Add files using upload-large-folder tool
Browse files- checkpoint-114591/config.json +74 -0
- checkpoint-114591/generation_config.json +13 -0
- checkpoint-114591/merges.txt +0 -0
- checkpoint-114591/model.safetensors +3 -0
- checkpoint-114591/optimizer.pt +3 -0
- checkpoint-114591/rng_state.pth +3 -0
- checkpoint-114591/scheduler.pt +3 -0
- checkpoint-114591/special_tokens_map.json +15 -0
- checkpoint-114591/tokenizer.json +0 -0
- checkpoint-114591/tokenizer_config.json +58 -0
- checkpoint-114591/trainer_state.json +1660 -0
- checkpoint-114591/training_args.bin +3 -0
- checkpoint-114591/vocab.json +0 -0
- checkpoint-38197/config.json +74 -0
- checkpoint-38197/generation_config.json +13 -0
- checkpoint-38197/merges.txt +0 -0
- checkpoint-38197/model.safetensors +3 -0
- checkpoint-38197/optimizer.pt +3 -0
- checkpoint-38197/rng_state.pth +3 -0
- checkpoint-38197/scheduler.pt +3 -0
- checkpoint-38197/special_tokens_map.json +15 -0
- checkpoint-38197/tokenizer.json +0 -0
- checkpoint-38197/tokenizer_config.json +58 -0
- checkpoint-38197/trainer_state.json +573 -0
- checkpoint-38197/training_args.bin +3 -0
- checkpoint-38197/vocab.json +0 -0
- checkpoint-76394/config.json +74 -0
- checkpoint-76394/generation_config.json +13 -0
- checkpoint-76394/merges.txt +0 -0
- checkpoint-76394/model.safetensors +3 -0
- checkpoint-76394/optimizer.pt +3 -0
- checkpoint-76394/rng_state.pth +3 -0
- checkpoint-76394/scheduler.pt +3 -0
- checkpoint-76394/special_tokens_map.json +15 -0
- checkpoint-76394/tokenizer.json +0 -0
- checkpoint-76394/tokenizer_config.json +58 -0
- checkpoint-76394/trainer_state.json +1113 -0
- checkpoint-76394/training_args.bin +3 -0
- checkpoint-76394/vocab.json +0 -0
- config.json +74 -0
- generation_config.json +13 -0
- load_model.ipynb +132 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_args.bin +3 -0
- vocab.json +0 -0
checkpoint-114591/config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": null,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_eos_token_id": 2,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_position_embeddings": 1024,
|
| 42 |
+
"model_type": "bart",
|
| 43 |
+
"no_repeat_ngram_size": null,
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"normalize_embedding": true,
|
| 46 |
+
"num_beams": null,
|
| 47 |
+
"num_hidden_layers": 6,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"scale_embedding": false,
|
| 50 |
+
"task_specific_params": {
|
| 51 |
+
"summarization": {
|
| 52 |
+
"length_penalty": 1.0,
|
| 53 |
+
"max_length": 128,
|
| 54 |
+
"min_length": 12,
|
| 55 |
+
"num_beams": 4
|
| 56 |
+
},
|
| 57 |
+
"summarization_cnn": {
|
| 58 |
+
"length_penalty": 2.0,
|
| 59 |
+
"max_length": 142,
|
| 60 |
+
"min_length": 56,
|
| 61 |
+
"num_beams": 4
|
| 62 |
+
},
|
| 63 |
+
"summarization_xsum": {
|
| 64 |
+
"length_penalty": 1.0,
|
| 65 |
+
"max_length": 62,
|
| 66 |
+
"min_length": 11,
|
| 67 |
+
"num_beams": 6
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"torch_dtype": "float32",
|
| 71 |
+
"transformers_version": "4.48.3",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"vocab_size": 50265
|
| 74 |
+
}
|
checkpoint-114591/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.48.3"
|
| 13 |
+
}
|
checkpoint-114591/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-114591/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d51cfc04e9563e0bb5243172241fcae18435e6bf2f3345ac6a478f467d2b9a89
|
| 3 |
+
size 557912620
|
checkpoint-114591/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:384fab2b110477564726241b00e9809e69583c1014cb8e7de6a549a12fde8a20
|
| 3 |
+
size 1115579898
|
checkpoint-114591/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b6d427e5c3d9c24d9ea333a029510ec3cd0cb7259cd1d0e64d1c6273959db9b
|
| 3 |
+
size 14244
|
checkpoint-114591/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5ac4a26afeaece2f0ff897872866e186c6d4879bd75dd30913c1402f4c2cf17
|
| 3 |
+
size 1064
|
checkpoint-114591/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
checkpoint-114591/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-114591/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "BartTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-114591/trainer_state.json
ADDED
|
@@ -0,0 +1,1660 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 114591,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.013090033248684452,
|
| 13 |
+
"grad_norm": 0.4367656707763672,
|
| 14 |
+
"learning_rate": 1.991273311167544e-05,
|
| 15 |
+
"loss": 1.32,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.026180066497368905,
|
| 20 |
+
"grad_norm": 0.39482298493385315,
|
| 21 |
+
"learning_rate": 1.9825466223350874e-05,
|
| 22 |
+
"loss": 0.0594,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.039270099746053354,
|
| 27 |
+
"grad_norm": 0.47824403643608093,
|
| 28 |
+
"learning_rate": 1.9738199335026312e-05,
|
| 29 |
+
"loss": 0.0497,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05236013299473781,
|
| 34 |
+
"grad_norm": 0.3971627652645111,
|
| 35 |
+
"learning_rate": 1.965093244670175e-05,
|
| 36 |
+
"loss": 0.043,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06545016624342226,
|
| 41 |
+
"grad_norm": 0.5000212788581848,
|
| 42 |
+
"learning_rate": 1.9563665558377188e-05,
|
| 43 |
+
"loss": 0.0374,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07854019949210671,
|
| 48 |
+
"grad_norm": 0.9078471064567566,
|
| 49 |
+
"learning_rate": 1.9476398670052623e-05,
|
| 50 |
+
"loss": 0.0357,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09163023274079116,
|
| 55 |
+
"grad_norm": 0.35205739736557007,
|
| 56 |
+
"learning_rate": 1.938913178172806e-05,
|
| 57 |
+
"loss": 0.0317,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.10472026598947562,
|
| 62 |
+
"grad_norm": 0.19642357528209686,
|
| 63 |
+
"learning_rate": 1.9301864893403495e-05,
|
| 64 |
+
"loss": 0.0304,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.11781029923816007,
|
| 69 |
+
"grad_norm": 0.5134682655334473,
|
| 70 |
+
"learning_rate": 1.9214598005078933e-05,
|
| 71 |
+
"loss": 0.0281,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.13090033248684452,
|
| 76 |
+
"grad_norm": 0.23212824761867523,
|
| 77 |
+
"learning_rate": 1.912733111675437e-05,
|
| 78 |
+
