 |
+
"forget_loss": 4.4825827671957086e-07,
|
| 1454 |
+
"retain_loss": 0.044060204178094864,
|
| 1455 |
+
"step": 460
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 1.8189910979228485,
|
| 1459 |
+
"forget_loss": 1.5432489419708872e-07,
|
| 1460 |
+
"retain_loss": 0.031750187277793884,
|
| 1461 |
+
"step": 460
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 1.8189910979228485,
|
| 1465 |
+
"forget_loss": 4.117340495213284e-07,
|
| 1466 |
+
"retain_loss": 0.04923136904835701,
|
| 1467 |
+
"step": 460
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 1.8585558852621167,
|
| 1471 |
+
"grad_norm": 0.6796875,
|
| 1472 |
+
"learning_rate": 3.7298387096774197e-06,
|
| 1473 |
+
"loss": 0.039948847889900205,
|
| 1474 |
+
"step": 470
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 1.8585558852621167,
|
| 1478 |
+
"forget_loss": 1.2325557463555015e-07,
|
| 1479 |
+
"retain_loss": 0.03459008038043976,
|
| 1480 |
+
"step": 470
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.8585558852621167,
|
| 1484 |
+
"forget_loss": 1.1708880975902503e-07,
|
| 1485 |
+
"retain_loss": 0.025717800483107567,
|
| 1486 |
+
"step": 470
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 1.8585558852621167,
|
| 1490 |
+
"forget_loss": 5.927329766564071e-06,
|
| 1491 |
+
"retain_loss": 0.025716962292790413,
|
| 1492 |
+
"step": 470
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 1.8585558852621167,
|
| 1496 |
+
"forget_loss": 6.584188128044843e-08,
|
| 1497 |
+
"retain_loss": 0.015229296870529652,
|
| 1498 |
+
"step": 470
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 1.8981206726013848,
|
| 1502 |
+
"grad_norm": 0.404296875,
|
| 1503 |
+
"learning_rate": 2.721774193548387e-06,
|
| 1504 |
+
"loss": 0.039198037981987,
|
| 1505 |
+
"step": 480
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 1.8981206726013848,
|
| 1509 |
+
"forget_loss": 2.8114575343352044e-06,
|
| 1510 |
+
"retain_loss": 0.18008944392204285,
|
| 1511 |
+
"step": 480
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 1.8981206726013848,
|
| 1515 |
+
"forget_loss": 1.3262372249300824e-06,
|
| 1516 |
+
"retain_loss": 0.031407859176397324,
|
| 1517 |
+
"step": 480
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 1.8981206726013848,
|
| 1521 |
+
"forget_loss": 9.033684591486235e-07,
|
| 1522 |
+
"retain_loss": 0.02400125376880169,
|
| 1523 |
+
"step": 480
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 1.8981206726013848,
|
| 1527 |
+
"forget_loss": 2.0957136825927591e-07,
|
| 1528 |
+
"retain_loss": 0.04799356311559677,
|
| 1529 |
+
"step": 480
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.9376854599406528,
|
| 1533 |
+
"grad_norm": 0.6484375,
|
| 1534 |
+
"learning_rate": 1.7137096774193548e-06,
|
| 1535 |
+
"loss": 0.04367169439792633,
|
| 1536 |
+
"step": 490
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.9376854599406528,
|
| 1540 |
+
"forget_loss": 7.195729949671659e-07,
|
| 1541 |
+
"retain_loss": 0.0549895353615284,
|
| 1542 |
+
"step": 490
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.9376854599406528,
|
| 1546 |
+
