upload simnpo_Olmo-3-1025-7B_20260428_231941
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 sha256:589f7a96cf6b0bc740dba095802c619fb8c4684d5aa9e83157073bbaf9c4ccb9
|
| 3 |
+
size 14596063960
|
checkpoint-200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83d8037bb183002beef170b433dbaec4737a88c50976d3fc763629b36a79e744
|
| 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": 2.203125,
|
| 77 |
+
"learning_rate": 4.909274193548387e-05,
|
| 78 |
+
"loss": 2.1829532623291015,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0791295746785361,
|
| 83 |
+
"forget_loss": 3.1555460736854e-05,
|
| 84 |
+
"retain_loss": 2.056671380996704,
|
| 85 |
+
"step": 20
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.0791295746785361,
|
| 89 |
+
"forget_loss": 1.3120857147441711e-05,
|
| 90 |
+
"retain_loss": 1.9920682907104492,
|
| 91 |
+
"step": 20
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.0791295746785361,
|
| 95 |
+
"forget_loss": 8.181996963685378e-05,
|
| 96 |
+
"retain_loss": 2.149359703063965,
|
| 97 |
+
"step": 20
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.0791295746785361,
|
| 101 |
+
"forget_loss": 4.155315400566906e-05,
|
| 102 |
+
"retain_loss": 1.797939419746399,
|
| 103 |
+
"step": 20
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.11869436201780416,
|
| 107 |
+
"grad_norm": 2.03125,
|
| 108 |
+
"learning_rate": 4.808467741935484e-05,
|
| 109 |
+
"loss": 1.9520586013793946,
|
| 110 |
+
"step": 30
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.11869436201780416,
|
| 114 |
+
"forget_loss": 2.097734068229329e-06,
|
| 115 |
+
"retain_loss": 1.9717810153961182,
|
| 116 |
+
"step": 30
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.11869436201780416,
|
| 120 |
+
"forget_loss": 9.0424384779908e-07,
|
| 121 |
+
"retain_loss": 2.1347732543945312,
|
| 122 |
+
"step": 30
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.11869436201780416,
|
| 126 |
+
"forget_loss": 1.5195576452242676e-05,
|
| 127 |
+
"retain_loss": 1.7591031789779663,
|
| 128 |
+
"step": 30
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.11869436201780416,
|
| 132 |
+
"forget_loss": 2.9381511922110803e-05,
|
| 133 |
+
"retain_loss": 2.324976682662964,
|
| 134 |
+
"step": 30
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.1582591493570722,
|
| 138 |
+
"grad_norm": 1.9453125,
|
| 139 |
+
"learning_rate": 4.7076612903225806e-05,
|
| 140 |
+
"loss": 1.7898395538330079,
|
| 141 |
+
"step": 40
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.1582591493570722,
|
| 145 |
+
"forget_loss": 2.347593181184493e-05,
|
| 146 |
+
"retain_loss": 1.5896490812301636,
|
| 147 |
+
"step": 40
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.1582591493570722,
|
| 151 |
+
"forget_loss": 2.7579757443163544e-05,
|
| 152 |
+
"retain_loss": 1.1212265491485596,
|
| 153 |
+
"step": 40
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.1582591493570722,
|
| 157 |
+
"forget_loss": 2.1694726456189528e-05,
|
| 158 |
+
"retain_loss": 2.051854133605957,
|
| 159 |
+
"step": 40
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.1582591493570722,
|
| 163 |
+
"forget_loss": 6.128148925199639e-06,
|
| 164 |
+
"retain_loss": 1.6619952917099,
|
| 165 |
+
"step": 40
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.19782393669634027,
|
| 169 |
+
"grad_norm": 1.96875,
|
| 170 |
+
"learning_rate": 4.606854838709678e-05,
|
| 171 |
+
"loss": 1.5459610939025878,
|
| 172 |
+
"step": 50
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.19782393669634027,
|
| 176 |
+
"forget_loss": 1.4324338735605124e-05,
|
| 177 |
+
"retain_loss": 1.7004584074020386,
|
| 178 |
+
"step": 50
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.19782393669634027,
|
| 182 |
+
"forget_loss": 5.814884843857726e-06,
|
| 183 |
+
"retain_loss": 1.3355984687805176,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.19782393669634027,
|
| 188 |
+
"forget_loss": 1.4618005934607936e-06,
|
| 189 |
+
"retain_loss": 1.7750041484832764,
|
| 190 |
+
"step": 50
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.19782393669634027,
|
| 194 |
+
"forget_loss": 1.6271239928755676e-06,
|
| 195 |
+
"retain_loss": 1.4064531326293945,
|
| 196 |
+
"step": 50
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.23738872403560832,
|
| 200 |
+
"grad_norm": 2.234375,
|
| 201 |
+
"learning_rate": 4.506048387096775e-05,
|
| 202 |
+
"loss": 1.4617247581481934,
|
| 203 |
+
"step": 60
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.23738872403560832,
|
| 207 |
+
"forget_loss": 9.254661563318223e-06,
|
| 208 |
+
"retain_loss": 1.8761130571365356,
|
| 209 |
+
"step": 60
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.23738872403560832,
|
| 213 |
+
"forget_loss": 9.365790901938453e-06,
|
| 214 |
+
"retain_loss": 1.1389141082763672,
|
| 215 |
+
"step": 60
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.23738872403560832,
|
| 219 |
+
"forget_loss": 6.40576909063384e-05,
|
| 220 |
+
"retain_loss": 1.0727425813674927,
|
| 221 |
+
"step": 60
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.23738872403560832,
|
| 225 |
+
"forget_loss": 3.140630724374205e-06,
|
| 226 |
+
"retain_loss": 1.2311009168624878,
|
| 227 |
+
"step": 60
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.27695351137487634,
|
| 231 |
+
"grad_norm": 2.125,
|
| 232 |
+
"learning_rate": 4.4052419354838714e-05,
|
| 233 |
+
"loss": 1.344314193725586,
|
| 234 |
+
"step": 70
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.27695351137487634,
|
| 238 |
+
"forget_loss": 2.0407464035088196e-05,
|
| 239 |
+
"retain_loss": 1.2631032466888428,
|
| 240 |
+
"step": 70
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.27695351137487634,
|
| 244 |
+
"forget_loss": 2.1732415916630998e-05,
|
| 245 |
+
"retain_loss": 1.4336204528808594,
|
| 246 |
+
"step": 70
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.27695351137487634,
|
| 250 |
+
"forget_loss": 1.3687983937415993e-06,
|
| 251 |
+
"retain_loss": 0.9825552105903625,
|
| 252 |
+
"step": 70
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.27695351137487634,
|
| 256 |
+
"forget_loss": 1.326372967014322e-06,
|
| 257 |
+
"retain_loss": 1.3998953104019165,
|
| 258 |
+
"step": 70
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.3165182987141444,
|
| 262 |
+
"grad_norm": 2.390625,
|
| 263 |
+
"learning_rate": 4.3044354838709674e-05,
|
| 264 |
+
"loss": 1.214775276184082,
|
| 265 |
+
"step": 80
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.3165182987141444,
|
| 269 |
+
"forget_loss": 1.3552562450058758e-06,
|
| 270 |
+
"retain_loss": 1.0332047939300537,
|
| 271 |
+
"step": 80
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.3165182987141444,
|
| 275 |
+
"forget_loss": 1.2774065908160992e-05,
|
| 276 |
+
"retain_loss": 1.007059931755066,
|
| 277 |
+
"step": 80
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.3165182987141444,
|
| 281 |
+
"forget_loss": 1.196574157802388e-05,
|
| 282 |
+
"retain_loss": 0.8872216939926147,
|
| 283 |
+
"step": 80
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3165182987141444,
|
| 287 |
+
"forget_loss": 4.2263846466994437e-07,
|
| 288 |
+
"retain_loss": 0.8739179372787476,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.3560830860534125,
|
| 293 |
+
"grad_norm": 2.28125,
|
| 294 |
+
"learning_rate": 4.203629032258065e-05,
|
| 295 |
+
"loss": 1.1429722785949707,
|
| 296 |
+
"step": 90
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3560830860534125,
|
| 300 |
+
"forget_loss": 2.522195063647814e-05,
|
| 301 |
+
"retain_loss": 0.8757652640342712,
|
| 302 |
+
"step": 90
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.3560830860534125,
|
| 306 |
+
"forget_loss": 2.2732887373422273e-05,
|
| 307 |
+
"retain_loss": 0.9618234634399414,
|
| 308 |
+
"step": 90
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.3560830860534125,
|
| 312 |
+
"forget_loss": 2.1186065168876667e-06,
|
| 313 |
+
"retain_loss": 0.82012540102005,
|
| 314 |
+
"step": 90
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3560830860534125,
|
| 318 |
+
"forget_loss": 1.5917968994472176e-05,
|
| 319 |
+
"retain_loss": 1.2091050148010254,
|
| 320 |
+
"step": 90
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.39564787339268054,
|
| 324 |
+
"grad_norm": 2.8125,
|
| 325 |
+
"learning_rate": 4.1028225806451615e-05,
|
| 326 |
+
"loss": 0.9440973281860352,
|
| 327 |
+
"step": 100
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.39564787339268054,
|
| 331 |
+
"forget_loss": 5.102012892166385e-07,
|
| 332 |
+
"retain_loss": 0.9886119365692139,
|
| 333 |
+
"step": 100
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.39564787339268054,
|
| 337 |
+
"forget_loss": 2.069048832709086e-06,
|
| 338 |
+
"retain_loss": 1.037408471107483,
|
| 339 |
+
"step": 100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.39564787339268054,
|
| 343 |
+
"forget_loss": 6.717852556903381e-06,
|
| 344 |
+
"retain_loss": 1.2528358697891235,
|
| 345 |
+
"step": 100
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.39564787339268054,
|
| 349 |
+
"forget_loss": 1.7514905266580172e-05,
|
| 350 |
+
"retain_loss": 0.5935210585594177,
|
| 351 |
+
"step": 100
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.4352126607319486,
|
| 355 |
+
"grad_norm": 2.34375,
|
| 356 |
+
"learning_rate": 4.002016129032258e-05,
|
| 357 |
+
"loss": 0.8624692916870117,
|
| 358 |
+
"step": 110
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.4352126607319486,
|
| 362 |
+
"forget_loss": 1.1634347174549475e-05,
|
| 363 |
+
"retain_loss": 0.5517681837081909,
|
| 364 |
+
"step": 110
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.4352126607319486,
|
| 368 |
+
"forget_loss": 6.400139795914583e-08,
|
| 369 |
+
"retain_loss": 1.0467280149459839,
|
| 370 |
+
"step": 110
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.4352126607319486,
|
| 374 |
+
"forget_loss": 1.9029957911698148e-05,
|
| 375 |
+
"retain_loss": 1.1268657445907593,
|
| 376 |
+
"step": 110
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.4352126607319486,
|
| 380 |
+
"forget_loss": 2.5354455601700465e-07,
|
| 381 |
+
"retain_loss": 0.8402698040008545,
|
| 382 |
+
"step": 110
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.47477744807121663,
|
| 386 |
+
"grad_norm": 2.609375,
|
| 387 |
+
"learning_rate": 3.901209677419355e-05,
|
| 388 |
+
"loss": 0.7725035190582276,
|
| 389 |
+
"step": 120
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.47477744807121663,
|
| 393 |
+
"forget_loss": 3.8098887671367265e-06,
|
| 394 |
+
"retain_loss": 0.3457094430923462,
|
| 395 |
+
"step": 120
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.47477744807121663,
|
| 399 |
+
"forget_loss": 2.3242062525241636e-05,
|
| 400 |
+
"retain_loss": 0.6856692433357239,
|
| 401 |
+
"step": 120
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.47477744807121663,
|
| 405 |
+
"forget_loss": 8.018694643396884e-06,
|
| 406 |
+
"retain_loss": 1.2206052541732788,
|
| 407 |
+
"step": 120
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.47477744807121663,
|
| 411 |
+
"forget_loss": 3.351060968270758e-06,
|
| 412 |
+
"retain_loss": 0.7469509840011597,
|
| 413 |
+
"step": 120
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.5143422354104846,
|
| 417 |
+
"grad_norm": 2.640625,
|
| 418 |
+
"learning_rate": 3.800403225806452e-05,
|
| 419 |
+
"loss": 0.6184093952178955,
|
| 420 |
+
"step": 130
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.5143422354104846,
|
| 424 |
+
"forget_loss": 3.902082880813396e-06,
|
| 425 |
+
"retain_loss": 0.9034799933433533,
|
| 426 |
+
"step": 130
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.5143422354104846,
|
| 430 |
+
"forget_loss": 1.8487480701878667e-07,
|
| 431 |
+
"retain_loss": 0.944042980670929,
|
| 432 |
+
"step": 130
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.5143422354104846,
|
| 436 |
+
"forget_loss": 7.273596338563948e-07,
|
| 437 |
+
"retain_loss": 0.589636504650116,
|
| 438 |
+
"step": 130
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.5143422354104846,
|
| 442 |
+
"forget_loss": 6.394767115125433e-05,
|
| 443 |
+
"retain_loss": 0.8495606780052185,
|
| 444 |
+
"step": 130
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5539070227497527,
|
| 448 |
+
"grad_norm": 2.09375,
|
| 449 |
+
"learning_rate": 3.6995967741935484e-05,
|
| 450 |
+
"loss": 0.5851613521575928,
|
| 451 |
+
"step": 140
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5539070227497527,
|
| 455 |
+
"forget_loss": 1.9570716176531278e-06,
|
| 456 |
+
"retain_loss": 0.31179508566856384,
|
| 457 |
+
"step": 140
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5539070227497527,
|
| 461 |
+
"forget_loss": 4.920673745800741e-06,
|
| 462 |
+
"retain_loss": 0.7174519300460815,
|
| 463 |
+
"step": 140
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.5539070227497527,
|
| 467 |
+
"forget_loss": 9.13152689463459e-07,
|
| 468 |
+
"retain_loss": 0.44045335054397583,
|
| 469 |
+
"step": 140
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.5539070227497527,
|
| 473 |
+
"forget_loss": 7.388467793134623e-07,
|
| 474 |
+
"retain_loss": 0.35985979437828064,
|
| 475 |
+
"step": 140
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.5934718100890207,
|
| 479 |
+
"grad_norm": 2.0625,
|
| 480 |
+
"learning_rate": 3.598790322580645e-05,
|
| 481 |
+
"loss": 0.5792353630065918,
|
| 482 |
+
"step": 150
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.5934718100890207,
|
| 486 |
+
"forget_loss": 1.258710966567378e-07,
|
| 487 |
+
"retain_loss": 0.45937851071357727,
|
| 488 |
+
"step": 150
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.5934718100890207,