"loss": 0.0274,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.14399036573552898,
|
| 83 |
+
"grad_norm": 0.4254980981349945,
|
| 84 |
+
"learning_rate": 1.904006422842981e-05,
|
| 85 |
+
"loss": 0.0247,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.15708039898421342,
|
| 90 |
+
"grad_norm": 0.4024842083454132,
|
| 91 |
+
"learning_rate": 1.8952797340105244e-05,
|
| 92 |
+
"loss": 0.0235,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.17017043223289788,
|
| 97 |
+
"grad_norm": 0.40947026014328003,
|
| 98 |
+
"learning_rate": 1.8865530451780682e-05,
|
| 99 |
+
"loss": 0.0235,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1832604654815823,
|
| 104 |
+
"grad_norm": 0.366158127784729,
|
| 105 |
+
"learning_rate": 1.877826356345612e-05,
|
| 106 |
+
"loss": 0.0225,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.19635049873026678,
|
| 111 |
+
"grad_norm": 0.4678824841976166,
|
| 112 |
+
"learning_rate": 1.8690996675131558e-05,
|
| 113 |
+
"loss": 0.0219,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.20944053197895124,
|
| 118 |
+
"grad_norm": 0.21004918217658997,
|
| 119 |
+
"learning_rate": 1.8603729786806996e-05,
|
| 120 |
+
"loss": 0.0198,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.22253056522763567,
|
| 125 |
+
"grad_norm": 0.2192375510931015,
|
| 126 |
+
"learning_rate": 1.851646289848243e-05,
|
| 127 |
+
"loss": 0.0201,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.23562059847632014,
|
| 132 |
+
"grad_norm": 0.15161575376987457,
|
| 133 |
+
"learning_rate": 1.842919601015787e-05,
|
| 134 |
+
"loss": 0.0192,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.24871063172500457,
|
| 139 |
+
"grad_norm": 0.3270639181137085,
|
| 140 |
+
"learning_rate": 1.8341929121833303e-05,
|
| 141 |
+
"loss": 0.0186,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.26180066497368903,
|
| 146 |
+
"grad_norm": 0.25447696447372437,
|
| 147 |
+
"learning_rate": 1.825466223350874e-05,
|
| 148 |
+
"loss": 0.0182,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2748906982223735,
|
| 153 |
+
"grad_norm": 0.1797029674053192,
|
| 154 |
+
"learning_rate": 1.816739534518418e-05,
|
| 155 |
+
"loss": 0.0182,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.28798073147105796,
|
| 160 |
+
"grad_norm": 0.4422529637813568,
|
| 161 |
+
"learning_rate": 1.8080128456859617e-05,
|
| 162 |
+
"loss": 0.0175,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.30107076471974237,
|
| 167 |
+
"grad_norm": 0.19019261002540588,
|
| 168 |
+
"learning_rate": 1.7992861568535052e-05,
|
| 169 |
+
"loss": 0.0159,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.31416079796842683,
|
| 174 |
+
"grad_norm": 0.12262561917304993,
|
| 175 |
+
"learning_rate": 1.790559468021049e-05,
|
| 176 |
+
"loss": 0.0162,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3272508312171113,
|
| 181 |
+
"grad_norm": 0.5514086484909058,
|
| 182 |
+
"learning_rate": 1.7818327791885924e-05,
|
| 183 |
+
"loss": 0.0159,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.34034086446579576,
|
| 188 |
+
"grad_norm": 0.3397659957408905,
|
| 189 |
+
"learning_rate": 1.7731060903561362e-05,
|
| 190 |
+
"loss": 0.0163,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.3534308977144802,
|
| 195 |
+
"grad_norm": 0.3542526364326477,
|
| 196 |
+
"learning_rate": 1.76437940152368e-05,
|
| 197 |
+
"loss": 0.0161,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3665209309631646,
|
| 202 |
+
"grad_norm": 0.22688041627407074,
|
| 203 |
+
"learning_rate": 1.7556527126912238e-05,
|
| 204 |
+
"loss": 0.0155,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3796109642118491,
|
| 209 |
+
"grad_norm": 0.20115447044372559,
|
| 210 |
+
"learning_rate": 1.7469260238587673e-05,
|
| 211 |
+
"loss": 0.0148,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.39270099746053355,
|
| 216 |
+
"grad_norm": 0.09773228317499161,
|
| 217 |
+
"learning_rate": 1.738199335026311e-05,
|
| 218 |
+
"loss": 0.0149,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.405791030709218,
|
| 223 |
+
"grad_norm": 0.41297146677970886,
|
| 224 |
+
"learning_rate": 1.729472646193855e-05,
|
| 225 |
+
"loss": 0.0146,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4188810639579025,
|
| 230 |
+
"grad_norm": 0.6495208740234375,
|
| 231 |
+
"learning_rate": 1.7207459573613983e-05,
|
| 232 |
+
"loss": 0.0136,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4319710972065869,
|
| 237 |
+
"grad_norm": 0.35930490493774414,
|
| 238 |
+
"learning_rate": 1.712019268528942e-05,
|
| 239 |
+
"loss": 0.0137,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.44506113045527135,
|
| 244 |
+
"grad_norm": 0.22953346371650696,
|
| 245 |
+
"learning_rate": 1.703292579696486e-05,
|
| 246 |
+
"loss": 0.0139,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4581511637039558,
|
| 251 |
+
"grad_norm": 0.41518378257751465,
|
| 252 |
+
"learning_rate": 1.6945658908640297e-05,
|
| 253 |
+
"loss": 0.0135,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4712411969526403,
|
| 258 |
+
"grad_norm": 0.2171572744846344,
|
| 259 |
+
"learning_rate": 1.6858392020315732e-05,
|
| 260 |
+
"loss": 0.0129,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.48433123020132474,
|
| 265 |
+
"grad_norm": 0.2897777557373047,
|
| 266 |
+
"learning_rate": 1.677112513199117e-05,
|
| 267 |
+
"loss": 0.0122,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.49742126345000914,
|
| 272 |
+
"grad_norm": 0.4209305942058563,
|
| 273 |
+
"learning_rate": 1.6683858243666608e-05,
|
| 274 |
+
"loss": 0.0128,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5105112966986937,
|
| 279 |
+
"grad_norm": 0.08220311999320984,
|
| 280 |
+
"learning_rate": 1.6596591355342046e-05,
|
| 281 |
+
"loss": 0.0123,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5236013299473781,
|
| 286 |
+
"grad_norm": 0.09847331047058105,
|
| 287 |
+
"learning_rate": 1.650932446701748e-05,
|
| 288 |
+
"loss": 0.0123,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5366913631960625,
|
| 293 |
+
"grad_norm": 0.41798558831214905,
|
| 294 |
+
"learning_rate": 1.642205757869292e-05,
|
| 295 |
+
"loss": 0.0128,
|
| 296 |
+
"step": 20500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.549781396444747,
|
| 300 |
+
"grad_norm": 0.2177186757326126,
|
| 301 |
+