"forget_loss": 1.568659172335174e-06,
|
| 1547 |
+
"retain_loss": 0.055492039769887924,
|
| 1548 |
+
"step": 490
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 1.9376854599406528,
|
| 1552 |
+
"forget_loss": 2.101234599649615e-07,
|
| 1553 |
+
"retain_loss": 0.024565406143665314,
|
| 1554 |
+
"step": 490
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.9376854599406528,
|
| 1558 |
+
"forget_loss": 9.418807849215227e-07,
|
| 1559 |
+
"retain_loss": 0.04276119917631149,
|
| 1560 |
+
"step": 490
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 1.9772502472799207,
|
| 1564 |
+
"grad_norm": 0.408203125,
|
| 1565 |
+
"learning_rate": 7.056451612903225e-07,
|
| 1566 |
+
"loss": 0.03923664093017578,
|
| 1567 |
+
"step": 500
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 1.9772502472799207,
|
| 1571 |
+
"forget_loss": 3.42980342793453e-07,
|
| 1572 |
+
"retain_loss": 0.029645651578903198,
|
| 1573 |
+
"step": 500
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 1.9772502472799207,
|
| 1577 |
+
"forget_loss": 1.9959605879193987e-07,
|
| 1578 |
+
"retain_loss": 0.0843573808670044,
|
| 1579 |
+
"step": 500
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 1.9772502472799207,
|
| 1583 |
+
"forget_loss": 6.622903470088204e-08,
|
| 1584 |
+
"retain_loss": 0.03647373244166374,
|
| 1585 |
+
"step": 500
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.9772502472799207,
|
| 1589 |
+
"forget_loss": 3.48915563108676e-07,
|
| 1590 |
+
"retain_loss": 0.024540118873119354,
|
| 1591 |
+
"step": 500
|
| 1592 |
+
}
|
| 1593 |
+
],
|
| 1594 |
+
"logging_steps": 10,
|
| 1595 |
+
"max_steps": 506,
|
| 1596 |
+
"num_input_tokens_seen": 0,
|
| 1597 |
+
"num_train_epochs": 2,
|
| 1598 |
+
"save_steps": 200,
|
| 1599 |
+
"stateful_callbacks": {
|
| 1600 |
+
"TrainerControl": {
|
| 1601 |
+
"args": {
|
| 1602 |
+
"should_epoch_stop": false,
|
| 1603 |
+
"should_evaluate": false,
|
| 1604 |
+
"should_log": false,
|
| 1605 |
+
"should_save": true,
|
| 1606 |
+
"should_training_stop": true
|
| 1607 |
+
},
|
| 1608 |
+
"attributes": {}
|
| 1609 |
+
}
|
| 1610 |
+
},
|
| 1611 |
+
"total_flos": 0.0,
|
| 1612 |
+
"train_batch_size": 8,
|
| 1613 |
+
"trial_name": null,
|
| 1614 |
+
"trial_params": null
|
| 1615 |
+
}
|
checkpoint-506/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7587f27094c5b0d28888635edb5fb75b1840350b6c54434f3d8d48a5fdd7e2f
|
| 3 |
+
size 5329
|
config.json
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Olmo3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": null,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 100257,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 11008,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"sliding_attention",
|
| 16 |
+
"sliding_attention",
|
| 17 |
+
"sliding_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"sliding_attention",
|
| 20 |
+
"sliding_attention",
|
| 21 |
+
"sliding_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"sliding_attention",
|
| 24 |
+
"sliding_attention",
|
| 25 |
+
"sliding_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"sliding_attention",