|
| 492 |
+
"forget_loss": 7.370726962108165e-07,
|
| 493 |
+
"retain_loss": 0.27468791604042053,
|
| 494 |
+
"step": 150
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.5934718100890207,
|
| 498 |
+
"forget_loss": 8.536089808330871e-06,
|
| 499 |
+
"retain_loss": 0.8069593906402588,
|
| 500 |
+
"step": 150
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.5934718100890207,
|
| 504 |
+
"forget_loss": 8.370562341042387e-07,
|
| 505 |
+
"retain_loss": 0.15817895531654358,
|
| 506 |
+
"step": 150
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.6330365974282888,
|
| 510 |
+
"grad_norm": 1.703125,
|
| 511 |
+
"learning_rate": 3.497983870967742e-05,
|
| 512 |
+
"loss": 0.40374002456665037,
|
| 513 |
+
"step": 160
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6330365974282888,
|
| 517 |
+
"forget_loss": 4.5395900087896734e-06,
|
| 518 |
+
"retain_loss": 0.6503518223762512,
|
| 519 |
+
"step": 160
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.6330365974282888,
|
| 523 |
+
"forget_loss": 1.2475591120164609e-06,
|
| 524 |
+
"retain_loss": 0.29691439867019653,
|
| 525 |
+
"step": 160
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.6330365974282888,
|
| 529 |
+
"forget_loss": 7.69290522839583e-07,
|
| 530 |
+
"retain_loss": 0.3579648435115814,
|
| 531 |
+
"step": 160
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.6330365974282888,
|
| 535 |
+
"forget_loss": 3.610326075431658e-06,
|
| 536 |
+
"retain_loss": 0.3425873816013336,
|
| 537 |
+
"step": 160
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.6726013847675568,
|
| 541 |
+
"grad_norm": 2.171875,
|
| 542 |
+
"learning_rate": 3.397177419354839e-05,
|
| 543 |
+
"loss": 0.3935901641845703,
|
| 544 |
+
"step": 170
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.6726013847675568,
|
| 548 |
+
"forget_loss": 7.11527832208958e-07,
|
| 549 |
+
"retain_loss": 0.45746102929115295,
|
| 550 |
+
"step": 170
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.6726013847675568,
|
| 554 |
+
"forget_loss": 3.808730753007694e-07,
|
| 555 |
+
"retain_loss": 0.4325888454914093,
|
| 556 |
+
"step": 170
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6726013847675568,
|
| 560 |
+
"forget_loss": 1.3094180530970334e-06,
|
| 561 |
+
"retain_loss": 0.1893959939479828,
|
| 562 |
+
"step": 170
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.6726013847675568,
|
| 566 |
+
"forget_loss": 5.8092759900318924e-06,
|
| 567 |
+
"retain_loss": 1.1242655515670776,
|
| 568 |
+
"step": 170
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.712166172106825,
|
| 572 |
+
"grad_norm": 2.28125,
|
| 573 |
+
"learning_rate": 3.296370967741936e-05,
|
| 574 |
+
"loss": 0.37663323879241944,
|
| 575 |
+
"step": 180
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.712166172106825,
|
| 579 |
+
"forget_loss": 1.8580192318040645e-06,
|
| 580 |
+
"retain_loss": 0.24432934820652008,
|
| 581 |
+
"step": 180
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.712166172106825,
|
| 585 |
+
"forget_loss": 3.5925964425587154e-07,
|
| 586 |
+
"retain_loss": 0.2534143328666687,
|
| 587 |
+
"step": 180
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.712166172106825,
|
| 591 |
+
"forget_loss": 5.5626283028686885e-06,
|
| 592 |
+
"retain_loss": 0.23151986300945282,
|
| 593 |
+
"step": 180
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.712166172106825,
|
| 597 |
+
"forget_loss": 5.4275651564239524e-06,
|
| 598 |
+
"retain_loss": 0.2856011688709259,
|
| 599 |
+
"step": 180
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.751730959446093,
|
| 603 |
+
"grad_norm": 2.265625,
|
| 604 |
+
"learning_rate": 3.1955645161290326e-05,
|
| 605 |
+
"loss": 0.3224222183227539,
|
| 606 |
+
"step": 190
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.751730959446093,
|
| 610 |
+
"forget_loss": 2.0351612874947023e-06,
|
| 611 |
+
"retain_loss": 0.30106958746910095,
|
| 612 |
+
"step": 190
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.751730959446093,
|
| 616 |
+
"forget_loss": 1.137744402512908e-05,
|
| 617 |
+
"retain_loss": 0.35559219121932983,
|
| 618 |
+
"step": 190
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.751730959446093,
|
| 622 |
+
"forget_loss": 4.769389647663047e-07,
|
| 623 |
+
"retain_loss": 0.12539999186992645,
|
| 624 |
+
"step": 190
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.751730959446093,
|
| 628 |
+
"forget_loss": 1.536158151793643e-07,
|
| 629 |
+
"retain_loss": 0.5091521143913269,
|
| 630 |
+
"step": 190
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.7912957467853611,
|
| 634 |
+
"grad_norm": 1.984375,
|
| 635 |
+
"learning_rate": 3.0947580645161286e-05,
|
| 636 |
+
"loss": 0.32691752910614014,
|
| 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:f4daa46b81e960187a13cf9715d61600f7d344da408f25fda410bfb3b965becf
|
| 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:abc2ec2327ea197a8a533f49660f35b1592bb4d0c19c27b24af176b1c42e6676
|
| 3 |
+
size 14596063960
|
checkpoint-400/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:941f95975671daa10f60e587093385f2abc159ef4ddb59b4d5ebcd64bb0d4f3c
|
| 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": 2.203125,
|
| 77 |
+
"learning_rate": 4.909274193548387e-05,
|
| 78 |
+
"loss": 2.1829532623291015,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0791295746785361,
|
| 83 |
+
"forget_loss": 3.1555460736854e-05,
|
| 84 |
+
"retain_loss": 2.056671380996704,
|
| 85 |
+
"step": 20
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.0791295746785361,
|
| 89 |
+
"forget_loss": 1.3120857147441711e-05,
|
| 90 |
+
"retain_loss": 1.9920682907104492,
|
| 91 |
+
"step": 20
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.0791295746785361,
|
| 95 |
+
"forget_loss": 8.181996963685378e-05,
|
| 96 |
+
"retain_loss": 2.149359703063965,
|
| 97 |
+
"step": 20
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.0791295746785361,
|
| 101 |
+
"forget_loss": 4.155315400566906e-05,
|
| 102 |
+
"retain_loss": 1.797939419746399,
|
| 103 |
+
"step": 20
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.11869436201780416,
|
| 107 |
+
"grad_norm": 2.03125,
|
| 108 |
+
"learning_rate": 4.808467741935484e-05,
|
| 109 |
+
"loss": 1.9520586013793946,
|
| 110 |
+
"step": 30
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.11869436201780416,
|
| 114 |
+
"forget_loss": 2.097734068229329e-06,
|
| 115 |
+
"retain_loss": 1.9717810153961182,
|
| 116 |
+
"step": 30
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.11869436201780416,
|
| 120 |
+
"forget_loss": 9.0424384779908e-07,
|
| 121 |
+
"retain_loss": 2.1347732543945312,
|
| 122 |
+
"step": 30
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.11869436201780416,
|
| 126 |
+
"forget_loss": 1.5195576452242676e-05,
|
| 127 |
+
"retain_loss": 1.7591031789779663,
|
| 128 |
+
"step": 30
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.11869436201780416,
|
| 132 |
+
"forget_loss": 2.9381511922110803e-05,
|
| 133 |
+
"retain_loss": 2.324976682662964,
|
| 134 |
+
"step": 30
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.1582591493570722,
|
| 138 |
+
"grad_norm": 1.9453125,
|
| 139 |
+
"learning_rate": 4.7076612903225806e-05,
|
| 140 |
+
"loss": 1.7898395538330079,
|
| 141 |
+
"step": 40
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.1582591493570722,
|
| 145 |
+
"forget_loss": 2.347593181184493e-05,
|
| 146 |
+
"retain_loss": 1.5896490812301636,
|
| 147 |
+
"step": 40
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.1582591493570722,
|
| 151 |
+
"forget_loss": 2.7579757443163544e-05,
|
| 152 |
+
"retain_loss": 1.1212265491485596,
|
| 153 |
+
"step": 40
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.1582591493570722,
|
| 157 |
+
"forget_loss": 2.1694726456189528e-05,
|
| 158 |
+
"retain_loss": 2.051854133605957,
|
| 159 |
+
"step": 40
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.1582591493570722,
|
| 163 |
+
"forget_loss": 6.128148925199639e-06,
|
| 164 |
+
"retain_loss": 1.6619952917099,
|
| 165 |
+
"step": 40
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.19782393669634027,
|
| 169 |
+
"grad_norm": 1.96875,
|
| 170 |
+
"learning_rate": 4.606854838709678e-05,
|
| 171 |
+
"loss": 1.5459610939025878,
|
| 172 |
+
"step": 50
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.19782393669634027,
|
| 176 |
+
"forget_loss": 1.4324338735605124e-05,
|
| 177 |
+
"retain_loss": 1.7004584074020386,
|
| 178 |
+
"step": 50
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.19782393669634027,
|
| 182 |
+
"forget_loss": 5.814884843857726e-06,
|
| 183 |
+
"retain_loss": 1.3355984687805176,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.19782393669634027,
|
| 188 |
+
"forget_loss": 1.4618005934607936e-06,
|
| 189 |
+
"retain_loss": 1.7750041484832764,
|
| 190 |
+
"step": 50
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.19782393669634027,
|
| 194 |
+
"forget_loss": 1.6271239928755676e-06,
|
| 195 |
+
"retain_loss": 1.4064531326293945,
|
| 196 |
+
"step": 50
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.23738872403560832,
|
| 200 |
+
"grad_norm": 2.234375,
|
| 201 |
+
"learning_rate": 4.506048387096775e-05,
|
| 202 |
+
"loss": 1.4617247581481934,
|
| 203 |
+
"step": 60
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.23738872403560832,
|
| 207 |
+
"forget_loss": 9.254661563318223e-06,
|
| 208 |
+
"retain_loss": 1.8761130571365356,
|
| 209 |
+
"step": 60
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.23738872403560832,
|
| 213 |
+
"forget_loss": 9.365790901938453e-06,
|
| 214 |
+
"retain_loss": 1.1389141082763672,
|
| 215 |
+
"step": 60
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.23738872403560832,
|
| 219 |
+
"forget_loss": 6.40576909063384e-05,
|
| 220 |
+
"retain_loss": 1.0727425813674927,
|
| 221 |
+
"step": 60
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.23738872403560832,
|
| 225 |
+
"forget_loss": 3.140630724374205e-06,
|
| 226 |
+
"retain_loss": 1.2311009168624878,
|
| 227 |
+
"step": 60
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.27695351137487634,
|
| 231 |
+
"grad_norm": 2.125,
|
| 232 |
+
"learning_rate": 4.4052419354838714e-05,
|
| 233 |
+
"loss": 1.344314193725586,
|
| 234 |
+
"step": 70
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.27695351137487634,
|
| 238 |
+
"forget_loss": 2.0407464035088196e-05,
|
| 239 |
+
"retain_loss": 1.2631032466888428,
|
| 240 |
+
"step": 70
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.27695351137487634,
|
| 244 |
+
"forget_loss": 2.1732415916630998e-05,
|
| 245 |
+
"retain_loss": 1.4336204528808594,
|
| 246 |
+
"step": 70
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.27695351137487634,
|
| 250 |
+
"forget_loss": 1.3687983937415993e-06,
|
| 251 |
+
"retain_loss": 0.9825552105903625,
|
| 252 |
+
"step": 70
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.27695351137487634,
|
| 256 |
+
"forget_loss": 1.326372967014322e-06,
|
| 257 |
+
"retain_loss": 1.3998953104019165,
|
| 258 |
+
"step": 70
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.3165182987141444,
|
| 262 |
+
"grad_norm": 2.390625,
|
| 263 |
+
"learning_rate": 4.3044354838709674e-05,
|
| 264 |
+
"loss": 1.214775276184082,
|
| 265 |
+
"step": 80
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.3165182987141444,
|
| 269 |
+
"forget_loss": 1.3552562450058758e-06,
|
| 270 |
+
"retain_loss": 1.0332047939300537,
|
| 271 |
+
"step": 80
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.3165182987141444,
|
| 275 |
+
"forget_loss": 1.2774065908160992e-05,
|
| 276 |
+
"retain_loss": 1.007059931755066,
|
| 277 |
+
"step": 80
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.3165182987141444,
|
| 281 |
+
"forget_loss": 1.196574157802388e-05,
|
| 282 |
+
"retain_loss": 0.8872216939926147,
|
| 283 |
+
"step": 80
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3165182987141444,
|
| 287 |
+
"forget_loss": 4.2263846466994437e-07,
|
| 288 |
+
"retain_loss": 0.8739179372787476,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.3560830860534125,
|
| 293 |
+
"grad_norm": 2.28125,
|
| 294 |
+
"learning_rate": 4.203629032258065e-05,
|
| 295 |
+
"loss": 1.1429722785949707,
|
| 296 |
+
"step": 90
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3560830860534125,
|
| 300 |
+
"forget_loss": 2.522195063647814e-05,
|
| 301 |
+
"retain_loss": 0.8757652640342712,
|
| 302 |
+
"step": 90
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.3560830860534125,
|
| 306 |
+
"forget_loss": 2.2732887373422273e-05,
|
| 307 |
+
"retain_loss": 0.9618234634399414,
|
| 308 |
+
"step": 90
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.3560830860534125,
|
| 312 |
+
"forget_loss": 2.1186065168876667e-06,
|
| 313 |
+
"retain_loss": 0.82012540102005,
|
| 314 |
+
"step": 90
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3560830860534125,
|
| 318 |
+
"forget_loss": 1.5917968994472176e-05,
|
| 319 |
+
"retain_loss": 1.2091050148010254,
|
| 320 |
+
"step": 90
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.39564787339268054,
|
| 324 |
+
"grad_norm": 2.8125,
|
| 325 |
+
"learning_rate": 4.1028225806451615e-05,
|
| 326 |
+
"loss": 0.9440973281860352,
|
| 327 |
+
"step": 100
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.39564787339268054,
|
| 331 |
+
"forget_loss": 5.102012892166385e-07,
|
| 332 |
+
"retain_loss": 0.9886119365692139,
|
| 333 |
+
"step": 100
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.39564787339268054,
|
| 337 |
+
"forget_loss": 2.069048832709086e-06,
|
| 338 |
+
"retain_loss": 1.037408471107483,
|
| 339 |
+
"step": 100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.39564787339268054,
|
| 343 |
+