"learning_rate": 1.6334790690368353e-05,
|
| 302 |
+
"loss": 0.0124,
|
| 303 |
+
"step": 21000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5628714296934314,
|
| 307 |
+
"grad_norm": 0.16467055678367615,
|
| 308 |
+
"learning_rate": 1.624752380204379e-05,
|
| 309 |
+
"loss": 0.0118,
|
| 310 |
+
"step": 21500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5759614629421159,
|
| 314 |
+
"grad_norm": 0.3392176330089569,
|
| 315 |
+
"learning_rate": 1.616025691371923e-05,
|
| 316 |
+
"loss": 0.0121,
|
| 317 |
+
"step": 22000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5890514961908003,
|
| 321 |
+
"grad_norm": 0.14208835363388062,
|
| 322 |
+
"learning_rate": 1.6072990025394667e-05,
|
| 323 |
+
"loss": 0.0118,
|
| 324 |
+
"step": 22500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6021415294394847,
|
| 328 |
+
"grad_norm": 0.18248602747917175,
|
| 329 |
+
"learning_rate": 1.5985723137070105e-05,
|
| 330 |
+
"loss": 0.0118,
|
| 331 |
+
"step": 23000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6152315626881693,
|
| 335 |
+
"grad_norm": 0.32215237617492676,
|
| 336 |
+
"learning_rate": 1.589845624874554e-05,
|
| 337 |
+
"loss": 0.0111,
|
| 338 |
+
"step": 23500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6283215959368537,
|
| 342 |
+
"grad_norm": 0.35770946741104126,
|
| 343 |
+
"learning_rate": 1.5811189360420978e-05,
|
| 344 |
+
"loss": 0.0111,
|
| 345 |
+
"step": 24000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6414116291855382,
|
| 349 |
+
"grad_norm": 0.21091119945049286,
|
| 350 |
+
"learning_rate": 1.5723922472096412e-05,
|
| 351 |
+
"loss": 0.0115,
|
| 352 |
+
"step": 24500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6545016624342226,
|
| 356 |
+
"grad_norm": 0.215097576379776,
|
| 357 |
+
"learning_rate": 1.563665558377185e-05,
|
| 358 |
+
"loss": 0.0107,
|
| 359 |
+
"step": 25000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.667591695682907,
|
| 363 |
+
"grad_norm": 0.15477751195430756,
|
| 364 |
+
"learning_rate": 1.554938869544729e-05,
|
| 365 |
+
"loss": 0.0105,
|
| 366 |
+
"step": 25500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.6806817289315915,
|
| 370 |
+
"grad_norm": 0.1576426774263382,
|
| 371 |
+
"learning_rate": 1.5462121807122726e-05,
|
| 372 |
+
"loss": 0.0105,
|
| 373 |
+
"step": 26000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6937717621802759,
|
| 377 |
+
"grad_norm": 0.19675689935684204,
|
| 378 |
+
"learning_rate": 1.537485491879816e-05,
|
| 379 |
+
"loss": 0.0096,
|
| 380 |
+
"step": 26500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.7068617954289604,
|
| 384 |
+
"grad_norm": 0.480955570936203,
|
| 385 |
+
"learning_rate": 1.52875880304736e-05,
|
| 386 |
+
"loss": 0.0104,
|
| 387 |
+
"step": 27000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7199518286776448,
|
| 391 |
+
"grad_norm": 0.2651515603065491,
|
| 392 |
+
"learning_rate": 1.5200321142149035e-05,
|
| 393 |
+
"loss": 0.0106,
|
| 394 |
+
"step": 27500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7330418619263293,
|
| 398 |
+
"grad_norm": 0.21407313644886017,
|
| 399 |
+
"learning_rate": 1.5113054253824473e-05,
|
| 400 |
+
"loss": 0.0102,
|
| 401 |
+
"step": 28000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.7461318951750138,
|
| 405 |
+
"grad_norm": 0.13915963470935822,
|
| 406 |
+
"learning_rate": 1.502578736549991e-05,
|
| 407 |
+
"loss": 0.0098,
|
| 408 |
+
"step": 28500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7592219284236982,
|
| 412 |
+
"grad_norm": 0.09625498950481415,
|
| 413 |
+
"learning_rate": 1.4938520477175348e-05,
|
| 414 |
+
"loss": 0.0099,
|
| 415 |
+
"step": 29000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7723119616723827,
|
| 419 |
+
"grad_norm": 0.26766207814216614,
|
| 420 |
+
"learning_rate": 1.4851253588850782e-05,
|
| 421 |
+
"loss": 0.01,
|
| 422 |
+
"step": 29500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7854019949210671,
|
| 426 |
+
"grad_norm": 0.03729819133877754,
|
| 427 |
+
"learning_rate": 1.476398670052622e-05,
|
| 428 |
+
"loss": 0.0092,
|
| 429 |
+
"step": 30000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7984920281697515,
|
| 433 |
+
"grad_norm": 0.19327211380004883,
|
| 434 |
+
"learning_rate": 1.4676719812201658e-05,
|
| 435 |
+
"loss": 0.0094,
|
| 436 |
+
"step": 30500
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.811582061418436,
|
| 440 |
+
"grad_norm": 0.27896180748939514,
|
| 441 |
+
"learning_rate": 1.4589452923877094e-05,
|
| 442 |
+
"loss": 0.01,
|
| 443 |
+
"step": 31000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.8246720946671204,
|
| 447 |
+
"grad_norm": 0.1490613967180252,
|
| 448 |
+
"learning_rate": 1.4502186035552532e-05,
|
| 449 |
+
"loss": 0.0092,
|
| 450 |
+
"step": 31500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.837762127915805,
|
| 454 |
+
"grad_norm": 0.22722095251083374,
|
| 455 |
+
"learning_rate": 1.4414919147227969e-05,
|
| 456 |
+
"loss": 0.0093,
|
| 457 |
+
"step": 32000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.8508521611644894,
|
| 461 |
+
"grad_norm": 0.2942313849925995,
|
| 462 |
+
"learning_rate": 1.4327652258903407e-05,
|
| 463 |
+
"loss": 0.0098,
|
| 464 |
+
"step": 32500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8639421944131738,
|
| 468 |
+
"grad_norm": 0.37654176354408264,
|
| 469 |
+
"learning_rate": 1.4240385370578841e-05,
|
| 470 |
+
"loss": 0.0095,
|
| 471 |
+
"step": 33000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8770322276618583,
|
| 475 |
+
"grad_norm": 0.21543939411640167,
|
| 476 |
+
"learning_rate": 1.415311848225428e-05,
|
| 477 |
+
"loss": 0.0097,
|
| 478 |
+
"step": 33500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8901222609105427,
|
| 482 |
+
"grad_norm": 0.4608267843723297,
|
| 483 |
+
"learning_rate": 1.4065851593929716e-05,
|
| 484 |
+
"loss": 0.0093,
|
| 485 |
+
"step": 34000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.9032122941592272,
|
| 489 |
+
"grad_norm": 0.1784515380859375,
|
| 490 |
+
"learning_rate": 1.3978584705605154e-05,
|
| 491 |
+
"loss": 0.009,
|
| 492 |
+
"step": 34500
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.9163023274079116,
|
| 496 |
+
"grad_norm": 0.3353884518146515,
|
| 497 |
+
"learning_rate": 1.389131781728059e-05,
|