|
| 28 |
+
"sliding_attention",
|
| 29 |
+
"sliding_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"sliding_attention",
|
| 32 |
+
"sliding_attention",
|
| 33 |
+
"sliding_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"sliding_attention",
|
| 36 |
+
"sliding_attention",
|
| 37 |
+
"sliding_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"sliding_attention",
|
| 40 |
+
"sliding_attention",
|
| 41 |
+
"sliding_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"sliding_attention",
|
| 44 |
+
"sliding_attention",
|
| 45 |
+
"sliding_attention",
|
| 46 |
+
"full_attention"
|
| 47 |
+
],
|
| 48 |
+
"max_position_embeddings": 65536,
|
| 49 |
+
"model_type": "olmo3",
|
| 50 |
+
"num_attention_heads": 32,
|
| 51 |
+
"num_hidden_layers": 32,
|
| 52 |
+
"num_key_value_heads": 32,
|
| 53 |
+
"pad_token_id": 100277,
|
| 54 |
+
"rms_norm_eps": 1e-06,
|
| 55 |
+
"rope_parameters": {
|
| 56 |
+
"attention_factor": 1.2079441541679836,
|
| 57 |
+
"beta_fast": 32.0,
|
| 58 |
+
"beta_slow": 1.0,
|
| 59 |
+
"factor": 8.0,
|
| 60 |
+
"original_max_position_embeddings": 8192,
|
| 61 |
+
"rope_theta": 500000,
|
| 62 |
+
"rope_type": "yarn"
|
| 63 |
+
},
|
| 64 |
+
"sliding_window": 4096,
|
| 65 |
+
"tie_word_embeddings": false,
|
| 66 |
+
"transformers_version": "5.6.0",
|
| 67 |
+
"use_cache": false,
|
| 68 |
+
"vocab_size": 100278
|
| 69 |
+
}
|
config.yaml
ADDED
|
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
model_name: allenai/Olmo-3-1025-7B
|
| 2 |
+
forget_path: unlearning-cleanslate/fsid-curated-olmo-7b:forget:baseline
|
| 3 |
+
retain_path: unlearning-cleanslate/fsid-curated-olmo-7b:retain:baseline
|
| 4 |
+
output_dir: /runs
|
| 5 |
+
objective: simnpo
|
| 6 |
+
num_epochs: 2
|
| 7 |
+
batch_size: 8
|
| 8 |
+
gradient_accum_steps: 4
|
| 9 |
+
lr: 5.0e-05
|
| 10 |
+
weight_decay: 0.0
|
| 11 |
+
warmup_steps: 10
|
| 12 |
+
max_grad_norm: 1.0
|
| 13 |
+
forget_weight: 5.0
|
| 14 |
+
retain_weight: 1.0
|
| 15 |
+
retain_loss_type: nll
|
| 16 |
+
npo_beta: 2.0
|
| 17 |
+
simnpo_delta: 0.25
|
| 18 |
+
rmu_steering_coeff: 2.0
|
| 19 |
+
rmu_module_regex: model\.layers\.7
|
| 20 |
+
rmu_control_vec_seed: 0
|
| 21 |
+
undial_beta: 10.0
|
| 22 |
+
save_every: 200
|
| 23 |
+
fsdp_sharding_strategy: full_shard
|
| 24 |
+
dtype: bfloat16
|
| 25 |
+
seed: 42
|
| 26 |
+
num_workers: 0
|
| 27 |
+
log_every: 10
|
| 28 |
+
gradient_checkpointing: false
|
| 29 |
+
torch_compile: false
|
| 30 |
+
push_to_hub: true
|
| 31 |
+
hub_repo_id: unlearning-cleanslate/olmo-3-7b-simnpo-baseline
|
| 32 |
+
hub_private: false
|
| 33 |
+
optim: adamw_torch
|
| 34 |
+
_run_name: simnpo_Olmo-3-1025-7B_20260428_231931
|
| 35 |
+
_run_dir: /runs/simnpo_Olmo-3-1025-7B_20260428_231931
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
100257
|
| 5 |
+
],
|
| 6 |
+
"pad_token_id": 100277,
|
| 7 |
+
"transformers_version": "5.6.0"
|
| 8 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8df81fd1ff28a8bc31b9efb605fa4d68414a7ae5451dc8224d2782cca686bbd6
|
| 3 |
+
size 14596063960
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": false,
|
| 9 |