"forget_loss": 6.717852556903381e-06,
|
| 344 |
+
"retain_loss": 1.2528358697891235,
|
| 345 |
+
"step": 100
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.39564787339268054,
|
| 349 |
+
"forget_loss": 1.7514905266580172e-05,
|
| 350 |
+
"retain_loss": 0.5935210585594177,
|
| 351 |
+
"step": 100
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.4352126607319486,
|
| 355 |
+
"grad_norm": 2.34375,
|
| 356 |
+
"learning_rate": 4.002016129032258e-05,
|
| 357 |
+
"loss": 0.8624692916870117,
|
| 358 |
+
"step": 110
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.4352126607319486,
|
| 362 |
+
"forget_loss": 1.1634347174549475e-05,
|
| 363 |
+
"retain_loss": 0.5517681837081909,
|
| 364 |
+
"step": 110
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.4352126607319486,
|
| 368 |
+
"forget_loss": 6.400139795914583e-08,
|
| 369 |
+
"retain_loss": 1.0467280149459839,
|
| 370 |
+
"step": 110
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.4352126607319486,
|
| 374 |
+
"forget_loss": 1.9029957911698148e-05,
|
| 375 |
+
"retain_loss": 1.1268657445907593,
|
| 376 |
+
"step": 110
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.4352126607319486,
|
| 380 |
+
"forget_loss": 2.5354455601700465e-07,
|
| 381 |
+
"retain_loss": 0.8402698040008545,
|
| 382 |
+
"step": 110
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.47477744807121663,
|
| 386 |
+
"grad_norm": 2.609375,
|
| 387 |
+
"learning_rate": 3.901209677419355e-05,
|
| 388 |
+
"loss": 0.7725035190582276,
|
| 389 |
+
"step": 120
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.47477744807121663,
|
| 393 |
+
"forget_loss": 3.8098887671367265e-06,
|
| 394 |
+
"retain_loss": 0.3457094430923462,
|
| 395 |
+
"step": 120
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.47477744807121663,
|
| 399 |
+
"forget_loss": 2.3242062525241636e-05,
|
| 400 |
+
"retain_loss": 0.6856692433357239,
|
| 401 |
+
"step": 120
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.47477744807121663,
|
| 405 |
+
"forget_loss": 8.018694643396884e-06,
|
| 406 |
+
"retain_loss": 1.2206052541732788,
|
| 407 |
+
"step": 120
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.47477744807121663,
|
| 411 |
+
"forget_loss": 3.351060968270758e-06,
|
| 412 |
+
"retain_loss": 0.7469509840011597,
|
| 413 |
+
"step": 120
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.5143422354104846,
|
| 417 |
+
"grad_norm": 2.640625,
|
| 418 |
+
"learning_rate": 3.800403225806452e-05,
|
| 419 |
+
"loss": 0.6184093952178955,
|
| 420 |
+
"step": 130
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.5143422354104846,
|
| 424 |
+
"forget_loss": 3.902082880813396e-06,
|
| 425 |
+
"retain_loss": 0.9034799933433533,
|
| 426 |
+
"step": 130
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.5143422354104846,
|
| 430 |
+
"forget_loss": 1.8487480701878667e-07,
|
| 431 |
+
"retain_loss": 0.944042980670929,
|
| 432 |
+
"step": 130
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.5143422354104846,
|
| 436 |
+
"forget_loss": 7.273596338563948e-07,
|
| 437 |
+
"retain_loss": 0.589636504650116,
|
| 438 |
+
"step": 130
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.5143422354104846,
|
| 442 |
+
"forget_loss": 6.394767115125433e-05,
|
| 443 |
+
"retain_loss": 0.8495606780052185,
|
| 444 |
+
"step": 130
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5539070227497527,
|
| 448 |
+
"grad_norm": 2.09375,
|
| 449 |
+
"learning_rate": 3.6995967741935484e-05,
|
| 450 |
+
"loss": 0.5851613521575928,
|
| 451 |
+
"step": 140
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5539070227497527,
|
| 455 |
+
"forget_loss": 1.9570716176531278e-06,
|
| 456 |
+
"retain_loss": 0.31179508566856384,
|
| 457 |
+
"step": 140
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5539070227497527,
|
| 461 |
+
"forget_loss": 4.920673745800741e-06,
|
| 462 |
+
"retain_loss": 0.7174519300460815,
|
| 463 |
+
"step": 140
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.5539070227497527,
|
| 467 |
+
"forget_loss": 9.13152689463459e-07,
|
| 468 |
+
"retain_loss": 0.44045335054397583,
|
| 469 |
+
"step": 140
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.5539070227497527,
|
| 473 |
+
"forget_loss": 7.388467793134623e-07,
|
| 474 |
+
"retain_loss": 0.35985979437828064,
|
| 475 |
+
"step": 140
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.5934718100890207,
|
| 479 |
+
"grad_norm": 2.0625,
|
| 480 |
+
"learning_rate": 3.598790322580645e-05,
|
| 481 |
+
"loss": 0.5792353630065918,
|
| 482 |
+
"step": 150
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.5934718100890207,
|
| 486 |
+
"forget_loss": 1.258710966567378e-07,
|
| 487 |
+
"retain_loss": 0.45937851071357727,
|
| 488 |
+
"step": 150
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.5934718100890207,
|
| 492 |
+
"forget_loss": 7.370726962108165e-07,
|
| 493 |
+
"retain_loss": 0.27468791604042053,
|
| 494 |
+
"step": 150
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.5934718100890207,
|
| 498 |
+
"forget_loss": 8.536089808330871e-06,
|
| 499 |
+
"retain_loss": 0.8069593906402588,
|
| 500 |
+
"step": 150
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.5934718100890207,
|
| 504 |
+
"forget_loss": 8.370562341042387e-07,
|
| 505 |
+
"retain_loss": 0.15817895531654358,
|
| 506 |
+
"step": 150
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.6330365974282888,
|
| 510 |
+
"grad_norm": 1.703125,
|
| 511 |
+
"learning_rate": 3.497983870967742e-05,
|
| 512 |
+
"loss": 0.40374002456665037,
|
| 513 |
+
"step": 160
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6330365974282888,
|
| 517 |
+
"forget_loss": 4.5395900087896734e-06,
|
| 518 |
+
"retain_loss": 0.6503518223762512,
|
| 519 |
+
"step": 160
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.6330365974282888,
|
| 523 |
+
"forget_loss": 1.2475591120164609e-06,
|
| 524 |
+
"retain_loss": 0.29691439867019653,
|
| 525 |
+
"step": 160
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.6330365974282888,
|
| 529 |
+
"forget_loss": 7.69290522839583e-07,
|
| 530 |
+
"retain_loss": 0.3579648435115814,
|
| 531 |
+
"step": 160
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.6330365974282888,
|
| 535 |
+
"forget_loss": 3.610326075431658e-06,
|
| 536 |
+
"retain_loss": 0.3425873816013336,
|
| 537 |
+
"step": 160
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.6726013847675568,
|
| 541 |
+
"grad_norm": 2.171875,
|
| 542 |
+
"learning_rate": 3.397177419354839e-05,
|
| 543 |
+
"loss": 0.3935901641845703,
|
| 544 |
+
"step": 170
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.6726013847675568,
|
| 548 |
+
"forget_loss": 7.11527832208958e-07,
|
| 549 |
+
"retain_loss": 0.45746102929115295,
|
| 550 |
+
"step": 170
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.6726013847675568,
|
| 554 |
+
"forget_loss": 3.808730753007694e-07,
|
| 555 |
+
"retain_loss": 0.4325888454914093,
|
| 556 |
+
"step": 170
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6726013847675568,
|
| 560 |
+
"forget_loss": 1.3094180530970334e-06,
|
| 561 |
+
"retain_loss": 0.1893959939479828,
|
| 562 |
+
"step": 170
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.6726013847675568,
|
| 566 |
+
"forget_loss": 5.8092759900318924e-06,
|
| 567 |
+
"retain_loss": 1.1242655515670776,
|
| 568 |
+
"step": 170
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.712166172106825,
|
| 572 |
+
"grad_norm": 2.28125,
|
| 573 |
+
"learning_rate": 3.296370967741936e-05,
|
| 574 |
+
"loss": 0.37663323879241944,
|
| 575 |
+
"step": 180
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.712166172106825,
|
| 579 |
+
"forget_loss": 1.8580192318040645e-06,
|
| 580 |
+
"retain_loss": 0.24432934820652008,
|
| 581 |
+
"step": 180
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.712166172106825,
|
| 585 |
+
"forget_loss": 3.5925964425587154e-07,
|
| 586 |
+
"retain_loss": 0.2534143328666687,
|
| 587 |
+
"step": 180
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.712166172106825,
|
| 591 |
+
"forget_loss": 5.5626283028686885e-06,
|
| 592 |
+
"retain_loss": 0.23151986300945282,
|
| 593 |
+
"step": 180
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.712166172106825,
|
| 597 |
+
"forget_loss": 5.4275651564239524e-06,
|
| 598 |
+
"retain_loss": 0.2856011688709259,
|
| 599 |
+
"step": 180
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.751730959446093,
|
| 603 |
+
"grad_norm": 2.265625,
|
| 604 |
+
"learning_rate": 3.1955645161290326e-05,
|
| 605 |
+
"loss": 0.3224222183227539,
|
| 606 |
+
"step": 190
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.751730959446093,
|
| 610 |
+
"forget_loss": 2.0351612874947023e-06,
|
| 611 |
+
"retain_loss": 0.30106958746910095,
|
| 612 |
+
"step": 190
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.751730959446093,
|
| 616 |
+
"forget_loss": 1.137744402512908e-05,
|
| 617 |
+
"retain_loss": 0.35559219121932983,
|
| 618 |
+
"step": 190
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.751730959446093,
|
| 622 |
+
"forget_loss": 4.769389647663047e-07,
|
| 623 |
+
"retain_loss": 0.12539999186992645,
|
| 624 |
+
"step": 190
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.751730959446093,
|
| 628 |
+
"forget_loss": 1.536158151793643e-07,
|
| 629 |
+
"retain_loss": 0.5091521143913269,
|
| 630 |
+
"step": 190
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.7912957467853611,
|
| 634 |
+
"grad_norm": 1.984375,
|
| 635 |
+
"learning_rate": 3.0947580645161286e-05,
|
| 636 |
+
"loss": 0.32691752910614014,
|
| 637 |
+
"step": 200
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.7912957467853611,
|
| 641 |
+
"forget_loss": 4.226240889693145e-06,
|
| 642 |
+
"retain_loss": 0.13701662421226501,
|
| 643 |
+
"step": 200
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.7912957467853611,
|
| 647 |
+
"forget_loss": 1.258511565538356e-05,
|
| 648 |
+
"retain_loss": 0.10310296714305878,
|
| 649 |
+
"step": 200
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.7912957467853611,
|
| 653 |
+
"forget_loss": 1.963040858754539e-06,
|
| 654 |
+
"retain_loss": 0.08762754499912262,
|
| 655 |
+
"step": 200
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.7912957467853611,
|
| 659 |
+
"forget_loss": 1.235385980180581e-06,
|
| 660 |
+
"retain_loss": 0.2134196013212204,
|
| 661 |
+
"step": 200
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.8308605341246291,
|
| 665 |
+
"grad_norm": 1.765625,
|
| 666 |
+
"learning_rate": 2.9939516129032256e-05,
|
| 667 |
+
"loss": 0.23421640396118165,
|
| 668 |
+
"step": 210
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.8308605341246291,
|
| 672 |
+
"forget_loss": 3.501550236251205e-05,
|
| 673 |
+
"retain_loss": 0.17837883532047272,
|
| 674 |
+
"step": 210
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.8308605341246291,
|
| 678 |
+
"forget_loss": 1.5083353446243564e-06,
|
| 679 |
+
"retain_loss": 0.1773965209722519,
|
| 680 |
+
"step": 210
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.8308605341246291,
|
| 684 |
+
"forget_loss": 1.7007857877615606e-06,
|
| 685 |
+
"retain_loss": 0.11213231086730957,
|
| 686 |
+
"step": 210
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.8308605341246291,
|
| 690 |
+
"forget_loss": 5.62718128094275e-07,
|
| 691 |
+
"retain_loss": 0.10278806835412979,
|
| 692 |
+
"step": 210
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.8704253214638972,
|
| 696 |
+
"grad_norm": 2.53125,
|
| 697 |
+
"learning_rate": 2.8931451612903227e-05,
|
| 698 |
+
"loss": 0.20826613903045654,
|
| 699 |
+
"step": 220
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.8704253214638972,
|
| 703 |
+
"forget_loss": 5.792419415229233e-07,
|
| 704 |
+
"retain_loss": 0.06651624292135239,
|
| 705 |
+
"step": 220
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.8704253214638972,
|
| 709 |
+
"forget_loss": 1.4317017758003203e-06,
|
| 710 |
+
"retain_loss": 0.3651600480079651,
|
| 711 |
+
"step": 220
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.8704253214638972,
|
| 715 |
+
"forget_loss": 2.790197299873398e-07,
|
| 716 |
+
"retain_loss": 0.059690482914447784,
|
| 717 |
+
"step": 220
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.8704253214638972,
|
| 721 |
+
"forget_loss": 2.358171514060814e-06,
|
| 722 |
+
"retain_loss": 0.07482323050498962,
|
| 723 |
+
"step": 220
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.9099901088031652,
|
| 727 |
+
"grad_norm": 2.015625,
|
| 728 |
+
"learning_rate": 2.7923387096774194e-05,
|
| 729 |
+
"loss": 0.19134424924850463,
|
| 730 |
+
"step": 230
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.9099901088031652,
|
| 734 |
+
"forget_loss": 1.6788119410193758e-06,
|
| 735 |
+
"retain_loss": 0.11503209918737411,
|
| 736 |
+
"step": 230
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.9099901088031652,
|
| 740 |
+
"forget_loss": 1.3623559880215907e-06,
|
| 741 |
+
"retain_loss": 0.09323878586292267,
|
| 742 |
+
"step": 230
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.9099901088031652,
|
| 746 |
+
"forget_loss": 9.115094599110307e-07,
|
| 747 |
+
"retain_loss": 0.2667946219444275,
|
| 748 |
+
"step": 230
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.9099901088031652,
|
| 752 |
+
"forget_loss": 1.176637056232721e-06,
|
| 753 |
+
"retain_loss": 0.09373427927494049,
|
| 754 |
+
"step": 230
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.9495548961424333,
|
| 758 |
+
"grad_norm": 1.890625,
|
| 759 |
+
"learning_rate": 2.6915322580645164e-05,
|
| 760 |
+
"loss": 0.19541234970092775,
|
| 761 |
+
"step": 240
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.9495548961424333,
|
| 765 |
+
"forget_loss": 4.323494522395777e-06,