| 498 |
+
"loss": 0.009,
|
| 499 |
+
"step": 35000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.929392360656596,
|
| 503 |
+
"grad_norm": 0.2330337017774582,
|
| 504 |
+
"learning_rate": 1.3804050928956028e-05,
|
| 505 |
+
"loss": 0.009,
|
| 506 |
+
"step": 35500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.9424823939052805,
|
| 510 |
+
"grad_norm": 0.32975077629089355,
|
| 511 |
+
"learning_rate": 1.3716784040631464e-05,
|
| 512 |
+
"loss": 0.0092,
|
| 513 |
+
"step": 36000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.955572427153965,
|
| 517 |
+
"grad_norm": 0.03280099481344223,
|
| 518 |
+
"learning_rate": 1.3629517152306902e-05,
|
| 519 |
+
"loss": 0.0084,
|
| 520 |
+
"step": 36500
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.9686624604026495,
|
| 524 |
+
"grad_norm": 0.22344884276390076,
|
| 525 |
+
"learning_rate": 1.3542250263982337e-05,
|
| 526 |
+
"loss": 0.0089,
|
| 527 |
+
"step": 37000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.9817524936513339,
|
| 531 |
+
"grad_norm": 0.361147403717041,
|
| 532 |
+
"learning_rate": 1.3454983375657775e-05,
|
| 533 |
+
"loss": 0.0084,
|
| 534 |
+
"step": 37500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.9948425269000183,
|
| 538 |
+
"grad_norm": 0.2099611908197403,
|
| 539 |
+
"learning_rate": 1.3367716487333213e-05,
|
| 540 |
+
"loss": 0.0088,
|
| 541 |
+
"step": 38000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.0,
|
| 545 |
+
"eval_loss": 0.005731215700507164,
|
| 546 |
+
"eval_runtime": 2297.4971,
|
| 547 |
+
"eval_samples_per_second": 133.003,
|
| 548 |
+
"eval_steps_per_second": 16.625,
|
| 549 |
+
"step": 38197
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.0079325601487028,
|
| 553 |
+
"grad_norm": 0.24136124551296234,
|
| 554 |
+
"learning_rate": 1.3280449599008649e-05,
|
| 555 |
+
"loss": 0.0078,
|
| 556 |
+
"step": 38500
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.0210225933973873,
|
| 560 |
+
"grad_norm": 0.42886942625045776,
|
| 561 |
+
"learning_rate": 1.3193182710684087e-05,
|
| 562 |
+
"loss": 0.0082,
|
| 563 |
+
"step": 39000
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.0341126266460716,
|
| 567 |
+
"grad_norm": 0.10831937938928604,
|
| 568 |
+
"learning_rate": 1.3105915822359523e-05,
|
| 569 |
+
"loss": 0.0071,
|
| 570 |
+
"step": 39500
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.0472026598947561,
|
| 574 |
+
"grad_norm": 0.20537184178829193,
|
| 575 |
+
"learning_rate": 1.3018648934034961e-05,
|
| 576 |
+
"loss": 0.0081,
|
| 577 |
+
"step": 40000
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.0602926931434407,
|
| 581 |
+
"grad_norm": 0.28797346353530884,
|
| 582 |
+
"learning_rate": 1.2931382045710396e-05,
|
| 583 |
+
"loss": 0.0075,
|
| 584 |
+
"step": 40500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.073382726392125,
|
| 588 |
+
"grad_norm": 0.22928300499916077,
|
| 589 |
+
"learning_rate": 1.2844115157385834e-05,
|
| 590 |
+
"loss": 0.0076,
|
| 591 |
+
"step": 41000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.0864727596408095,
|
| 595 |
+
"grad_norm": 0.003099123015999794,
|
| 596 |
+
"learning_rate": 1.275684826906127e-05,
|
| 597 |
+
"loss": 0.0079,
|
| 598 |
+
"step": 41500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.099562792889494,
|
| 602 |
+
"grad_norm": 0.287396639585495,
|
| 603 |
+
"learning_rate": 1.2669581380736708e-05,
|
| 604 |
+
"loss": 0.0075,
|
| 605 |
+
"step": 42000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.1126528261381785,
|
| 609 |
+
"grad_norm": 0.07049620896577835,
|
| 610 |
+
"learning_rate": 1.2582314492412144e-05,
|
| 611 |
+
"loss": 0.007,
|
| 612 |
+
"step": 42500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.1257428593868628,
|
| 616 |
+
"grad_norm": 0.2029752880334854,
|
| 617 |
+
"learning_rate": 1.2495047604087582e-05,
|
| 618 |
+
"loss": 0.0076,
|
| 619 |
+
"step": 43000
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.1388328926355473,
|
| 623 |
+
"grad_norm": 0.04248388856649399,
|
| 624 |
+
"learning_rate": 1.2407780715763019e-05,
|
| 625 |
+
"loss": 0.0072,
|
| 626 |
+
"step": 43500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.1519229258842318,
|
| 630 |
+
"grad_norm": 0.4174834191799164,
|
| 631 |
+
"learning_rate": 1.2320513827438457e-05,
|
| 632 |
+
"loss": 0.0077,
|
| 633 |
+
"step": 44000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.1650129591329161,
|
| 637 |
+
"grad_norm": 0.25623586773872375,
|
| 638 |
+
"learning_rate": 1.2233246939113891e-05,
|
| 639 |
+
"loss": 0.0069,
|
| 640 |
+
"step": 44500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.1781029923816007,
|
| 644 |
+
"grad_norm": 0.12231756001710892,
|
| 645 |
+
"learning_rate": 1.214598005078933e-05,
|
| 646 |
+
"loss": 0.0076,
|
| 647 |
+
"step": 45000
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.1911930256302852,
|
| 651 |
+
"grad_norm": 0.24928466975688934,
|
| 652 |
+
"learning_rate": 1.2058713162464767e-05,
|
| 653 |
+
"loss": 0.0072,
|
| 654 |
+
"step": 45500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.2042830588789695,
|
| 658 |
+
"grad_norm": 0.11469607055187225,
|
| 659 |
+
"learning_rate": 1.1971446274140204e-05,
|
| 660 |
+
"loss": 0.0068,
|
| 661 |
+
"step": 46000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.217373092127654,
|
| 665 |
+
"grad_norm": 0.389217734336853,
|
| 666 |
+
"learning_rate": 1.1884179385815642e-05,
|
| 667 |
+
"loss": 0.0072,
|
| 668 |
+
"step": 46500
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.2304631253763385,
|
| 672 |
+
"grad_norm": 0.1249752938747406,
|
| 673 |
+
"learning_rate": 1.1796912497491078e-05,
|
| 674 |
+
"loss": 0.0065,
|
| 675 |
+
"step": 47000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.2435531586250228,
|
| 679 |
+
"grad_norm": 0.2189619392156601,
|
| 680 |
+
"learning_rate": 1.1709645609166516e-05,
|
| 681 |
+
"loss": 0.0073,
|
| 682 |
+
"step": 47500
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2566431918737073,
|
| 686 |
+
"grad_norm": 0.3927897810935974,
|
| 687 |
+
"learning_rate": 1.1622378720841952e-05,
|
| 688 |
+
"loss": 0.0069,
|
| 689 |
+
"step": 48000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2697332251223918,
|
| 693 |
+
"grad_norm": 0.07470349222421646,
|
| 694 |
+