+
"local_files_only": false,
|
| 10 |
+
"model_max_length": 65536,
|
| 11 |
+
"pad_token": "<|pad|>",
|
| 12 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 13 |
+
"unk_token": "<|endoftext|>"
|
| 14 |
+
}
|
train.log
ADDED
|
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
2026-04-28 23:20:12,969 INFO cleanslate.fsid.training.trainer: [RANK 0] FSID train: model=allenai/Olmo-3-1025-7B objective=simnpo run_dir=/runs/simnpo_Olmo-3-1025-7B_20260428_231931
|
| 2 |
+
2026-04-28 23:20:12,969 INFO cleanslate.fsid.training.trainer: [RANK 0] Starting training: objective=simnpo epochs=2
|
| 3 |
+
2026-04-28 23:36:10,445 INFO cleanslate.fsid.training.trainer: [RANK 0] Saved checkpoint to /runs/simnpo_Olmo-3-1025-7B_20260428_231931
|
| 4 |
+
2026-04-28 23:36:10,450 INFO cleanslate.fsid.training.trainer: [RANK 0] Training complete (914.0s)
|
| 5 |
+
2026-04-28 23:36:11,175 INFO cleanslate.fsid.training.trainer: [RANK 0] Pushing checkpoint dir /runs/simnpo_Olmo-3-1025-7B_20260428_231931 to unlearning-cleanslate/olmo-3-7b-simnpo-baseline
|
train_summary.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"run_name": "simnpo_Olmo-3-1025-7B_20260428_231931",
|
| 3 |
+
"run_dir": "/runs/simnpo_Olmo-3-1025-7B_20260428_231931",
|
| 4 |
+
"config": {
|
| 5 |
+
"model_name": "allenai/Olmo-3-1025-7B",
|
| 6 |
+
"forget_path": "unlearning-cleanslate/fsid-curated-olmo-7b:forget:baseline",
|
| 7 |
+
"retain_path": "unlearning-cleanslate/fsid-curated-olmo-7b:retain:baseline",
|
| 8 |
+
"output_dir": "/runs",
|
| 9 |
+
"objective": "simnpo",
|
| 10 |
+
"num_epochs": 2,
|
| 11 |
+
"batch_size": 8,
|
| 12 |
+
"gradient_accum_steps": 4,
|
| 13 |
+
"lr": 5e-05,
|
| 14 |
+
"weight_decay": 0.0,
|
| 15 |
+
"warmup_steps": 10,
|
| 16 |
+
"max_grad_norm": 1.0,
|
| 17 |
+
"forget_weight": 5.0,
|
| 18 |
+
"retain_weight": 1.0,
|
| 19 |
+
"retain_loss_type": "nll",
|
| 20 |
+
"npo_beta": 2.0,
|
| 21 |
+
"simnpo_delta": 0.25,
|
| 22 |
+
"rmu_steering_coeff": 2.0,
|
| 23 |
+
"rmu_module_regex": "model\\.layers\\.7",
|
| 24 |
+
"rmu_control_vec_seed": 0,
|
| 25 |
+
"undial_beta": 10.0,
|
| 26 |
+
"save_every": 200,
|
| 27 |
+
"fsdp_sharding_strategy": "full_shard",
|
| 28 |
+
"dtype": "bfloat16",
|
| 29 |
+
"seed": 42,
|
| 30 |
+
"num_workers": 0,
|
| 31 |
+
"log_every": 10,
|
| 32 |
+
"gradient_checkpointing": false,
|
| 33 |
+
"torch_compile": false,
|
| 34 |
+
"push_to_hub": true,
|
| 35 |
+
"hub_repo_id": "unlearning-cleanslate/olmo-3-7b-simnpo-baseline",
|
| 36 |
+
"hub_private": false,
|
| 37 |
+
"optim": "adamw_torch"
|
| 38 |
+
},
|
| 39 |
+
"num_forget_rows": 8084,
|
| 40 |
+
"num_forget_pairs": 8084,
|
| 41 |
+
"num_retain_rows": 1646,
|
| 42 |
+
"num_retain_sequences": 1646,
|
| 43 |
+
"num_trainable_params": 7298011136,
|
| 44 |
+
"num_total_params": 7298011136,
|
| 45 |
+
"run_seconds": 913.9792716503143,
|
| 46 |
+
"checkpoint_dir": "/runs/simnpo_Olmo-3-1025-7B_20260428_231931",
|
| 47 |
+
"is_main_process": true
|
| 48 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7587f27094c5b0d28888635edb5fb75b1840350b6c54434f3d8d48a5fdd7e2f
|
| 3 |
+
size 5329
|