|
| 766 |
+
"retain_loss": 0.060076676309108734,
|
| 767 |
+
"step": 240
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.9495548961424333,
|
| 771 |
+
"forget_loss": 3.29818294630968e-06,
|
| 772 |
+
"retain_loss": 0.1765175312757492,
|
| 773 |
+
"step": 240
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.9495548961424333,
|
| 777 |
+
"forget_loss": 1.1875378902459488e-07,
|
| 778 |
+
"retain_loss": 0.04277701675891876,
|
| 779 |
+
"step": 240
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.9495548961424333,
|
| 783 |
+
"forget_loss": 2.5362205633427948e-06,
|
| 784 |
+
"retain_loss": 0.05752837285399437,
|
| 785 |
+
"step": 240
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.9891196834817013,
|
| 789 |
+
"grad_norm": 1.4453125,
|
| 790 |
+
"learning_rate": 2.590725806451613e-05,
|
| 791 |
+
"loss": 0.17172594070434571,
|
| 792 |
+
"step": 250
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.9891196834817013,
|
| 796 |
+
"forget_loss": 2.3277580112335272e-06,
|
| 797 |
+
"retain_loss": 0.08483278006315231,
|
| 798 |
+
"step": 250
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.9891196834817013,
|
| 802 |
+
"forget_loss": 5.033873094362207e-06,
|
| 803 |
+
"retain_loss": 0.24280749261379242,
|
| 804 |
+
"step": 250
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.9891196834817013,
|
| 808 |
+
"forget_loss": 4.555405212158803e-06,
|
| 809 |
+
"retain_loss": 0.4092475473880768,
|
| 810 |
+
"step": 250
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.9891196834817013,
|
| 814 |
+
"forget_loss": 4.822932737624797e-07,
|
| 815 |
+
"retain_loss": 0.062368009239435196,
|
| 816 |
+
"step": 250
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 1.0276953511374876,
|
| 820 |
+
"grad_norm": 2.078125,
|
| 821 |
+
"learning_rate": 2.48991935483871e-05,
|
| 822 |
+
"loss": 0.14231110811233522,
|
| 823 |
+
"step": 260
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 1.0276953511374876,
|
| 827 |
+
"forget_loss": 2.3665279513807036e-06,
|
| 828 |
+
"retain_loss": 0.04678928107023239,
|
| 829 |
+
"step": 260
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.0276953511374876,
|
| 833 |
+
"forget_loss": 1.7857011016531033e-06,
|
| 834 |
+
"retain_loss": 0.15241962671279907,
|
| 835 |
+
"step": 260
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.0276953511374876,
|
| 839 |
+
"forget_loss": 3.6310279938334133e-07,
|
| 840 |
+
"retain_loss": 0.20368625223636627,
|
| 841 |
+
"step": 260
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.0276953511374876,
|
| 845 |
+
"forget_loss": 5.83898440709163e-07,
|
| 846 |
+
"retain_loss": 0.06002001464366913,
|
| 847 |
+
"step": 260
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.0672601384767557,
|
| 851 |
+
"grad_norm": 1.4921875,
|
| 852 |
+
"learning_rate": 2.3891129032258066e-05,
|
| 853 |
+
"loss": 0.12347257137298584,
|
| 854 |
+
"step": 270
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.0672601384767557,
|
| 858 |
+
"forget_loss": 6.095945082051912e-07,
|
| 859 |
+
"retain_loss": 0.2563520669937134,
|
| 860 |
+
"step": 270
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.0672601384767557,
|
| 864 |
+
"forget_loss": 7.611353112224606e-07,
|
| 865 |
+
"retain_loss": 0.23337779939174652,
|
| 866 |
+
"step": 270
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.0672601384767557,
|
| 870 |
+
"forget_loss": 1.0488522548257606e-06,
|
| 871 |
+
"retain_loss": 0.0406014546751976,
|
| 872 |
+
"step": 270
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.0672601384767557,
|
| 876 |
+
"forget_loss": 1.4446818568103481e-06,
|
| 877 |
+
"retain_loss": 0.03464161604642868,
|
| 878 |
+
"step": 270
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.1068249258160237,
|
| 882 |
+
"grad_norm": 0.97265625,
|
| 883 |
+
"learning_rate": 2.2883064516129033e-05,
|
| 884 |
+
"loss": 0.12490516901016235,
|
| 885 |
+
"step": 280
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.1068249258160237,
|
| 889 |
+
"forget_loss": 2.0972819925191288e-07,
|
| 890 |
+
"retain_loss": 0.038518667221069336,
|
| 891 |
+
"step": 280
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.1068249258160237,
|
| 895 |
+
"forget_loss": 2.309284582224791e-06,
|
| 896 |
+
"retain_loss": 0.05753574147820473,
|
| 897 |
+
"step": 280
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.1068249258160237,
|
| 901 |
+
"forget_loss": 4.084875797616405e-07,
|
| 902 |
+
"retain_loss": 0.10644430667161942,
|
| 903 |
+
"step": 280
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.1068249258160237,
|
| 907 |
+
"forget_loss": 1.1346749317908689e-08,
|
| 908 |
+
"retain_loss": 0.11500366032123566,
|
| 909 |
+
"step": 280
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.1463897131552918,
|
| 913 |
+
"grad_norm": 1.109375,
|
| 914 |
+
"learning_rate": 2.1875e-05,
|
| 915 |
+
"loss": 0.09100213646888733,
|
| 916 |
+
"step": 290
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.1463897131552918,
|
| 920 |
+
"forget_loss": 4.1612356653786264e-06,
|
| 921 |
+
"retain_loss": 0.07052873820066452,
|
| 922 |
+
"step": 290
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.1463897131552918,
|
| 926 |
+
"forget_loss": 9.997415872931015e-08,
|
| 927 |
+
"retain_loss": 0.04744183272123337,
|
| 928 |
+
"step": 290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 1.1463897131552918,
|
| 932 |
+
"forget_loss": 1.2092109500372317e-06,
|
| 933 |
+
"retain_loss": 0.07089261710643768,
|
| 934 |
+
"step": 290
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.1463897131552918,
|
| 938 |
+
"forget_loss": 2.131706423824653e-06,
|
| 939 |
+
"retain_loss": 0.2522507607936859,
|
| 940 |
+
"step": 290
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.1859545004945597,
|
| 944 |
+
"grad_norm": 1.2265625,
|
| 945 |
+
"learning_rate": 2.086693548387097e-05,
|
| 946 |
+
"loss": 0.09003463983535767,
|
| 947 |
+
"step": 300
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.1859545004945597,
|
| 951 |
+
"forget_loss": 1.1781303328461945e-06,
|
| 952 |
+
"retain_loss": 0.02843177132308483,
|
| 953 |
+
"step": 300
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.1859545004945597,
|
| 957 |
+
"forget_loss": 2.6735065716820827e-07,
|
| 958 |
+
"retain_loss": 0.04060671105980873,
|
| 959 |
+
"step": 300
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.1859545004945597,
|
| 963 |
+
"forget_loss": 3.643542186182458e-06,
|
| 964 |
+
"retain_loss": 0.0628509372472763,
|
| 965 |
+
"step": 300
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.1859545004945597,
|
| 969 |
+
"forget_loss": 4.7639906597396475e-07,
|
| 970 |
+
"retain_loss": 0.03408809378743172,
|
| 971 |
+
"step": 300
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.225519287833828,
|
| 975 |
+
"grad_norm": 0.74609375,
|
| 976 |
+
"learning_rate": 1.9858870967741934e-05,
|
| 977 |
+
"loss": 0.07631087303161621,
|
| 978 |
+
"step": 310
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 1.225519287833828,
|
| 982 |
+
"forget_loss": 1.8324541883885104e-07,
|
| 983 |
+
"retain_loss": 0.1489202380180359,
|
| 984 |
+
"step": 310
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.225519287833828,
|
| 988 |
+
"forget_loss": 1.505328555140295e-06,
|
| 989 |
+
"retain_loss": 0.09023259580135345,
|
| 990 |
+
"step": 310
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.225519287833828,
|
| 994 |
+
"forget_loss": 1.2370117019600002e-06,
|
| 995 |
+
"retain_loss": 0.11567945778369904,
|
| 996 |
+
"step": 310
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.225519287833828,
|
| 1000 |
+
"forget_loss": 6.62587012811855e-07,
|
| 1001 |
+
"retain_loss": 0.07907626777887344,
|
| 1002 |
+
"step": 310
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.265084075173096,
|
| 1006 |
+
"grad_norm": 1.5546875,
|
| 1007 |
+
"learning_rate": 1.8850806451612904e-05,
|
| 1008 |
+
"loss": 0.09484220743179321,
|
| 1009 |
+
"step": 320
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.265084075173096,
|
| 1013 |
+
"forget_loss": 6.137950094853295e-06,
|
| 1014 |
+
"retain_loss": 0.0641757920384407,
|
| 1015 |
+
"step": 320
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 1.265084075173096,
|
| 1019 |
+
"forget_loss": 2.837170541170053e-06,
|
| 1020 |
+
"retain_loss": 0.0350993350148201,
|
| 1021 |
+
"step": 320
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.265084075173096,
|
| 1025 |
+
"forget_loss": 1.2725810449865094e-07,
|
| 1026 |
+
"retain_loss": 0.04542815685272217,
|
| 1027 |
+
"step": 320
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 1.265084075173096,
|
| 1031 |
+
"forget_loss": 4.864556899519812e-07,
|
| 1032 |
+
"retain_loss": 0.05786221846938133,
|
| 1033 |
+
"step": 320
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.304648862512364,
|
| 1037 |
+
"grad_norm": 1.328125,
|
| 1038 |
+
"learning_rate": 1.784274193548387e-05,
|
| 1039 |
+
"loss": 0.06601499915122985,
|
| 1040 |
+
"step": 330
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.304648862512364,
|
| 1044 |
+
"forget_loss": 5.855958420397656e-07,
|
| 1045 |
+
"retain_loss": 0.04558321461081505,
|
| 1046 |
+
"step": 330
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.304648862512364,
|
| 1050 |
+
"forget_loss": 1.0734013358160155e-06,
|
| 1051 |
+
"retain_loss": 0.061824798583984375,
|
| 1052 |
+
"step": 330
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.304648862512364,
|
| 1056 |
+
"forget_loss": 3.7222815763016115e-07,
|
| 1057 |
+
"retain_loss": 0.04270363599061966,
|
| 1058 |
+
"step": 330
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.304648862512364,
|
| 1062 |
+
"forget_loss": 6.617690360144479e-07,
|
| 1063 |
+
"retain_loss": 0.16833367943763733,
|
| 1064 |
+
"step": 330
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.344213649851632,
|
| 1068 |
+
"grad_norm": 0.49609375,
|
| 1069 |
+
"learning_rate": 1.683467741935484e-05,
|
| 1070 |
+
"loss": 0.06903731822967529,
|
| 1071 |
+
"step": 340
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 1.344213649851632,
|
| 1075 |
+
"forget_loss": 1.1879722023877548e-06,
|
| 1076 |
+
"retain_loss": 0.02958919107913971,
|
| 1077 |
+
"step": 340
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.344213649851632,
|
| 1081 |
+
"forget_loss": 4.095278995919216e-07,
|
| 1082 |
+
"retain_loss": 0.04107590764760971,
|
| 1083 |
+
"step": 340
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 1.344213649851632,
|
| 1087 |
+
"forget_loss": 7.392562224595167e-07,
|
| 1088 |
+
"retain_loss": 0.404009610414505,
|
| 1089 |
+
"step": 340
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.344213649851632,
|
| 1093 |
+
"forget_loss": 2.7393613777348946e-07,
|
| 1094 |
+
"retain_loss": 0.02813897468149662,
|
| 1095 |
+
"step": 340
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.3837784371909,
|
| 1099 |
+
"grad_norm": 1.4140625,
|
| 1100 |
+
"learning_rate": 1.5826612903225806e-05,
|
| 1101 |
+
"loss": 0.069232177734375,
|
| 1102 |
+
"step": 350
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.3837784371909,
|
| 1106 |
+
"forget_loss": 6.865487307550211e-07,
|
| 1107 |
+
"retain_loss": 0.02693028561770916,
|
| 1108 |
+
"step": 350
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.3837784371909,
|
| 1112 |
+
"forget_loss": 4.187642161923577e-07,
|
| 1113 |
+
"retain_loss": 0.04608120024204254,
|
| 1114 |
+
"step": 350
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.3837784371909,
|
| 1118 |
+
"forget_loss": 8.139955554042899e-08,
|
| 1119 |
+
"retain_loss": 0.06439628452062607,
|
| 1120 |
+
"step": 350
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 1.3837784371909,
|
| 1124 |
+
"forget_loss": 8.785929139776272e-08,
|
| 1125 |
+
"retain_loss": 0.17509031295776367,
|
| 1126 |
+
"step": 350
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.4233432245301683,
|
| 1130 |
+
"grad_norm": 0.7265625,
|
| 1131 |
+
"learning_rate": 1.4818548387096776e-05,
|
| 1132 |
+
"loss": 0.07515097260475159,
|
| 1133 |
+
"step": 360
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.4233432245301683,
|
| 1137 |
+
"forget_loss": 1.5587008874717867e-06,
|
| 1138 |
+
"retain_loss": 0.027441687881946564,
|
| 1139 |
+
"step": 360
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 1.4233432245301683,
|
| 1143 |
+
"forget_loss": 2.0895599561754352e-07,
|
| 1144 |
+
"retain_loss": 0.022471986711025238,
|
| 1145 |
+
"step": 360
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.4233432245301683,
|
| 1149 |
+
"forget_loss": 6.960410701140063e-07,
|
| 1150 |
+
"retain_loss": 0.0480155348777771,
|
| 1151 |
+
"step": 360
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.4233432245301683,
|
| 1155 |
+
"forget_loss": 1.2851671726821223e-07,
|
| 1156 |
+
"retain_loss": 0.02052563615143299,
|
| 1157 |
+
"step": 360
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.4629080118694362,
|
| 1161 |
+
"grad_norm": 0.75390625,
|
| 1162 |
+
"learning_rate": 1.3810483870967741e-05,
|
| 1163 |
+
"loss": 0.055222952365875246,
|
| 1164 |
+
"step": 370
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.4629080118694362,
|
| 1168 |
+
"forget_loss": 9.040416557581921e-07,
|
| 1169 |
+
"retain_loss": 0.03805703669786453,
|
| 1170 |
+
"step": 370
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.4629080118694362,
|
| 1174 |
+
"forget_loss": 2.56950727361982e-07,
|
| 1175 |
+
"retain_loss": 0.04338216036558151,
|
| 1176 |
+
"step": 370
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 1.4629080118694362,
|
| 1180 |
+
"forget_loss": 1.555378958073561e-06,
|
| 1181 |
+
"retain_loss": 0.027456099167466164,
|
| 1182 |
+
"step": 370
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.4629080118694362,