"learning_rate": 1.153511183251739e-05,
|
| 695 |
+
"loss": 0.0076,
|
| 696 |
+
"step": 48500
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.2828232583710761,
|
| 700 |
+
"grad_norm": 0.3911282420158386,
|
| 701 |
+
"learning_rate": 1.1447844944192825e-05,
|
| 702 |
+
"loss": 0.0071,
|
| 703 |
+
"step": 49000
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.2959132916197607,
|
| 707 |
+
"grad_norm": 0.2361019402742386,
|
| 708 |
+
"learning_rate": 1.1360578055868263e-05,
|
| 709 |
+
"loss": 0.0074,
|
| 710 |
+
"step": 49500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.3090033248684452,
|
| 714 |
+
"grad_norm": 0.1682516634464264,
|
| 715 |
+
"learning_rate": 1.1273311167543699e-05,
|
| 716 |
+
"loss": 0.0076,
|
| 717 |
+
"step": 50000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.3220933581171297,
|
| 721 |
+
"grad_norm": 0.1294177621603012,
|
| 722 |
+
"learning_rate": 1.1186044279219137e-05,
|
| 723 |
+
"loss": 0.0065,
|
| 724 |
+
"step": 50500
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.335183391365814,
|
| 728 |
+
"grad_norm": 0.5710951685905457,
|
| 729 |
+
"learning_rate": 1.1098777390894573e-05,
|
| 730 |
+
"loss": 0.0068,
|
| 731 |
+
"step": 51000
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.3482734246144985,
|
| 735 |
+
"grad_norm": 0.12587948143482208,
|
| 736 |
+
"learning_rate": 1.1011510502570011e-05,
|
| 737 |
+
"loss": 0.0071,
|
| 738 |
+
"step": 51500
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.361363457863183,
|
| 742 |
+
"grad_norm": 0.37146255373954773,
|
| 743 |
+
"learning_rate": 1.0924243614245446e-05,
|
| 744 |
+
"loss": 0.0069,
|
| 745 |
+
"step": 52000
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.3744534911118675,
|
| 749 |
+
"grad_norm": 0.29824337363243103,
|
| 750 |
+
"learning_rate": 1.0836976725920884e-05,
|
| 751 |
+
"loss": 0.0069,
|
| 752 |
+
"step": 52500
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.3875435243605518,
|
| 756 |
+
"grad_norm": 0.10349422693252563,
|
| 757 |
+
"learning_rate": 1.0749709837596322e-05,
|
| 758 |
+
"loss": 0.007,
|
| 759 |
+
"step": 53000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.4006335576092364,
|
| 763 |
+
"grad_norm": 0.2823665142059326,
|
| 764 |
+
"learning_rate": 1.0662442949271758e-05,
|
| 765 |
+
"loss": 0.0069,
|
| 766 |
+
"step": 53500
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.4137235908579209,
|
| 770 |
+
"grad_norm": 0.038343362510204315,
|
| 771 |
+
"learning_rate": 1.0575176060947196e-05,
|
| 772 |
+
"loss": 0.0061,
|
| 773 |
+
"step": 54000
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.4268136241066052,
|
| 777 |
+
"grad_norm": 0.2581956088542938,
|
| 778 |
+
"learning_rate": 1.0487909172622633e-05,
|
| 779 |
+
"loss": 0.0062,
|
| 780 |
+
"step": 54500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.4399036573552897,
|
| 784 |
+
"grad_norm": 0.11447520554065704,
|
| 785 |
+
"learning_rate": 1.040064228429807e-05,
|
| 786 |
+
"loss": 0.0066,
|
| 787 |
+
"step": 55000
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.4529936906039742,
|
| 791 |
+
"grad_norm": 0.4050372838973999,
|
| 792 |
+
"learning_rate": 1.0313375395973507e-05,
|
| 793 |
+
"loss": 0.007,
|
| 794 |
+
"step": 55500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.4660837238526585,
|
| 798 |
+
"grad_norm": 0.022968396544456482,
|
| 799 |
+
"learning_rate": 1.0226108507648945e-05,
|
| 800 |
+
"loss": 0.0066,
|
| 801 |
+
"step": 56000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.479173757101343,
|
| 805 |
+
"grad_norm": 0.07500626146793365,
|
| 806 |
+
"learning_rate": 1.013884161932438e-05,
|
| 807 |
+
"loss": 0.0065,
|
| 808 |
+
"step": 56500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.4922637903500275,
|
| 812 |
+
"grad_norm": 0.031823791563510895,
|
| 813 |
+
"learning_rate": 1.0051574730999817e-05,
|
| 814 |
+
"loss": 0.0063,
|
| 815 |
+
"step": 57000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.5053538235987118,
|
| 819 |
+
"grad_norm": 0.19768255949020386,
|
| 820 |
+
"learning_rate": 9.964307842675255e-06,
|
| 821 |
+
"loss": 0.0068,
|
| 822 |
+
"step": 57500
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.5184438568473964,
|
| 826 |
+
"grad_norm": 0.210379958152771,
|
| 827 |
+
"learning_rate": 9.877040954350692e-06,
|
| 828 |
+
"loss": 0.0064,
|
| 829 |
+
"step": 58000
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.5315338900960809,
|
| 833 |
+
"grad_norm": 0.14373145997524261,
|
| 834 |
+
"learning_rate": 9.789774066026128e-06,
|
| 835 |
+
"loss": 0.007,
|
| 836 |
+
"step": 58500
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.5446239233447652,
|
| 840 |
+
"grad_norm": 0.2256031185388565,
|
| 841 |
+
"learning_rate": 9.702507177701566e-06,
|
| 842 |
+
"loss": 0.0063,
|
| 843 |
+
"step": 59000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.55771395659345,
|
| 847 |
+
"grad_norm": 0.11486474424600601,
|
| 848 |
+
"learning_rate": 9.615240289377002e-06,
|
| 849 |
+
"loss": 0.0062,
|
| 850 |
+
"step": 59500
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.5708039898421342,
|
| 854 |
+
"grad_norm": 0.20883575081825256,
|
| 855 |
+
"learning_rate": 9.527973401052439e-06,
|
| 856 |
+
"loss": 0.0061,
|
| 857 |
+
"step": 60000
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.5838940230908185,
|
| 861 |
+
"grad_norm": 0.15535525977611542,
|
| 862 |
+
"learning_rate": 9.440706512727877e-06,
|
| 863 |
+
"loss": 0.006,
|
| 864 |
+
"step": 60500
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.5969840563395032,
|
| 868 |
+
"grad_norm": 0.2790842652320862,
|
| 869 |
+
"learning_rate": 9.353439624403313e-06,
|
| 870 |
+
"loss": 0.0065,
|
| 871 |
+
"step": 61000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.6100740895881875,
|
| 875 |
+
"grad_norm": 0.338480681180954,
|
| 876 |
+
"learning_rate": 9.266172736078751e-06,
|
| 877 |
+
"loss": 0.0066,
|
| 878 |
+
"step": 61500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.623164122836872,
|
| 882 |
+
"grad_norm": 0.3213784098625183,
|
| 883 |
+
"learning_rate": 9.178905847754187e-06,
|
| 884 |
+
"loss": 0.0064,
|
| 885 |
+
"step": 62000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.6362541560855566,
|
| 889 |
+
"grad_norm": 0.22697031497955322,
|
| 890 |
+
"learning_rate": 9.091638959429623e-06,
|
| 891 |
+
"loss": 0.0066,
|
| 892 |
+
"step": 62500
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.6493441893342409,
|
| 896 |
+
"grad_norm": 0.12834736704826355,
|
| 897 |
+
"learning_rate": 9.004372071105061e-06,
|
| 898 |
+
"loss": 0.0063,
|
| 899 |
+
"step": 63000
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.6624342225829254,
|
| 903 |
+
"grad_norm": 0.08631685376167297,
|
| 904 |
+
"learning_rate": 8.9171051827805e-06,
|
| 905 |
+
"loss": 0.0058,
|
| 906 |
+
"step": 63500
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.67552425583161,
|
| 910 |
+
"grad_norm": 0.12295836955308914,
|
| 911 |
+
"learning_rate": 8.829838294455936e-06,
|
| 912 |
+
"loss": 0.0054,
|
| 913 |
+
"step": 64000
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.6886142890802942,
|
| 917 |
+
"grad_norm": 0.3893487751483917,
|
| 918 |
+
"learning_rate": 8.742571406131372e-06,
|
| 919 |
+
"loss": 0.0062,
|
| 920 |
+
"step": 64500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.7017043223289787,
|
| 924 |
+
"grad_norm": 0.14583726227283478,
|
| 925 |
+
"learning_rate": 8.65530451780681e-06,
|
| 926 |
+
"loss": 0.0063,
|
| 927 |
+
"step": 65000
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.7147943555776632,
|
| 931 |
+
"grad_norm": 0.3584669232368469,
|
| 932 |
+
"learning_rate": 8.568037629482246e-06,
|
| 933 |
+
"loss": 0.0064,
|
| 934 |
+
"step": 65500
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.7278843888263475,
|
| 938 |
+
"grad_norm": 0.05680006742477417,
|
| 939 |
+
"learning_rate": 8.480770741157683e-06,
|
| 940 |
+
"loss": 0.0061,
|
| 941 |
+
"step": 66000
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.740974422075032,
|
| 945 |
+
"grad_norm": 0.15972712635993958,
|
| 946 |
+
"learning_rate": 8.39350385283312e-06,
|
| 947 |
+
"loss": 0.0061,
|
| 948 |
+
"step": 66500
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.7540644553237166,
|
| 952 |
+
"grad_norm": 0.3504839837551117,
|
| 953 |
+
"learning_rate": 8.306236964508557e-06,
|
| 954 |
+
"loss": 0.0056,
|
| 955 |
+
"step": 67000
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.7671544885724009,
|
| 959 |
+
"grad_norm": 0.2058769315481186,
|
| 960 |
+
"learning_rate": 8.218970076183995e-06,
|
| 961 |
+
"loss": 0.0062,
|
| 962 |
+
"step": 67500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.7802445218210854,
|
| 966 |
+
"grad_norm": 0.2028743475675583,
|
| 967 |
+
"learning_rate": 8.131703187859431e-06,
|
| 968 |
+
"loss": 0.0062,
|
| 969 |
+
"step": 68000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.79333455506977,
|
| 973 |
+
"grad_norm": 0.11009418964385986,
|
| 974 |
+
"learning_rate": 8.044436299534868e-06,
|
| 975 |
+
"loss": 0.0062,
|
| 976 |
+
"step": 68500
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.8064245883184542,
|
| 980 |
+
"grad_norm": 0.0618484802544117,
|
| 981 |
+
"learning_rate": 7.957169411210305e-06,
|
| 982 |
+
"loss": 0.0062,
|
| 983 |
+
"step": 69000
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.819514621567139,
|
| 987 |
+
"grad_norm": 0.08521759510040283,
|
| 988 |
+
"learning_rate": 7.869902522885742e-06,
|
| 989 |
+
"loss": 0.0059,
|
| 990 |
+
"step": 69500
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.8326046548158232,
|
| 994 |
+
"grad_norm": 0.3029402196407318,
|
| 995 |
+
"learning_rate": 7.782635634561178e-06,
|
| 996 |
+
"loss": 0.0059,
|
| 997 |
+
"step": 70000
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.8456946880645075,
|
| 1001 |
+
"grad_norm": 0.23642723262310028,
|
| 1002 |
+
"learning_rate": 7.695368746236616e-06,
|
| 1003 |
+
"loss": 0.006,
|
| 1004 |
+
"step": 70500
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.8587847213131923,
|
| 1008 |
+
"grad_norm": 0.14888063073158264,
|
| 1009 |
+
"learning_rate": 7.608101857912053e-06,
|
| 1010 |
+
"loss": 0.006,
|
| 1011 |
+
"step": 71000
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.8718747545618766,
|
| 1015 |
+
"grad_norm": 0.10285039246082306,
|
| 1016 |
+
"learning_rate": 7.52083496958749e-06,
|
| 1017 |
+
"loss": 0.0054,
|
| 1018 |
+
"step": 71500
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.884964787810561,
|
| 1022 |
+
"grad_norm": 0.1975327879190445,
|
| 1023 |
+
"learning_rate": 7.4335680812629275e-06,
|
| 1024 |
+
"loss": 0.0059,
|
| 1025 |
+
"step": 72000
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.8980548210592456,
|
| 1029 |
+
"grad_norm": 0.24295471608638763,
|
| 1030 |
+
"learning_rate": 7.346301192938365e-06,
|
| 1031 |
+
"loss": 0.0058,
|
| 1032 |
+
"step": 72500
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.91114485430793,
|
| 1036 |
+
"grad_norm": 0.03384074568748474,
|
| 1037 |
+
"learning_rate": 7.259034304613801e-06,
|
| 1038 |
+
"loss": 0.0058,
|
| 1039 |
+
"step": 73000
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.9242348875566144,
|
| 1043 |
+
"grad_norm": 0.18082177639007568,
|
| 1044 |
+
"learning_rate": 7.171767416289238e-06,
|
| 1045 |
+
"loss": 0.0058,
|
| 1046 |
+
"step": 73500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.937324920805299,
|
| 1050 |
+
"grad_norm": 0.33321407437324524,
|
| 1051 |
+
"learning_rate": 7.084500527964675e-06,
|
| 1052 |
+
"loss": 0.0057,
|
| 1053 |
+
"step": 74000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.9504149540539832,
|
| 1057 |
+
"grad_norm": 0.0694960206747055,
|
| 1058 |
+
"learning_rate": 6.9972336396401115e-06,
|
| 1059 |
+
"loss": 0.0058,
|
| 1060 |
+
"step": 74500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.9635049873026678,
|
| 1064 |
+
"grad_norm": 0.11903239041566849,
|
| 1065 |
+
"learning_rate": 6.909966751315549e-06,
|
| 1066 |
+
"loss": 0.0057,
|
| 1067 |
+
"step": 75000
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.9765950205513523,
|
| 1071 |
+
"grad_norm": 0.28279566764831543,
|
| 1072 |
+
"learning_rate": 6.822699862990986e-06,
|
| 1073 |
+
"loss": 0.0054,
|
| 1074 |
+
"step": 75500
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.9896850538000366,
|
| 1078 |
+
"grad_norm": 0.12491460144519806,
|
| 1079 |
+
"learning_rate": 6.735432974666423e-06,
|
| 1080 |
+
"loss": 0.0055,
|
| 1081 |
+
"step": 76000
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.0,
|
| 1085 |
+
"eval_loss": 0.0037132962606847286,
|