|
| 1186 |
+
"forget_loss": 1.5528239600826055e-06,
|
| 1187 |
+
"retain_loss": 0.11473647505044937,
|
| 1188 |
+
"step": 370
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 1.5024727992087041,
|
| 1192 |
+
"grad_norm": 0.82421875,
|
| 1193 |
+
"learning_rate": 1.280241935483871e-05,
|
| 1194 |
+
"loss": 0.05010308623313904,
|
| 1195 |
+
"step": 380
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 1.5024727992087041,
|
| 1199 |
+
"forget_loss": 6.783013759559253e-07,
|
| 1200 |
+
"retain_loss": 0.044970110058784485,
|
| 1201 |
+
"step": 380
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 1.5024727992087041,
|
| 1205 |
+
"forget_loss": 5.374618922360241e-06,
|
| 1206 |
+
"retain_loss": 0.02438696101307869,
|
| 1207 |
+
"step": 380
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.5024727992087041,
|
| 1211 |
+
"forget_loss": 2.9677858037757687e-07,
|
| 1212 |
+
"retain_loss": 0.023668058216571808,
|
| 1213 |
+
"step": 380
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.5024727992087041,
|
| 1217 |
+
"forget_loss": 1.109128611176402e-08,
|
| 1218 |
+
"retain_loss": 0.04492601007223129,
|
| 1219 |
+
"step": 380
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 1.5420375865479723,
|
| 1223 |
+
"grad_norm": 0.56640625,
|
| 1224 |
+
"learning_rate": 1.1794354838709679e-05,
|
| 1225 |
+
"loss": 0.05652405023574829,
|
| 1226 |
+
"step": 390
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 1.5420375865479723,
|
| 1230 |
+
"forget_loss": 8.616879654255172e-07,
|
| 1231 |
+
"retain_loss": 0.0335644893348217,
|
| 1232 |
+
"step": 390
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.5420375865479723,
|
| 1236 |
+
"forget_loss": 6.417557187887724e-07,
|
| 1237 |
+
"retain_loss": 0.03396674245595932,
|
| 1238 |
+
"step": 390
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.5420375865479723,
|
| 1242 |
+
"forget_loss": 1.2950030736647022e-07,
|
| 1243 |
+
"retain_loss": 0.04779934883117676,
|
| 1244 |
+
"step": 390
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 1.5420375865479723,
|
| 1248 |
+
"forget_loss": 3.2295685059580137e-07,
|
| 1249 |
+
"retain_loss": 0.022925786674022675,
|
| 1250 |
+
"step": 390
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.5816023738872405,
|
| 1254 |
+
"grad_norm": 0.92578125,
|
| 1255 |
+
"learning_rate": 1.0786290322580646e-05,
|
| 1256 |
+
"loss": 0.0499935507774353,
|
| 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:f4daa46b81e960187a13cf9715d61600f7d344da408f25fda410bfb3b965becf
|
| 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 sha256:0a91bd65af2bfe705722480faf3fd4d68a88a346aa1679533fb34857076817e0
|
| 3 |
+
size 14596063960
|
checkpoint-506/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ca55d7fa0cedbce24360a0177cfc8f79a8ac81d22262b70258498102681e4f2
|
| 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": 2.203125,
|
| 77 |
+
"learning_rate": 4.909274193548387e-05,
|
| 78 |
+
"loss": 2.1829532623291015,
|
| 79 |
+
"step": 20
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.0791295746785361,
|
| 83 |
+
"forget_loss": 3.1555460736854e-05,
|
| 84 |
+
"retain_loss": 2.056671380996704,
|
| 85 |
+
"step": 20
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"epoch": 0.0791295746785361,
|
| 89 |
+
"forget_loss": 1.3120857147441711e-05,
|
| 90 |
+
"retain_loss": 1.9920682907104492,
|
| 91 |
+
"step": 20
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 0.0791295746785361,
|
| 95 |
+
"forget_loss": 8.181996963685378e-05,
|
| 96 |
+
"retain_loss": 2.149359703063965,
|
| 97 |
+
"step": 20
|
| 98 |
+
},
|
| 99 |
+
{
|
| 100 |
+
"epoch": 0.0791295746785361,
|
| 101 |
+
"forget_loss": 4.155315400566906e-05,
|
| 102 |
+
"retain_loss": 1.797939419746399,
|
| 103 |
+
"step": 20
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.11869436201780416,
|
| 107 |
+
"grad_norm": 2.03125,
|
| 108 |
+
"learning_rate": 4.808467741935484e-05,
|
| 109 |
+
"loss": 1.9520586013793946,
|
| 110 |
+
"step": 30
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.11869436201780416,
|
| 114 |
+
"forget_loss": 2.097734068229329e-06,
|
| 115 |
+
"retain_loss": 1.9717810153961182,
|
| 116 |
+
"step": 30
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.11869436201780416,
|
| 120 |
+
"forget_loss": 9.0424384779908e-07,
|
| 121 |
+
"retain_loss": 2.1347732543945312,
|
| 122 |
+
"step": 30
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.11869436201780416,
|
| 126 |
+
"forget_loss": 1.5195576452242676e-05,
|
| 127 |
+
"retain_loss": 1.7591031789779663,
|
| 128 |
+
"step": 30
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.11869436201780416,
|
| 132 |
+
"forget_loss": 2.9381511922110803e-05,
|
| 133 |
+
"retain_loss": 2.324976682662964,
|
| 134 |
+
"step": 30
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.1582591493570722,
|
| 138 |
+
"grad_norm": 1.9453125,
|
| 139 |
+
"learning_rate": 4.7076612903225806e-05,
|
| 140 |
+
"loss": 1.7898395538330079,
|
| 141 |
+
"step": 40
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.1582591493570722,
|
| 145 |
+
"forget_loss": 2.347593181184493e-05,
|
| 146 |
+
"retain_loss": 1.5896490812301636,
|
| 147 |
+
"step": 40
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.1582591493570722,
|
| 151 |
+
"forget_loss": 2.7579757443163544e-05,
|
| 152 |
+
"retain_loss": 1.1212265491485596,
|
| 153 |
+
"step": 40
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.1582591493570722,
|
| 157 |
+
"forget_loss": 2.1694726456189528e-05,
|
| 158 |
+
"retain_loss": 2.051854133605957,
|
| 159 |
+
"step": 40
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.1582591493570722,
|
| 163 |
+
"forget_loss": 6.128148925199639e-06,
|
| 164 |
+
"retain_loss": 1.6619952917099,
|
| 165 |
+
"step": 40
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.19782393669634027,
|
| 169 |
+
"grad_norm": 1.96875,
|
| 170 |
+
"learning_rate": 4.606854838709678e-05,
|
| 171 |
+
"loss": 1.5459610939025878,
|
| 172 |
+
"step": 50
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 0.19782393669634027,
|
| 176 |
+
"forget_loss": 1.4324338735605124e-05,
|
| 177 |
+
"retain_loss": 1.7004584074020386,
|
| 178 |
+
"step": 50
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.19782393669634027,
|
| 182 |
+
"forget_loss": 5.814884843857726e-06,
|
| 183 |
+
"retain_loss": 1.3355984687805176,
|
| 184 |
+
"step": 50
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.19782393669634027,
|
| 188 |
+
"forget_loss": 1.4618005934607936e-06,
|
| 189 |
+
"retain_loss": 1.7750041484832764,
|
| 190 |
+
"step": 50
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.19782393669634027,
|
| 194 |
+
"forget_loss": 1.6271239928755676e-06,
|
| 195 |
+
"retain_loss": 1.4064531326293945,
|
| 196 |
+
"step": 50
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.23738872403560832,
|
| 200 |
+
"grad_norm": 2.234375,
|
| 201 |
+
"learning_rate": 4.506048387096775e-05,
|
| 202 |
+
"loss": 1.4617247581481934,
|
| 203 |
+
"step": 60
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.23738872403560832,
|
| 207 |
+
"forget_loss": 9.254661563318223e-06,
|
| 208 |
+
"retain_loss": 1.8761130571365356,
|
| 209 |
+
"step": 60
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.23738872403560832,
|
| 213 |
+
"forget_loss": 9.365790901938453e-06,
|
| 214 |
+
"retain_loss": 1.1389141082763672,
|
| 215 |
+
"step": 60
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 0.23738872403560832,
|
| 219 |
+
"forget_loss": 6.40576909063384e-05,
|
| 220 |
+
"retain_loss": 1.0727425813674927,
|
| 221 |
+
"step": 60
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 0.23738872403560832,
|
| 225 |
+
"forget_loss": 3.140630724374205e-06,
|
| 226 |
+
"retain_loss": 1.2311009168624878,
|
| 227 |
+
"step": 60
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.27695351137487634,
|
| 231 |
+
"grad_norm": 2.125,
|
| 232 |
+
"learning_rate": 4.4052419354838714e-05,
|
| 233 |
+
"loss": 1.344314193725586,
|
| 234 |
+
"step": 70
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.27695351137487634,
|
| 238 |
+
"forget_loss": 2.0407464035088196e-05,
|
| 239 |
+
"retain_loss": 1.2631032466888428,
|
| 240 |
+
"step": 70
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.27695351137487634,
|
| 244 |
+
"forget_loss": 2.1732415916630998e-05,
|
| 245 |
+
"retain_loss": 1.4336204528808594,
|
| 246 |
+
"step": 70
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.27695351137487634,
|
| 250 |
+
"forget_loss": 1.3687983937415993e-06,
|
| 251 |
+
"retain_loss": 0.9825552105903625,
|
| 252 |
+
"step": 70
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.27695351137487634,
|
| 256 |
+
"forget_loss": 1.326372967014322e-06,
|
| 257 |
+
"retain_loss": 1.3998953104019165,
|
| 258 |
+
"step": 70
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 0.3165182987141444,
|
| 262 |
+
"grad_norm": 2.390625,
|
| 263 |
+
"learning_rate": 4.3044354838709674e-05,
|
| 264 |
+
"loss": 1.214775276184082,
|
| 265 |
+
"step": 80
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"epoch": 0.3165182987141444,
|
| 269 |
+
"forget_loss": 1.3552562450058758e-06,
|
| 270 |
+
"retain_loss": 1.0332047939300537,
|
| 271 |
+
"step": 80
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 0.3165182987141444,
|
| 275 |
+
"forget_loss": 1.2774065908160992e-05,
|
| 276 |
+
"retain_loss": 1.007059931755066,
|
| 277 |
+
"step": 80
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 0.3165182987141444,
|
| 281 |
+
"forget_loss": 1.196574157802388e-05,
|
| 282 |
+
"retain_loss": 0.8872216939926147,
|
| 283 |
+
"step": 80
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3165182987141444,
|
| 287 |
+
"forget_loss": 4.2263846466994437e-07,
|
| 288 |
+
"retain_loss": 0.8739179372787476,
|
| 289 |
+
"step": 80
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.3560830860534125,
|
| 293 |
+
"grad_norm": 2.28125,
|
| 294 |
+
"learning_rate": 4.203629032258065e-05,
|
| 295 |
+
"loss": 1.1429722785949707,
|
| 296 |
+
"step": 90
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3560830860534125,
|
| 300 |
+
"forget_loss": 2.522195063647814e-05,
|
| 301 |
+
"retain_loss": 0.8757652640342712,
|
| 302 |
+
"step": 90
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.3560830860534125,
|
| 306 |
+
"forget_loss": 2.2732887373422273e-05,
|
| 307 |
+
"retain_loss": 0.9618234634399414,
|
| 308 |
+
"step": 90
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.3560830860534125,
|
| 312 |
+
"forget_loss": 2.1186065168876667e-06,
|
| 313 |
+
"retain_loss": 0.82012540102005,
|
| 314 |
+
"step": 90
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.3560830860534125,
|
| 318 |
+
"forget_loss": 1.5917968994472176e-05,
|
| 319 |
+
"retain_loss": 1.2091050148010254,
|
| 320 |
+
"step": 90
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.39564787339268054,
|
| 324 |
+
"grad_norm": 2.8125,
|
| 325 |
+
"learning_rate": 4.1028225806451615e-05,
|
| 326 |
+
"loss": 0.9440973281860352,
|
| 327 |
+
"step": 100
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.39564787339268054,
|
| 331 |
+
"forget_loss": 5.102012892166385e-07,
|
| 332 |
+
"retain_loss": 0.9886119365692139,
|
| 333 |
+
"step": 100
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.39564787339268054,
|
| 337 |
+
"forget_loss": 2.069048832709086e-06,
|
| 338 |
+
"retain_loss": 1.037408471107483,
|
| 339 |
+
"step": 100
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.39564787339268054,
|
| 343 |
+
"forget_loss": 6.717852556903381e-06,
|
| 344 |
+
"retain_loss": 1.2528358697891235,
|
| 345 |
+
"step": 100
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.39564787339268054,
|
| 349 |
+
"forget_loss": 1.7514905266580172e-05,
|
| 350 |
+
"retain_loss": 0.5935210585594177,
|
| 351 |
+
"step": 100
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.4352126607319486,
|
| 355 |
+
"grad_norm": 2.34375,
|
| 356 |
+
"learning_rate": 4.002016129032258e-05,
|
| 357 |
+
"loss": 0.8624692916870117,
|
| 358 |
+
"step": 110
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.4352126607319486,
|
| 362 |
+
"forget_loss": 1.1634347174549475e-05,
|
| 363 |
+
"retain_loss": 0.5517681837081909,
|
| 364 |
+
"step": 110
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"epoch": 0.4352126607319486,
|
| 368 |
+
"forget_loss": 6.400139795914583e-08,
|
| 369 |
+
"retain_loss": 1.0467280149459839,
|
| 370 |
+
"step": 110
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.4352126607319486,
|
| 374 |
+
"forget_loss": 1.9029957911698148e-05,
|
| 375 |
+
"retain_loss": 1.1268657445907593,
|
| 376 |
+
"step": 110
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.4352126607319486,
|
| 380 |
+
"forget_loss": 2.5354455601700465e-07,
|
| 381 |
+
"retain_loss": 0.8402698040008545,
|
| 382 |
+
"step": 110
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.47477744807121663,
|
| 386 |
+
"grad_norm": 2.609375,
|
| 387 |
+
"learning_rate": 3.901209677419355e-05,
|
| 388 |
+
"loss": 0.7725035190582276,
|
| 389 |
+
"step": 120
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.47477744807121663,
|
| 393 |
+
"forget_loss": 3.8098887671367265e-06,
|
| 394 |
+
"retain_loss": 0.3457094430923462,
|
| 395 |
+
"step": 120
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.47477744807121663,
|
| 399 |
+
"forget_loss": 2.3242062525241636e-05,
|
| 400 |
+
"retain_loss": 0.6856692433357239,
|
| 401 |
+
"step": 120
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.47477744807121663,
|
| 405 |
+
"forget_loss": 8.018694643396884e-06,
|
| 406 |
+
"retain_loss": 1.2206052541732788,
|
| 407 |
+
"step": 120
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.47477744807121663,