| 1086 |
+
"eval_runtime": 2298.3508,
|
| 1087 |
+
"eval_samples_per_second": 132.953,
|
| 1088 |
+
"eval_steps_per_second": 16.619,
|
| 1089 |
+
"step": 76394
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 2.0027750870487213,
|
| 1093 |
+
"grad_norm": 0.17459292709827423,
|
| 1094 |
+
"learning_rate": 6.648166086341859e-06,
|
| 1095 |
+
"loss": 0.0053,
|
| 1096 |
+
"step": 76500
|
| 1097 |
+
},
|
| 1098 |
+
{
|
| 1099 |
+
"epoch": 2.0158651202974056,
|
| 1100 |
+
"grad_norm": 0.12316348403692245,
|
| 1101 |
+
"learning_rate": 6.560899198017296e-06,
|
| 1102 |
+
"loss": 0.0048,
|
| 1103 |
+
"step": 77000
|
| 1104 |
+
},
|
| 1105 |
+
{
|
| 1106 |
+
"epoch": 2.02895515354609,
|
| 1107 |
+
"grad_norm": 0.2703343331813812,
|
| 1108 |
+
"learning_rate": 6.4736323096927336e-06,
|
| 1109 |
+
"loss": 0.0052,
|
| 1110 |
+
"step": 77500
|
| 1111 |
+
},
|
| 1112 |
+
{
|
| 1113 |
+
"epoch": 2.0420451867947746,
|
| 1114 |
+
"grad_norm": 0.16996227204799652,
|
| 1115 |
+
"learning_rate": 6.386365421368171e-06,
|
| 1116 |
+
"loss": 0.0051,
|
| 1117 |
+
"step": 78000
|
| 1118 |
+
},
|
| 1119 |
+
{
|
| 1120 |
+
"epoch": 2.055135220043459,
|
| 1121 |
+
"grad_norm": 0.11727280914783478,
|
| 1122 |
+
"learning_rate": 6.299098533043609e-06,
|
| 1123 |
+
"loss": 0.0047,
|
| 1124 |
+
"step": 78500
|
| 1125 |
+
},
|
| 1126 |
+
{
|
| 1127 |
+
"epoch": 2.0682252532921432,
|
| 1128 |
+
"grad_norm": 0.2634254992008209,
|
| 1129 |
+
"learning_rate": 6.211831644719045e-06,
|
| 1130 |
+
"loss": 0.0049,
|
| 1131 |
+
"step": 79000
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 2.081315286540828,
|
| 1135 |
+
"grad_norm": 0.10610348731279373,
|
| 1136 |
+
"learning_rate": 6.124564756394482e-06,
|
| 1137 |
+
"loss": 0.0052,
|
| 1138 |
+
"step": 79500
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 2.0944053197895123,
|
| 1142 |
+
"grad_norm": 0.09022970497608185,
|
| 1143 |
+
"learning_rate": 6.037297868069919e-06,
|
| 1144 |
+
"loss": 0.005,
|
| 1145 |
+
"step": 80000
|
| 1146 |
+
},
|
| 1147 |
+
{
|
| 1148 |
+
"epoch": 2.1074953530381966,
|
| 1149 |
+
"grad_norm": 0.061074189841747284,
|
| 1150 |
+
"learning_rate": 5.9500309797453556e-06,
|
| 1151 |
+
"loss": 0.0049,
|
| 1152 |
+
"step": 80500
|
| 1153 |
+
},
|
| 1154 |
+
{
|
| 1155 |
+
"epoch": 2.1205853862868813,
|
| 1156 |
+
"grad_norm": 0.13339538872241974,
|
| 1157 |
+
"learning_rate": 5.862764091420793e-06,
|
| 1158 |
+
"loss": 0.0047,
|
| 1159 |
+
"step": 81000
|
| 1160 |
+
},
|
| 1161 |
+
{
|
| 1162 |
+
"epoch": 2.1336754195355656,
|
| 1163 |
+
"grad_norm": 0.0852557048201561,
|
| 1164 |
+
"learning_rate": 5.77549720309623e-06,
|
| 1165 |
+
"loss": 0.0051,
|
| 1166 |
+
"step": 81500
|
| 1167 |
+
},
|
| 1168 |
+
{
|
| 1169 |
+
"epoch": 2.14676545278425,
|
| 1170 |
+
"grad_norm": 0.10160050541162491,
|
| 1171 |
+
"learning_rate": 5.688230314771667e-06,
|
| 1172 |
+
"loss": 0.0048,
|
| 1173 |
+
"step": 82000
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 2.1598554860329346,
|
| 1177 |
+
"grad_norm": 0.04886355251073837,
|
| 1178 |
+
"learning_rate": 5.600963426447103e-06,
|
| 1179 |
+
"loss": 0.0048,
|
| 1180 |
+
"step": 82500
|
| 1181 |
+
},
|
| 1182 |
+
{
|
| 1183 |
+
"epoch": 2.172945519281619,
|
| 1184 |
+
"grad_norm": 0.13570809364318848,
|
| 1185 |
+
"learning_rate": 5.5136965381225404e-06,
|
| 1186 |
+
"loss": 0.0048,
|
| 1187 |
+
"step": 83000
|
| 1188 |
+
},
|
| 1189 |
+
{
|
| 1190 |
+
"epoch": 2.1860355525303032,
|
| 1191 |
+
"grad_norm": 0.4608564078807831,
|
| 1192 |
+
"learning_rate": 5.426429649797978e-06,
|
| 1193 |
+
"loss": 0.0047,
|
| 1194 |
+
"step": 83500
|
| 1195 |
+
},
|
| 1196 |
+
{
|
| 1197 |
+
"epoch": 2.199125585778988,
|
| 1198 |
+
"grad_norm": 0.21086885035037994,
|
| 1199 |
+
"learning_rate": 5.339162761473414e-06,
|
| 1200 |
+
"loss": 0.0048,
|
| 1201 |
+
"step": 84000
|
| 1202 |
+
},
|
| 1203 |
+
{
|
| 1204 |
+
"epoch": 2.2122156190276723,
|
| 1205 |
+
"grad_norm": 0.10506796091794968,
|
| 1206 |
+
"learning_rate": 5.251895873148851e-06,
|
| 1207 |
+
"loss": 0.0045,
|
| 1208 |
+
"step": 84500
|
| 1209 |
+
},
|
| 1210 |
+
{
|
| 1211 |
+
"epoch": 2.225305652276357,
|
| 1212 |
+
"grad_norm": 0.11701245605945587,
|
| 1213 |
+
"learning_rate": 5.164628984824288e-06,
|
| 1214 |
+
"loss": 0.0052,
|
| 1215 |
+
"step": 85000
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 2.2383956855250413,
|
| 1219 |
+
"grad_norm": 0.12591439485549927,
|
| 1220 |
+
"learning_rate": 5.077362096499725e-06,
|
| 1221 |
+
"loss": 0.0051,
|
| 1222 |
+
"step": 85500
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 2.2514857187737256,
|
| 1226 |
+
"grad_norm": 0.17858508229255676,
|
| 1227 |
+
"learning_rate": 4.9900952081751625e-06,
|
| 1228 |
+
"loss": 0.0046,
|
| 1229 |
+
"step": 86000
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"epoch": 2.2645757520224103,
|
| 1233 |
+
"grad_norm": 0.1313404142856598,
|
| 1234 |
+
"learning_rate": 4.9028283198506e-06,
|
| 1235 |
+
"loss": 0.0049,
|
| 1236 |
+
"step": 86500
|
| 1237 |
+
},
|
| 1238 |
+
{
|
| 1239 |
+
"epoch": 2.2776657852710946,
|
| 1240 |
+
"grad_norm": 0.017278827726840973,
|
| 1241 |
+
"learning_rate": 4.815561431526036e-06,
|
| 1242 |
+
"loss": 0.0046,
|
| 1243 |
+
"step": 87000
|
| 1244 |
+
},
|
| 1245 |
+
{
|
| 1246 |
+
"epoch": 2.290755818519779,
|
| 1247 |
+
"grad_norm": 0.08634085208177567,
|
| 1248 |
+
"learning_rate": 4.728294543201473e-06,
|
| 1249 |
+
"loss": 0.0047,
|
| 1250 |
+
"step": 87500
|
| 1251 |
+
},
|
| 1252 |
+
{
|
| 1253 |
+
"epoch": 2.3038458517684637,
|
| 1254 |
+
"grad_norm": 0.15097448229789734,
|
| 1255 |
+
"learning_rate": 4.641027654876911e-06,
|
| 1256 |
+
"loss": 0.0049,
|
| 1257 |
+
"step": 88000
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 2.316935885017148,
|
| 1261 |
+
"grad_norm": 0.16411340236663818,
|
| 1262 |
+
"learning_rate": 4.553760766552347e-06,
|
| 1263 |
+
"loss": 0.0048,
|
| 1264 |
+
"step": 88500
|
| 1265 |
+
},
|
| 1266 |
+
{
|
| 1267 |
+
"epoch": 2.3300259182658323,
|
| 1268 |
+
"grad_norm": 0.15543577075004578,
|
| 1269 |
+
"learning_rate": 4.4664938782277845e-06,
|
| 1270 |
+
"loss": 0.0045,
|
| 1271 |
+
"step": 89000
|
| 1272 |
+
},
|
| 1273 |
+
{
|
| 1274 |
+
"epoch": 2.343115951514517,
|
| 1275 |
+
"grad_norm": 0.20463259518146515,
|
| 1276 |
+