|
| 411 |
+
"forget_loss": 3.351060968270758e-06,
|
| 412 |
+
"retain_loss": 0.7469509840011597,
|
| 413 |
+
"step": 120
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.5143422354104846,
|
| 417 |
+
"grad_norm": 2.640625,
|
| 418 |
+
"learning_rate": 3.800403225806452e-05,
|
| 419 |
+
"loss": 0.6184093952178955,
|
| 420 |
+
"step": 130
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 0.5143422354104846,
|
| 424 |
+
"forget_loss": 3.902082880813396e-06,
|
| 425 |
+
"retain_loss": 0.9034799933433533,
|
| 426 |
+
"step": 130
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 0.5143422354104846,
|
| 430 |
+
"forget_loss": 1.8487480701878667e-07,
|
| 431 |
+
"retain_loss": 0.944042980670929,
|
| 432 |
+
"step": 130
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 0.5143422354104846,
|
| 436 |
+
"forget_loss": 7.273596338563948e-07,
|
| 437 |
+
"retain_loss": 0.589636504650116,
|
| 438 |
+
"step": 130
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.5143422354104846,
|
| 442 |
+
"forget_loss": 6.394767115125433e-05,
|
| 443 |
+
"retain_loss": 0.8495606780052185,
|
| 444 |
+
"step": 130
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5539070227497527,
|
| 448 |
+
"grad_norm": 2.09375,
|
| 449 |
+
"learning_rate": 3.6995967741935484e-05,
|
| 450 |
+
"loss": 0.5851613521575928,
|
| 451 |
+
"step": 140
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5539070227497527,
|
| 455 |
+
"forget_loss": 1.9570716176531278e-06,
|
| 456 |
+
"retain_loss": 0.31179508566856384,
|
| 457 |
+
"step": 140
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.5539070227497527,
|
| 461 |
+
"forget_loss": 4.920673745800741e-06,
|
| 462 |
+
"retain_loss": 0.7174519300460815,
|
| 463 |
+
"step": 140
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"epoch": 0.5539070227497527,
|
| 467 |
+
"forget_loss": 9.13152689463459e-07,
|
| 468 |
+
"retain_loss": 0.44045335054397583,
|
| 469 |
+
"step": 140
|
| 470 |
+
},
|
| 471 |
+
{
|
| 472 |
+
"epoch": 0.5539070227497527,
|
| 473 |
+
"forget_loss": 7.388467793134623e-07,
|
| 474 |
+
"retain_loss": 0.35985979437828064,
|
| 475 |
+
"step": 140
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 0.5934718100890207,
|
| 479 |
+
"grad_norm": 2.0625,
|
| 480 |
+
"learning_rate": 3.598790322580645e-05,
|
| 481 |
+
"loss": 0.5792353630065918,
|
| 482 |
+
"step": 150
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.5934718100890207,
|
| 486 |
+
"forget_loss": 1.258710966567378e-07,
|
| 487 |
+
"retain_loss": 0.45937851071357727,
|
| 488 |
+
"step": 150
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.5934718100890207,
|
| 492 |
+
"forget_loss": 7.370726962108165e-07,
|
| 493 |
+
"retain_loss": 0.27468791604042053,
|
| 494 |
+
"step": 150
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.5934718100890207,
|
| 498 |
+
"forget_loss": 8.536089808330871e-06,
|
| 499 |
+
"retain_loss": 0.8069593906402588,
|
| 500 |
+
"step": 150
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.5934718100890207,
|
| 504 |
+
"forget_loss": 8.370562341042387e-07,
|
| 505 |
+
"retain_loss": 0.15817895531654358,
|
| 506 |
+
"step": 150
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.6330365974282888,
|
| 510 |
+
"grad_norm": 1.703125,
|
| 511 |
+
"learning_rate": 3.497983870967742e-05,
|
| 512 |
+
"loss": 0.40374002456665037,
|
| 513 |
+
"step": 160
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.6330365974282888,
|
| 517 |
+
"forget_loss": 4.5395900087896734e-06,
|
| 518 |
+
"retain_loss": 0.6503518223762512,
|
| 519 |
+
"step": 160
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.6330365974282888,
|
| 523 |
+
"forget_loss": 1.2475591120164609e-06,
|
| 524 |
+
"retain_loss": 0.29691439867019653,
|
| 525 |
+
"step": 160
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.6330365974282888,
|
| 529 |
+
"forget_loss": 7.69290522839583e-07,
|
| 530 |
+
"retain_loss": 0.3579648435115814,
|
| 531 |
+
"step": 160
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.6330365974282888,
|
| 535 |
+
"forget_loss": 3.610326075431658e-06,
|
| 536 |
+
"retain_loss": 0.3425873816013336,
|
| 537 |
+
"step": 160
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.6726013847675568,
|
| 541 |
+
"grad_norm": 2.171875,
|
| 542 |
+
"learning_rate": 3.397177419354839e-05,
|
| 543 |
+
"loss": 0.3935901641845703,
|
| 544 |
+
"step": 170
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.6726013847675568,
|
| 548 |
+
"forget_loss": 7.11527832208958e-07,
|
| 549 |
+
"retain_loss": 0.45746102929115295,
|
| 550 |
+
"step": 170
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.6726013847675568,
|
| 554 |
+
"forget_loss": 3.808730753007694e-07,
|
| 555 |
+
"retain_loss": 0.4325888454914093,
|
| 556 |
+
"step": 170
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6726013847675568,
|
| 560 |
+
"forget_loss": 1.3094180530970334e-06,
|
| 561 |
+
"retain_loss": 0.1893959939479828,
|
| 562 |
+
"step": 170
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.6726013847675568,
|
| 566 |
+
"forget_loss": 5.8092759900318924e-06,
|
| 567 |
+
"retain_loss": 1.1242655515670776,
|
| 568 |
+
"step": 170
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.712166172106825,
|
| 572 |
+
"grad_norm": 2.28125,
|
| 573 |
+
"learning_rate": 3.296370967741936e-05,
|
| 574 |
+
"loss": 0.37663323879241944,
|
| 575 |
+
"step": 180
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.712166172106825,
|
| 579 |
+
"forget_loss": 1.8580192318040645e-06,
|
| 580 |
+
"retain_loss": 0.24432934820652008,
|
| 581 |
+
"step": 180
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.712166172106825,
|
| 585 |
+
"forget_loss": 3.5925964425587154e-07,
|
| 586 |
+
"retain_loss": 0.2534143328666687,
|
| 587 |
+
"step": 180
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.712166172106825,
|
| 591 |
+
"forget_loss": 5.5626283028686885e-06,
|
| 592 |
+
"retain_loss": 0.23151986300945282,
|
| 593 |
+
"step": 180
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.712166172106825,
|
| 597 |
+
"forget_loss": 5.4275651564239524e-06,
|
| 598 |
+
"retain_loss": 0.2856011688709259,
|
| 599 |
+
"step": 180
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.751730959446093,
|
| 603 |
+
"grad_norm": 2.265625,
|
| 604 |
+
"learning_rate": 3.1955645161290326e-05,
|
| 605 |
+
"loss": 0.3224222183227539,
|
| 606 |
+
"step": 190
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.751730959446093,
|
| 610 |
+
"forget_loss": 2.0351612874947023e-06,
|
| 611 |
+
"retain_loss": 0.30106958746910095,
|
| 612 |
+
"step": 190
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.751730959446093,
|
| 616 |
+
"forget_loss": 1.137744402512908e-05,
|
| 617 |
+
"retain_loss": 0.35559219121932983,
|
| 618 |
+
"step": 190
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.751730959446093,
|
| 622 |
+
"forget_loss": 4.769389647663047e-07,
|
| 623 |
+
"retain_loss": 0.12539999186992645,
|
| 624 |
+
"step": 190
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.751730959446093,
|
| 628 |
+
"forget_loss": 1.536158151793643e-07,
|
| 629 |
+
"retain_loss": 0.5091521143913269,
|
| 630 |
+
"step": 190
|
| 631 |
+
},
|
| 632 |
+
{
|
| 633 |
+
"epoch": 0.7912957467853611,
|
| 634 |
+
"grad_norm": 1.984375,
|
| 635 |
+
"learning_rate": 3.0947580645161286e-05,
|
| 636 |
+
"loss": 0.32691752910614014,
|
| 637 |
+
"step": 200
|
| 638 |
+
},
|
| 639 |
+
{
|
| 640 |
+
"epoch": 0.7912957467853611,
|
| 641 |
+
"forget_loss": 4.226240889693145e-06,
|
| 642 |
+
"retain_loss": 0.13701662421226501,
|
| 643 |
+
"step": 200
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"epoch": 0.7912957467853611,
|
| 647 |
+
"forget_loss": 1.258511565538356e-05,
|
| 648 |
+
"retain_loss": 0.10310296714305878,
|
| 649 |
+
"step": 200
|
| 650 |
+
},
|
| 651 |
+
{
|
| 652 |
+
"epoch": 0.7912957467853611,
|
| 653 |
+
"forget_loss": 1.963040858754539e-06,
|
| 654 |
+
"retain_loss": 0.08762754499912262,
|
| 655 |
+
"step": 200
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.7912957467853611,
|
| 659 |
+
"forget_loss": 1.235385980180581e-06,
|
| 660 |
+
"retain_loss": 0.2134196013212204,
|
| 661 |
+
"step": 200
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.8308605341246291,
|
| 665 |
+
"grad_norm": 1.765625,
|
| 666 |
+
"learning_rate": 2.9939516129032256e-05,
|
| 667 |
+
"loss": 0.23421640396118165,
|
| 668 |
+
"step": 210
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.8308605341246291,
|
| 672 |
+
"forget_loss": 3.501550236251205e-05,
|
| 673 |
+
"retain_loss": 0.17837883532047272,
|
| 674 |
+
"step": 210
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 0.8308605341246291,
|
| 678 |
+
"forget_loss": 1.5083353446243564e-06,
|
| 679 |
+
"retain_loss": 0.1773965209722519,
|
| 680 |
+
"step": 210
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.8308605341246291,
|
| 684 |
+
"forget_loss": 1.7007857877615606e-06,
|
| 685 |
+
"retain_loss": 0.11213231086730957,
|
| 686 |
+
"step": 210
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.8308605341246291,
|
| 690 |
+
"forget_loss": 5.62718128094275e-07,
|
| 691 |
+
"retain_loss": 0.10278806835412979,
|
| 692 |
+
"step": 210
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.8704253214638972,
|
| 696 |
+
"grad_norm": 2.53125,
|
| 697 |
+
"learning_rate": 2.8931451612903227e-05,
|
| 698 |
+
"loss": 0.20826613903045654,
|
| 699 |
+
"step": 220
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.8704253214638972,
|
| 703 |
+
"forget_loss": 5.792419415229233e-07,
|
| 704 |
+
"retain_loss": 0.06651624292135239,
|
| 705 |
+
"step": 220
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.8704253214638972,
|
| 709 |
+
"forget_loss": 1.4317017758003203e-06,
|
| 710 |
+
"retain_loss": 0.3651600480079651,
|
| 711 |
+
"step": 220
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.8704253214638972,
|
| 715 |
+
"forget_loss": 2.790197299873398e-07,
|
| 716 |
+
"retain_loss": 0.059690482914447784,
|
| 717 |
+
"step": 220
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.8704253214638972,
|
| 721 |
+
"forget_loss": 2.358171514060814e-06,
|
| 722 |
+
"retain_loss": 0.07482323050498962,
|
| 723 |
+
"step": 220
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.9099901088031652,
|
| 727 |
+
"grad_norm": 2.015625,
|
| 728 |
+
"learning_rate": 2.7923387096774194e-05,
|
| 729 |
+
"loss": 0.19134424924850463,
|
| 730 |
+
"step": 230
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.9099901088031652,
|
| 734 |
+
"forget_loss": 1.6788119410193758e-06,
|
| 735 |
+
"retain_loss": 0.11503209918737411,
|
| 736 |
+
"step": 230
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.9099901088031652,
|
| 740 |
+
"forget_loss": 1.3623559880215907e-06,
|
| 741 |
+
"retain_loss": 0.09323878586292267,
|
| 742 |
+
"step": 230
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.9099901088031652,
|
| 746 |
+
"forget_loss": 9.115094599110307e-07,
|
| 747 |
+
"retain_loss": 0.2667946219444275,
|
| 748 |
+
"step": 230
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 0.9099901088031652,
|
| 752 |
+
"forget_loss": 1.176637056232721e-06,
|
| 753 |
+
"retain_loss": 0.09373427927494049,
|
| 754 |
+
"step": 230
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.9495548961424333,
|
| 758 |
+
"grad_norm": 1.890625,
|
| 759 |
+
"learning_rate": 2.6915322580645164e-05,
|
| 760 |
+
"loss": 0.19541234970092775,
|
| 761 |
+
"step": 240
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.9495548961424333,
|
| 765 |
+
"forget_loss": 4.323494522395777e-06,
|
| 766 |
+
"retain_loss": 0.060076676309108734,
|
| 767 |
+
"step": 240
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.9495548961424333,
|
| 771 |
+
"forget_loss": 3.29818294630968e-06,
|
| 772 |
+
"retain_loss": 0.1765175312757492,
|
| 773 |
+
"step": 240
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.9495548961424333,
|
| 777 |
+
"forget_loss": 1.1875378902459488e-07,
|
| 778 |
+
"retain_loss": 0.04277701675891876,
|
| 779 |
+
"step": 240
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.9495548961424333,
|
| 783 |
+
"forget_loss": 2.5362205633427948e-06,
|
| 784 |
+
"retain_loss": 0.05752837285399437,
|
| 785 |
+
"step": 240
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.9891196834817013,
|
| 789 |
+
"grad_norm": 1.4453125,
|
| 790 |
+
"learning_rate": 2.590725806451613e-05,
|
| 791 |
+
"loss": 0.17172594070434571,
|
| 792 |
+
"step": 250
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 0.9891196834817013,
|
| 796 |
+
"forget_loss": 2.3277580112335272e-06,
|
| 797 |
+
"retain_loss": 0.08483278006315231,
|
| 798 |
+
"step": 250
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 0.9891196834817013,
|
| 802 |
+
"forget_loss": 5.033873094362207e-06,
|
| 803 |
+
"retain_loss": 0.24280749261379242,
|
| 804 |
+
"step": 250
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.9891196834817013,
|
| 808 |
+
"forget_loss": 4.555405212158803e-06,
|
| 809 |
+
"retain_loss": 0.4092475473880768,
|
| 810 |
+
"step": 250
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.9891196834817013,
|
| 814 |
+
"forget_loss": 4.822932737624797e-07,
|
| 815 |
+
"retain_loss": 0.062368009239435196,
|
| 816 |
+
"step": 250
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 1.0276953511374876,
|
| 820 |
+
"grad_norm": 2.078125,
|
| 821 |
+
"learning_rate": 2.48991935483871e-05,
|
| 822 |
+
"loss": 0.14231110811233522,
|
| 823 |
+
"step": 260
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 1.0276953511374876,
|
| 827 |
+
"forget_loss": 2.3665279513807036e-06,
|
| 828 |
+
"retain_loss": 0.04678928107023239,
|
| 829 |
+
"step": 260
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.0276953511374876,
|
| 833 |
+
"forget_loss": 1.7857011016531033e-06,
|
| 834 |
+
"retain_loss": 0.15241962671279907,
|
| 835 |
+
"step": 260
|
| 836 |
+
},
|
| 837 |
+
{
|
| 838 |
+
"epoch": 1.0276953511374876,
|
| 839 |
+
"forget_loss": 3.6310279938334133e-07,
|
| 840 |
+
"retain_loss": 0.20368625223636627,
|
| 841 |
+
"step": 260
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 1.0276953511374876,
|
| 845 |
+
"forget_loss": 5.83898440709163e-07,
|
| 846 |
+
"retain_loss": 0.06002001464366913,
|
| 847 |
+
"step": 260
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 1.0672601384767557,
|
| 851 |
+
"grad_norm": 1.4921875,
|
| 852 |
+
"learning_rate": 2.3891129032258066e-05,
|
| 853 |
+
"loss": 0.12347257137298584,
|
| 854 |
+
"step": 270
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 1.0672601384767557,
|
| 858 |
+
"forget_loss": 6.095945082051912e-07,
|
| 859 |
+
"retain_loss": 0.2563520669937134,
|
| 860 |
+
"step": 270
|
| 861 |
+
},
|
| 862 |
+
{
|
| 863 |
+
"epoch": 1.0672601384767557,
|
| 864 |
+
"forget_loss": 7.611353112224606e-07,
|
| 865 |
+
"retain_loss": 0.23337779939174652,
|
| 866 |
+
"step": 270
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 1.0672601384767557,
|
| 870 |
+
"forget_loss": 1.0488522548257606e-06,
|
| 871 |
+
"retain_loss": 0.0406014546751976,
|
| 872 |
+
"step": 270
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 1.0672601384767557,
|
| 876 |
+
"forget_loss": 1.4446818568103481e-06,
|
| 877 |
+
"retain_loss": 0.03464161604642868,
|
| 878 |
+
"step": 270
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.1068249258160237,
|
| 882 |
+
"grad_norm": 0.97265625,
|
| 883 |
+
"learning_rate": 2.2883064516129033e-05,
|
| 884 |
+
"loss": 0.12490516901016235,
|
| 885 |
+
"step": 280
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.1068249258160237,
|
| 889 |
+
"forget_loss": 2.0972819925191288e-07,
|
| 890 |
+
"retain_loss": 0.038518667221069336,
|
| 891 |
+
"step": 280
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 1.1068249258160237,
|
| 895 |
+
"forget_loss": 2.309284582224791e-06,
|
| 896 |
+
"retain_loss": 0.05753574147820473,
|
| 897 |
+
"step": 280
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 1.1068249258160237,
|
| 901 |
+
"forget_loss": 4.084875797616405e-07,
|
| 902 |
+
"retain_loss": 0.10644430667161942,
|
| 903 |
+
"step": 280
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 1.1068249258160237,
|
| 907 |
+
"forget_loss": 1.1346749317908689e-08,
|
| 908 |
+
"retain_loss": 0.11500366032123566,
|
| 909 |
+
"step": 280
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 1.1463897131552918,
|
| 913 |
+
"grad_norm": 1.109375,
|
| 914 |
+
"learning_rate": 2.1875e-05,
|
| 915 |
+
"loss": 0.09100213646888733,
|
| 916 |
+
"step": 290
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 1.1463897131552918,
|
| 920 |
+
"forget_loss": 4.1612356653786264e-06,
|
| 921 |
+
"retain_loss": 0.07052873820066452,
|
| 922 |
+
"step": 290
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.1463897131552918,
|
| 926 |
+
"forget_loss": 9.997415872931015e-08,
|
| 927 |
+
"retain_loss": 0.04744183272123337,
|
| 928 |
+
"step": 290
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 1.1463897131552918,
|
| 932 |
+
"forget_loss": 1.2092109500372317e-06,
|
| 933 |
+
"retain_loss": 0.07089261710643768,
|
| 934 |
+
"step": 290
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.1463897131552918,
|
| 938 |
+
"forget_loss": 2.131706423824653e-06,
|
| 939 |
+
"retain_loss": 0.2522507607936859,
|
| 940 |
+
"step": 290
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 1.1859545004945597,
|
| 944 |
+
"grad_norm": 1.2265625,
|
| 945 |
+
"learning_rate": 2.086693548387097e-05,
|
| 946 |
+
"loss": 0.09003463983535767,
|
| 947 |
+
"step": 300
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 1.1859545004945597,
|
| 951 |
+
"forget_loss": 1.1781303328461945e-06,
|
| 952 |
+
"retain_loss": 0.02843177132308483,
|
| 953 |
+
"step": 300
|
| 954 |
+
},
|
| 955 |
+
{
|
| 956 |
+
"epoch": 1.1859545004945597,
|
| 957 |
+
"forget_loss": 2.6735065716820827e-07,
|
| 958 |
+
"retain_loss": 0.04060671105980873,
|
| 959 |
+
"step": 300
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 1.1859545004945597,
|
| 963 |
+
"forget_loss": 3.643542186182458e-06,
|
| 964 |
+
"retain_loss": 0.0628509372472763,
|
| 965 |
+
"step": 300
|
| 966 |
+
},
|
| 967 |
+
{
|
| 968 |
+
"epoch": 1.1859545004945597,
|
| 969 |
+
"forget_loss": 4.7639906597396475e-07,
|
| 970 |
+
"retain_loss": 0.03408809378743172,
|
| 971 |
+
"step": 300
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 1.225519287833828,
|
| 975 |
+
"grad_norm": 0.74609375,
|
| 976 |
+
"learning_rate": 1.9858870967741934e-05,
|
| 977 |
+
"loss": 0.07631087303161621,
|
| 978 |
+
"step": 310
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 1.225519287833828,
|
| 982 |
+
"forget_loss": 1.8324541883885104e-07,
|
| 983 |
+
"retain_loss": 0.1489202380180359,
|
| 984 |
+
"step": 310
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 1.225519287833828,
|
| 988 |
+
"forget_loss": 1.505328555140295e-06,
|
| 989 |
+
"retain_loss": 0.09023259580135345,
|
| 990 |
+
"step": 310
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.225519287833828,
|
| 994 |
+
"forget_loss": 1.2370117019600002e-06,
|
| 995 |
+
"retain_loss": 0.11567945778369904,
|
| 996 |
+
"step": 310
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"epoch": 1.225519287833828,
|
| 1000 |
+
"forget_loss": 6.62587012811855e-07,
|
| 1001 |
+
"retain_loss": 0.07907626777887344,
|
| 1002 |
+
"step": 310
|
| 1003 |
+
},
|
| 1004 |
+
{
|
| 1005 |
+
"epoch": 1.265084075173096,
|
| 1006 |
+
"grad_norm": 1.5546875,
|
| 1007 |
+
"learning_rate": 1.8850806451612904e-05,
|
| 1008 |
+
"loss": 0.09484220743179321,
|
| 1009 |
+
"step": 320
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 1.265084075173096,
|
| 1013 |
+
"forget_loss": 6.137950094853295e-06,
|
| 1014 |
+
"retain_loss": 0.0641757920384407,
|
| 1015 |
+
"step": 320
|
| 1016 |
+
},
|
| 1017 |
+
{
|
| 1018 |
+
"epoch": 1.265084075173096,
|
| 1019 |
+
"forget_loss": 2.837170541170053e-06,
|
| 1020 |
+
"retain_loss": 0.0350993350148201,
|
| 1021 |
+
"step": 320
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"epoch": 1.265084075173096,
|
| 1025 |
+
"forget_loss": 1.2725810449865094e-07,
|
| 1026 |
+
"retain_loss": 0.04542815685272217,
|
| 1027 |
+
"step": 320
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 1.265084075173096,
|
| 1031 |
+
"forget_loss": 4.864556899519812e-07,
|
| 1032 |
+
"retain_loss": 0.05786221846938133,
|
| 1033 |
+
"step": 320
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 1.304648862512364,
|
| 1037 |
+
"grad_norm": 1.328125,
|
| 1038 |
+
"learning_rate": 1.784274193548387e-05,
|
| 1039 |
+
"loss": 0.06601499915122985,
|
| 1040 |
+
"step": 330
|
| 1041 |
+
},
|
| 1042 |
+
{
|
| 1043 |
+
"epoch": 1.304648862512364,
|
| 1044 |
+
"forget_loss": 5.855958420397656e-07,
|
| 1045 |
+
"retain_loss": 0.04558321461081505,
|
| 1046 |
+
"step": 330
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.304648862512364,
|
| 1050 |
+
"forget_loss": 1.0734013358160155e-06,
|
| 1051 |
+
"retain_loss": 0.061824798583984375,
|
| 1052 |
+
"step": 330
|
| 1053 |
+
},
|
| 1054 |
+
{
|
| 1055 |
+
"epoch": 1.304648862512364,
|
| 1056 |
+
"forget_loss": 3.7222815763016115e-07,
|
| 1057 |
+
"retain_loss": 0.04270363599061966,
|
| 1058 |
+
"step": 330
|
| 1059 |
+
},
|
| 1060 |
+
{
|
| 1061 |
+
"epoch": 1.304648862512364,
|
| 1062 |
+
"forget_loss": 6.617690360144479e-07,
|
| 1063 |
+
"retain_loss": 0.16833367943763733,
|
| 1064 |
+
"step": 330
|
| 1065 |
+
},
|
| 1066 |
+
{
|
| 1067 |
+
"epoch": 1.344213649851632,
|
| 1068 |
+
"grad_norm": 0.49609375,
|
| 1069 |
+
"learning_rate": 1.683467741935484e-05,
|
| 1070 |
+
"loss": 0.06903731822967529,
|
| 1071 |
+
"step": 340
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 1.344213649851632,
|
| 1075 |
+
"forget_loss": 1.1879722023877548e-06,
|
| 1076 |
+
"retain_loss": 0.02958919107913971,
|
| 1077 |
+
"step": 340
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 1.344213649851632,
|
| 1081 |
+
"forget_loss": 4.095278995919216e-07,
|
| 1082 |
+
"retain_loss": 0.04107590764760971,
|
| 1083 |
+
"step": 340
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 1.344213649851632,
|
| 1087 |
+
"forget_loss": 7.392562224595167e-07,
|
| 1088 |
+
"retain_loss": 0.404009610414505,
|
| 1089 |
+
"step": 340
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 1.344213649851632,
|
| 1093 |
+
"forget_loss": 2.7393613777348946e-07,
|
| 1094 |
+
"retain_loss": 0.02813897468149662,
|
| 1095 |
+
"step": 340
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.3837784371909,
|
| 1099 |
+
"grad_norm": 1.4140625,
|
| 1100 |
+
"learning_rate": 1.5826612903225806e-05,
|
| 1101 |
+
"loss": 0.069232177734375,
|
| 1102 |
+
"step": 350
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.3837784371909,
|
| 1106 |
+
"forget_loss": 6.865487307550211e-07,
|
| 1107 |
+
"retain_loss": 0.02693028561770916,
|
| 1108 |
+
"step": 350
|
| 1109 |
+
},
|
| 1110 |
+
{
|
| 1111 |
+
"epoch": 1.3837784371909,
|
| 1112 |
+
"forget_loss": 4.187642161923577e-07,
|
| 1113 |
+
"retain_loss": 0.04608120024204254,
|
| 1114 |
+
"step": 350
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.3837784371909,
|
| 1118 |
+
"forget_loss": 8.139955554042899e-08,
|
| 1119 |
+
"retain_loss": 0.06439628452062607,
|
| 1120 |
+
"step": 350
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 1.3837784371909,
|
| 1124 |
+
"forget_loss": 8.785929139776272e-08,
|
| 1125 |
+
"retain_loss": 0.17509031295776367,
|
| 1126 |
+
"step": 350
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.4233432245301683,
|
| 1130 |
+
"grad_norm": 0.7265625,
|
| 1131 |
+
"learning_rate": 1.4818548387096776e-05,
|
| 1132 |
+
"loss": 0.07515097260475159,
|
| 1133 |
+
"step": 360
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 1.4233432245301683,
|
| 1137 |
+
"forget_loss": 1.5587008874717867e-06,
|
| 1138 |
+
"retain_loss": 0.027441687881946564,
|
| 1139 |
+
"step": 360
|
| 1140 |
+
},
|
| 1141 |
+
{
|
| 1142 |
+
"epoch": 1.4233432245301683,
|
| 1143 |
+
"forget_loss": 2.0895599561754352e-07,
|
| 1144 |
+
"retain_loss": 0.022471986711025238,
|
| 1145 |
+
"step": 360
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 1.4233432245301683,
|
| 1149 |
+
"forget_loss": 6.960410701140063e-07,
|
| 1150 |
+
"retain_loss": 0.0480155348777771,
|
| 1151 |
+
"step": 360
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.4233432245301683,
|
| 1155 |
+
"forget_loss": 1.2851671726821223e-07,
|
| 1156 |
+
"retain_loss": 0.02052563615143299,
|
| 1157 |
+
"step": 360
|
| 1158 |
+
},
|
| 1159 |
+
{
|
| 1160 |
+
"epoch": 1.4629080118694362,
|
| 1161 |
+
"grad_norm": 0.75390625,
|
| 1162 |
+
"learning_rate": 1.3810483870967741e-05,
|
| 1163 |
+
"loss": 0.055222952365875246,
|
| 1164 |
+
"step": 370
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"epoch": 1.4629080118694362,
|
| 1168 |
+
"forget_loss": 9.040416557581921e-07,
|
| 1169 |
+
"retain_loss": 0.03805703669786453,
|
| 1170 |
+
"step": 370
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 1.4629080118694362,
|
| 1174 |
+
"forget_loss": 2.56950727361982e-07,
|
| 1175 |
+
"retain_loss": 0.04338216036558151,
|
| 1176 |
+
"step": 370
|
| 1177 |
+
},
|
| 1178 |
+
{
|
| 1179 |
+
"epoch": 1.4629080118694362,
|
| 1180 |
+
"forget_loss": 1.555378958073561e-06,
|
| 1181 |
+
"retain_loss": 0.027456099167466164,
|
| 1182 |
+
"step": 370
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 1.4629080118694362,
|
| 1186 |
+
"forget_loss": 1.5528239600826055e-06,
|
| 1187 |
+
"retain_loss": 0.11473647505044937,
|
| 1188 |
+
"step": 370
|
| 1189 |
+
},
|
| 1190 |
+
{
|
| 1191 |
+
"epoch": 1.5024727992087041,
|
| 1192 |
+
"grad_norm": 0.82421875,
|
| 1193 |
+
"learning_rate": 1.280241935483871e-05,
|
| 1194 |
+
"loss": 0.05010308623313904,
|
| 1195 |
+
"step": 380
|
| 1196 |
+
},
|
| 1197 |
+
{
|
| 1198 |
+
"epoch": 1.5024727992087041,
|
| 1199 |
+
"forget_loss": 6.783013759559253e-07,
|
| 1200 |
+
"retain_loss": 0.044970110058784485,
|
| 1201 |
+
"step": 380
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 1.5024727992087041,
|
| 1205 |
+
"forget_loss": 5.374618922360241e-06,
|
| 1206 |
+
"retain_loss": 0.02438696101307869,
|
| 1207 |
+
"step": 380
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.5024727992087041,
|
| 1211 |
+
"forget_loss": 2.9677858037757687e-07,
|
| 1212 |
+
"retain_loss": 0.023668058216571808,
|
| 1213 |
+
"step": 380
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 1.5024727992087041,
|
| 1217 |
+
"forget_loss": 1.109128611176402e-08,
|
| 1218 |
+
"retain_loss": 0.04492601007223129,
|
| 1219 |
+
"step": 380
|
| 1220 |
+
},
|
| 1221 |
+
{
|
| 1222 |
+
"epoch": 1.5420375865479723,
|
| 1223 |
+
"grad_norm": 0.56640625,
|
| 1224 |
+
"learning_rate": 1.1794354838709679e-05,
|
| 1225 |
+
"loss": 0.05652405023574829,
|
| 1226 |
+
"step": 390
|
| 1227 |
+
},
|
| 1228 |
+
{
|
| 1229 |
+
"epoch": 1.5420375865479723,
|
| 1230 |
+
"forget_loss": 8.616879654255172e-07,
|
| 1231 |
+
"retain_loss": 0.0335644893348217,
|
| 1232 |
+
"step": 390
|
| 1233 |
+
},
|
| 1234 |
+
{
|
| 1235 |
+
"epoch": 1.5420375865479723,
|
| 1236 |
+
"forget_loss": 6.417557187887724e-07,
|
| 1237 |
+
"retain_loss": 0.03396674245595932,
|
| 1238 |
+
"step": 390
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 1.5420375865479723,
|
| 1242 |
+
"forget_loss": 1.2950030736647022e-07,
|
| 1243 |
+
"retain_loss": 0.04779934883117676,
|
| 1244 |
+
"step": 390
|
| 1245 |
+
},
|
| 1246 |
+
{
|
| 1247 |
+
"epoch": 1.5420375865479723,
|
| 1248 |
+
"forget_loss": 3.2295685059580137e-07,
|
| 1249 |
+
"retain_loss": 0.022925786674022675,
|
| 1250 |
+
"step": 390
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 1.5816023738872405,
|
| 1254 |
+
"grad_norm": 0.92578125,
|
| 1255 |
+
"learning_rate": 1.0786290322580646e-05,
|
| 1256 |
+
"loss": 0.0499935507774353,
|
| 1257 |
+
"step": 400
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 1.5816023738872405,
|
| 1261 |
+
"forget_loss": 1.4149179605738027e-07,
|
| 1262 |
+
"retain_loss": 0.09424184262752533,
|
| 1263 |
+
"step": 400
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.5816023738872405,
|
| 1267 |
+
"forget_loss": 2.579657198964469e-08,
|
| 1268 |
+
"retain_loss": 0.022774428129196167,
|
| 1269 |
+
"step": 400
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 1.5816023738872405,
|
| 1273 |
+
"forget_loss": 9.055776899913326e-06,
|
| 1274 |
+
"retain_loss": 0.03912818431854248,
|
| 1275 |
+
"step": 400
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 1.5816023738872405,
|
| 1279 |
+
"forget_loss": 5.612932341136911e-07,
|
| 1280 |
+
"retain_loss": 0.01830551028251648,
|
| 1281 |
+
"step": 400
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 1.6211671612265084,
|
| 1285 |
+
"grad_norm": 0.41796875,
|
| 1286 |
+
"learning_rate": 9.778225806451613e-06,
|
| 1287 |
+
"loss": 0.05245124697685242,
|
| 1288 |
+
"step": 410
|
| 1289 |
+
},
|
| 1290 |
+
{
|
| 1291 |
+
"epoch": 1.6211671612265084,
|
| 1292 |
+
"forget_loss": 1.0918882935584406e-06,
|
| 1293 |
+
"retain_loss": 0.03899680823087692,
|
| 1294 |
+
"step": 410
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 1.6211671612265084,
|
| 1298 |
+
"forget_loss": 4.972907845512964e-07,
|
| 1299 |
+
"retain_loss": 0.036254264414310455,
|
| 1300 |
+
"step": 410
|
| 1301 |
+
},
|
| 1302 |
+
{
|
| 1303 |
+
"epoch": 1.6211671612265084,
|
| 1304 |
+
"forget_loss": 2.1247342374408618e-06,
|
| 1305 |
+
"retain_loss": 0.03961007297039032,
|
| 1306 |
+
"step": 410
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.6211671612265084,
|
| 1310 |
+
"forget_loss": 4.669371378440701e-08,
|
| 1311 |
+
"retain_loss": 0.14862912893295288,
|
| 1312 |
+
"step": 410
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.6607319485657763,
|
| 1316 |
+
"grad_norm": 0.51953125,
|
| 1317 |
+
"learning_rate": 8.770161290322582e-06,
|
| 1318 |
+
"loss": 0.04853116869926453,
|
| 1319 |
+
"step": 420
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.6607319485657763,
|
| 1323 |
+
"forget_loss": 2.079215306594051e-07,
|
| 1324 |
+
"retain_loss": 0.0473225861787796,
|
| 1325 |
+
"step": 420
|
| 1326 |
+
},
|
| 1327 |
+
{
|
| 1328 |
+
"epoch": 1.6607319485657763,
|
| 1329 |
+
"forget_loss": 1.4471823305939324e-05,
|
| 1330 |
+
"retain_loss": 0.04140442609786987,
|
| 1331 |
+
"step": 420
|
| 1332 |
+
},
|
| 1333 |
+
{
|
| 1334 |
+
"epoch": 1.6607319485657763,
|
| 1335 |
+
"forget_loss": 4.412034684264654e-07,
|
| 1336 |
+
"retain_loss": 0.022193601354956627,
|
| 1337 |
+
"step": 420
|
| 1338 |
+
},
|
| 1339 |
+
{
|
| 1340 |
+
"epoch": 1.6607319485657763,
|
| 1341 |
+
"forget_loss": 2.4310432422680606e-07,
|
| 1342 |
+
"retain_loss": 0.02164550870656967,
|
| 1343 |
+
"step": 420
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 1.7002967359050445,
|
| 1347 |
+
"grad_norm": 0.5390625,
|
| 1348 |
+
"learning_rate": 7.762096774193549e-06,
|
| 1349 |
+
"loss": 0.04437119960784912,
|
| 1350 |
+
"step": 430
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 1.7002967359050445,
|
| 1354 |
+
"forget_loss": 7.294415809155907e-07,
|
| 1355 |
+
"retain_loss": 0.04582787677645683,
|
| 1356 |
+
"step": 430
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 1.7002967359050445,
|
| 1360 |
+
"forget_loss": 1.6502593780387542e-07,
|
| 1361 |
+
"retain_loss": 0.02343440242111683,
|
| 1362 |
+
"step": 430
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 1.7002967359050445,
|
| 1366 |
+
"forget_loss": 2.4713807533771615e-07,
|
| 1367 |
+
"retain_loss": 0.027170918881893158,
|
| 1368 |
+
"step": 430
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.7002967359050445,
|
| 1372 |
+
"forget_loss": 1.208927358220535e-07,
|
| 1373 |
+
"retain_loss": 0.05825173109769821,
|
| 1374 |
+
"step": 430
|
| 1375 |
+
},
|
| 1376 |
+
{
|
| 1377 |
+
"epoch": 1.7398615232443126,
|
| 1378 |
+
"grad_norm": 1.0078125,
|
| 1379 |
+
"learning_rate": 6.754032258064516e-06,
|
| 1380 |
+
"loss": 0.04427404403686523,
|
| 1381 |
+
"step": 440
|
| 1382 |
+
},
|
| 1383 |
+
{
|
| 1384 |
+
"epoch": 1.7398615232443126,
|
| 1385 |
+
"forget_loss": 2.307926251887693e-06,
|
| 1386 |
+
"retain_loss": 0.047143761068582535,
|
| 1387 |
+
"step": 440
|
| 1388 |
+
},
|
| 1389 |
+
{
|
| 1390 |
+
"epoch": 1.7398615232443126,
|
| 1391 |
+
"forget_loss": 5.785019538961933e-07,
|
| 1392 |
+
"retain_loss": 0.026861390098929405,
|
| 1393 |
+
"step": 440
|
| 1394 |
+
},
|
| 1395 |
+
{
|
| 1396 |
+
"epoch": 1.7398615232443126,
|
| 1397 |
+
"forget_loss": 5.3523475429528844e-08,
|
| 1398 |
+
"retain_loss": 0.03771151602268219,
|
| 1399 |
+
"step": 440
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 1.7398615232443126,
|
| 1403 |
+
"forget_loss": 1.33451692363451e-07,
|
| 1404 |
+
"retain_loss": 0.030054600909352303,
|
| 1405 |
+
"step": 440
|
| 1406 |
+
},
|
| 1407 |
+
{
|
| 1408 |
+
"epoch": 1.7794263105835806,
|
| 1409 |
+
"grad_norm": 0.41796875,
|
| 1410 |
+
"learning_rate": 5.745967741935484e-06,
|
| 1411 |
+
"loss": 0.05158230662345886,
|
| 1412 |
+
"step": 450
|
| 1413 |
+
},
|
| 1414 |
+
{
|
| 1415 |
+
"epoch": 1.7794263105835806,
|
| 1416 |
+
"forget_loss": 7.282965270860586e-06,
|
| 1417 |
+
"retain_loss": 0.02785342186689377,
|
| 1418 |
+
"step": 450
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 1.7794263105835806,
|
| 1422 |
+
"forget_loss": 6.616839982598322e-07,
|
| 1423 |
+
"retain_loss": 0.03133387118577957,
|
| 1424 |
+
"step": 450
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.7794263105835806,
|
| 1428 |
+
"forget_loss": 1.6606659869466966e-07,
|
| 1429 |
+
"retain_loss": 0.028537921607494354,
|
| 1430 |
+
"step": 450
|
| 1431 |
+
},
|
| 1432 |
+
{
|
| 1433 |
+
"epoch": 1.7794263105835806,
|
| 1434 |
+
"forget_loss": 4.580670065479353e-08,
|
| 1435 |
+
"retain_loss": 0.0259918924421072,
|
| 1436 |
+
"step": 450
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"epoch": 1.8189910979228485,
|
| 1440 |
+
"grad_norm": 0.5703125,
|
| 1441 |
+
"learning_rate": 4.737903225806452e-06,
|
| 1442 |
+
"loss": 0.039455512166023256,
|
| 1443 |
+
"step": 460
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 1.8189910979228485,
|
| 1447 |
+
"forget_loss": 6.603767133128713e-07,
|
| 1448 |
+
"retain_loss": 0.03985912352800369,
|
| 1449 |
+
"step": 460
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 1.8189910979228485,
|
| 1453 |
+
"forget_loss": 3.943401907235966e-07,
|
| 1454 |
+
"retain_loss": 0.04197068139910698,
|
| 1455 |
+
"step": 460
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 1.8189910979228485,
|
| 1459 |
+
"forget_loss": 1.5381397133751307e-07,
|
| 1460 |
+
"retain_loss": 0.032300617545843124,
|
| 1461 |
+
"step": 460
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 1.8189910979228485,
|
| 1465 |
+
"forget_loss": 4.2404886357871874e-07,
|
| 1466 |
+
"retain_loss": 0.05860987678170204,
|
| 1467 |
+
"step": 460
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 1.8585558852621167,
|
| 1471 |
+
"grad_norm": 0.73046875,
|
| 1472 |
+
"learning_rate": 3.7298387096774197e-06,
|
| 1473 |
+
"loss": 0.03943937718868255,
|
| 1474 |
+
"step": 470
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 1.8585558852621167,
|
| 1478 |
+
"forget_loss": 1.0874501299440453e-07,
|
| 1479 |
+
"retain_loss": 0.034533917903900146,
|
| 1480 |
+
"step": 470
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.8585558852621167,
|
| 1484 |
+
"forget_loss": 1.2879773692020535e-07,
|
| 1485 |
+
"retain_loss": 0.02758140303194523,
|
| 1486 |
+
"step": 470
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 1.8585558852621167,
|
| 1490 |
+
"forget_loss": 4.720429387816694e-06,
|
| 1491 |
+
"retain_loss": 0.025139721110463142,
|
| 1492 |
+
"step": 470
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 1.8585558852621167,
|
| 1496 |
+
"forget_loss": 6.679280772914353e-08,
|
| 1497 |
+
"retain_loss": 0.014747953973710537,
|
| 1498 |
+
"step": 470
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 1.8981206726013848,
|
| 1502 |
+
"grad_norm": 0.396484375,
|
| 1503 |
+
"learning_rate": 2.721774193548387e-06,
|
| 1504 |
+
"loss": 0.03879976570606232,
|
| 1505 |
+
"step": 480
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 1.8981206726013848,
|
| 1509 |
+
"forget_loss": 2.390359213677584e-06,
|
| 1510 |
+
"retain_loss": 0.17955298721790314,
|
| 1511 |
+
"step": 480
|
| 1512 |
+
},
|
| 1513 |
+
{
|
| 1514 |
+
"epoch": 1.8981206726013848,
|
| 1515 |
+
"forget_loss": 1.1778739690271323e-06,
|
| 1516 |
+
"retain_loss": 0.03140717372298241,
|
| 1517 |
+
"step": 480
|
| 1518 |
+
},
|
| 1519 |
+
{
|
| 1520 |
+
"epoch": 1.8981206726013848,
|
| 1521 |
+
"forget_loss": 8.414248213739484e-07,
|
| 1522 |
+
"retain_loss": 0.024419624358415604,
|
| 1523 |
+
"step": 480
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 1.8981206726013848,
|
| 1527 |
+
"forget_loss": 1.882670517261431e-07,
|
| 1528 |
+
"retain_loss": 0.04787850007414818,
|
| 1529 |
+
"step": 480
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.9376854599406528,
|
| 1533 |
+
"grad_norm": 0.69140625,
|
| 1534 |
+
"learning_rate": 1.7137096774193548e-06,
|
| 1535 |
+
"loss": 0.04431060552597046,
|
| 1536 |
+
"step": 490
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.9376854599406528,
|
| 1540 |
+
"forget_loss": 6.971927746235451e-07,
|
| 1541 |
+
"retain_loss": 0.056132722645998,
|
| 1542 |
+
"step": 490
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 1.9376854599406528,
|
| 1546 |
+
"forget_loss": 1.3472174487105804e-06,
|
| 1547 |
+
"retain_loss": 0.05203668773174286,
|
| 1548 |
+
"step": 490
|
| 1549 |
+
},
|
| 1550 |
+
{
|
| 1551 |
+
"epoch": 1.9376854599406528,
|
| 1552 |
+
"forget_loss": 1.8118841182968026e-07,
|
| 1553 |
+
"retain_loss": 0.02416139468550682,
|
| 1554 |
+
"step": 490
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 1.9376854599406528,
|
| 1558 |
+
"forget_loss": 9.088048500416335e-07,
|
| 1559 |
+
"retain_loss": 0.04348018392920494,
|
| 1560 |
+
"step": 490
|
| 1561 |
+
},
|
| 1562 |
+
{
|
| 1563 |
+
"epoch": 1.9772502472799207,
|
| 1564 |
+
"grad_norm": 0.40625,
|
| 1565 |
+
"learning_rate": 7.056451612903225e-07,
|
| 1566 |
+
"loss": 0.038701888918876645,
|
| 1567 |
+
"step": 500
|
| 1568 |
+
},
|
| 1569 |
+
{
|
| 1570 |
+
"epoch": 1.9772502472799207,
|
| 1571 |
+
"forget_loss": 3.1423081736647873e-07,
|
| 1572 |
+
"retain_loss": 0.025279447436332703,
|
| 1573 |
+
"step": 500
|
| 1574 |
+
},
|
| 1575 |
+
{
|
| 1576 |
+
"epoch": 1.9772502472799207,
|
| 1577 |
+
"forget_loss": 2.0392130295476818e-07,
|
| 1578 |
+
"retain_loss": 0.08473268151283264,
|
| 1579 |
+
"step": 500
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 1.9772502472799207,
|
| 1583 |
+
"forget_loss": 6.266716212621759e-08,
|
| 1584 |
+
"retain_loss": 0.03677506372332573,
|
| 1585 |
+
"step": 500
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.9772502472799207,
|
| 1589 |
+
"forget_loss": 3.635840073457075e-07,
|
| 1590 |
+
"retain_loss": 0.02540448121726513,
|
| 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:f4daa46b81e960187a13cf9715d61600f7d344da408f25fda410bfb3b965becf
|
| 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-target-100:forget:baseline
|
| 3 |
+
retain_path: unlearning-cleanslate/fsid-curated-olmo-7b-target-100: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-target-100
|
| 32 |
+
hub_private: false
|
| 33 |
+
optim: adamw_torch
|
| 34 |
+
_run_name: simnpo_Olmo-3-1025-7B_20260428_231941
|
| 35 |
+
_run_dir: /runs/simnpo_Olmo-3-1025-7B_20260428_231941
|
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 sha256:0a91bd65af2bfe705722480faf3fd4d68a88a346aa1679533fb34857076817e0
|
| 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 23:21:09,776 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_231941
|
| 2 |
+
2026-04-28 23:21:09,776 INFO cleanslate.fsid.training.trainer: [RANK 0] Starting training: objective=simnpo epochs=2
|
| 3 |
+
2026-04-28 23:34:43,528 INFO cleanslate.fsid.training.trainer: [RANK 0] Saved checkpoint to /runs/simnpo_Olmo-3-1025-7B_20260428_231941
|
| 4 |
+
2026-04-28 23:34:43,531 INFO cleanslate.fsid.training.trainer: [RANK 0] Training complete (791.7s)
|
| 5 |
+
2026-04-28 23:34:43,995 INFO cleanslate.fsid.training.trainer: [RANK 0] Pushing checkpoint dir /runs/simnpo_Olmo-3-1025-7B_20260428_231941 to unlearning-cleanslate/olmo-3-7b-simnpo-baseline-target-100
|
train_summary.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"run_name": "simnpo_Olmo-3-1025-7B_20260428_231941",
|
| 3 |
+
"run_dir": "/runs/simnpo_Olmo-3-1025-7B_20260428_231941",
|
| 4 |
+
"config": {
|
| 5 |
+
"model_name": "allenai/Olmo-3-1025-7B",
|
| 6 |
+
"forget_path": "unlearning-cleanslate/fsid-curated-olmo-7b-target-100:forget:baseline",
|
| 7 |
+
"retain_path": "unlearning-cleanslate/fsid-curated-olmo-7b-target-100: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-target-100",
|
| 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": 791.6917028427124,
|
| 46 |
+
"checkpoint_dir": "/runs/simnpo_Olmo-3-1025-7B_20260428_231941",
|
| 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:f4daa46b81e960187a13cf9715d61600f7d344da408f25fda410bfb3b965becf
|
| 3 |
+
size 5329
|