"learning_rate": 4.379226989903222e-06,
|
| 1277 |
+
"loss": 0.0045,
|
| 1278 |
+
"step": 89500
|
| 1279 |
+
},
|
| 1280 |
+
{
|
| 1281 |
+
"epoch": 2.3562059847632013,
|
| 1282 |
+
"grad_norm": 0.04198065027594566,
|
| 1283 |
+
"learning_rate": 4.291960101578658e-06,
|
| 1284 |
+
"loss": 0.0046,
|
| 1285 |
+
"step": 90000
|
| 1286 |
+
},
|
| 1287 |
+
{
|
| 1288 |
+
"epoch": 2.3692960180118856,
|
| 1289 |
+
"grad_norm": 0.16238822042942047,
|
| 1290 |
+
"learning_rate": 4.204693213254095e-06,
|
| 1291 |
+
"loss": 0.0045,
|
| 1292 |
+
"step": 90500
|
| 1293 |
+
},
|
| 1294 |
+
{
|
| 1295 |
+
"epoch": 2.3823860512605703,
|
| 1296 |
+
"grad_norm": 0.012462672777473927,
|
| 1297 |
+
"learning_rate": 4.117426324929532e-06,
|
| 1298 |
+
"loss": 0.0051,
|
| 1299 |
+
"step": 91000
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 2.3954760845092546,
|
| 1303 |
+
"grad_norm": 0.015213750302791595,
|
| 1304 |
+
"learning_rate": 4.030159436604969e-06,
|
| 1305 |
+
"loss": 0.0044,
|
| 1306 |
+
"step": 91500
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 2.408566117757939,
|
| 1310 |
+
"grad_norm": 0.040404822677373886,
|
| 1311 |
+
"learning_rate": 3.9428925482804065e-06,
|
| 1312 |
+
"loss": 0.0049,
|
| 1313 |
+
"step": 92000
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 2.4216561510066237,
|
| 1317 |
+
"grad_norm": 0.15160289406776428,
|
| 1318 |
+
"learning_rate": 3.855625659955844e-06,
|
| 1319 |
+
"loss": 0.0049,
|
| 1320 |
+
"step": 92500
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 2.434746184255308,
|
| 1324 |
+
"grad_norm": 0.08896700292825699,
|
| 1325 |
+
"learning_rate": 3.7683587716312804e-06,
|
| 1326 |
+
"loss": 0.0046,
|
| 1327 |
+
"step": 93000
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 2.4478362175039923,
|
| 1331 |
+
"grad_norm": 0.015480602160096169,
|
| 1332 |
+
"learning_rate": 3.681091883306717e-06,
|
| 1333 |
+
"loss": 0.0044,
|
| 1334 |
+
"step": 93500
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 2.460926250752677,
|
| 1338 |
+
"grad_norm": 0.011969960294663906,
|
| 1339 |
+
"learning_rate": 3.5938249949821542e-06,
|
| 1340 |
+
"loss": 0.0054,
|
| 1341 |
+
"step": 94000
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 2.4740162840013613,
|
| 1345 |
+
"grad_norm": 0.11534956097602844,
|
| 1346 |
+
"learning_rate": 3.506558106657591e-06,
|
| 1347 |
+
"loss": 0.0046,
|
| 1348 |
+
"step": 94500
|
| 1349 |
+
},
|
| 1350 |
+
{
|
| 1351 |
+
"epoch": 2.4871063172500456,
|
| 1352 |
+
"grad_norm": 0.2974827289581299,
|
| 1353 |
+
"learning_rate": 3.419291218333028e-06,
|
| 1354 |
+
"loss": 0.0043,
|
| 1355 |
+
"step": 95000
|
| 1356 |
+
},
|
| 1357 |
+
{
|
| 1358 |
+
"epoch": 2.5001963504987303,
|
| 1359 |
+
"grad_norm": 0.22537314891815186,
|
| 1360 |
+
"learning_rate": 3.3320243300084652e-06,
|
| 1361 |
+
"loss": 0.0044,
|
| 1362 |
+
"step": 95500
|
| 1363 |
+
},
|
| 1364 |
+
{
|
| 1365 |
+
"epoch": 2.5132863837474146,
|
| 1366 |
+
"grad_norm": 0.4512380361557007,
|
| 1367 |
+
"learning_rate": 3.2447574416839024e-06,
|
| 1368 |
+
"loss": 0.0041,
|
| 1369 |
+
"step": 96000
|
| 1370 |
+
},
|
| 1371 |
+
{
|
| 1372 |
+
"epoch": 2.526376416996099,
|
| 1373 |
+
"grad_norm": 0.11714764684438705,
|
| 1374 |
+
"learning_rate": 3.157490553359339e-06,
|
| 1375 |
+
"loss": 0.0044,
|
| 1376 |
+
"step": 96500
|
| 1377 |
+
},
|
| 1378 |
+
{
|
| 1379 |
+
"epoch": 2.5394664502447837,
|
| 1380 |
+
"grad_norm": 0.33583053946495056,
|
| 1381 |
+
"learning_rate": 3.0702236650347762e-06,
|
| 1382 |
+
"loss": 0.0046,
|
| 1383 |
+
"step": 97000
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 2.552556483493468,
|
| 1387 |
+
"grad_norm": 0.08749152719974518,
|
| 1388 |
+
"learning_rate": 2.982956776710213e-06,
|
| 1389 |
+
"loss": 0.0046,
|
| 1390 |
+
"step": 97500
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 2.5656465167421523,
|
| 1394 |
+
"grad_norm": 0.213958740234375,
|
| 1395 |
+
"learning_rate": 2.89568988838565e-06,
|
| 1396 |
+
"loss": 0.0042,
|
| 1397 |
+
"step": 98000
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"epoch": 2.578736549990837,
|
| 1401 |
+
"grad_norm": 0.019278518855571747,
|
| 1402 |
+
"learning_rate": 2.808423000061087e-06,
|
| 1403 |
+
"loss": 0.0048,
|
| 1404 |
+
"step": 98500
|
| 1405 |
+
},
|
| 1406 |
+
{
|
| 1407 |
+
"epoch": 2.5918265832395213,
|
| 1408 |
+
"grad_norm": 0.2929363548755646,
|
| 1409 |
+
"learning_rate": 2.7211561117365244e-06,
|
| 1410 |
+
"loss": 0.0041,
|
| 1411 |
+
"step": 99000
|
| 1412 |
+
},
|
| 1413 |
+
{
|
| 1414 |
+
"epoch": 2.6049166164882056,
|
| 1415 |
+
"grad_norm": 0.13888810575008392,
|
| 1416 |
+
"learning_rate": 2.633889223411961e-06,
|
| 1417 |
+
"loss": 0.0043,
|
| 1418 |
+
"step": 99500
|
| 1419 |
+
},
|
| 1420 |
+
{
|
| 1421 |
+
"epoch": 2.6180066497368903,
|
| 1422 |
+
"grad_norm": 0.0986974686384201,
|
| 1423 |
+
"learning_rate": 2.5466223350873983e-06,
|
| 1424 |
+
"loss": 0.0046,
|
| 1425 |
+
"step": 100000
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 2.6310966829855746,
|
| 1429 |
+
"grad_norm": 0.3214912712574005,
|
| 1430 |
+
"learning_rate": 2.459355446762835e-06,
|
| 1431 |
+
"loss": 0.0047,
|
| 1432 |
+
"step": 100500
|
| 1433 |
+
},
|
| 1434 |
+
{
|
| 1435 |
+
"epoch": 2.6441867162342594,
|
| 1436 |
+
"grad_norm": 0.0012846454046666622,
|
| 1437 |
+
"learning_rate": 2.3720885584382717e-06,
|
| 1438 |
+
"loss": 0.0045,
|
| 1439 |
+
"step": 101000
|
| 1440 |
+
},
|
| 1441 |
+
{
|
| 1442 |
+
"epoch": 2.6572767494829437,
|
| 1443 |
+
"grad_norm": 0.3178112506866455,
|
| 1444 |
+
"learning_rate": 2.284821670113709e-06,
|
| 1445 |
+
"loss": 0.0045,
|
| 1446 |
+
"step": 101500
|
| 1447 |
+
},
|
| 1448 |
+
{
|
| 1449 |
+
"epoch": 2.670366782731628,
|
| 1450 |
+
"grad_norm": 0.26486077904701233,
|
| 1451 |
+
"learning_rate": 2.197554781789146e-06,
|
| 1452 |
+
"loss": 0.0043,
|
| 1453 |
+
"step": 102000
|
| 1454 |
+
},
|
| 1455 |
+
{
|
| 1456 |
+
"epoch": 2.6834568159803127,
|
| 1457 |
+
"grad_norm": 0.1955183446407318,
|
| 1458 |
+
"learning_rate": 2.1102878934645827e-06,
|
| 1459 |
+
"loss": 0.0043,
|
| 1460 |
+
"step": 102500
|
| 1461 |
+
},
|
| 1462 |
+
{
|
| 1463 |
+
"epoch": 2.696546849228997,
|
| 1464 |
+
"grad_norm": 0.27978459000587463,
|
| 1465 |
+
"learning_rate": 2.02302100514002e-06,
|
| 1466 |
+
"loss": 0.0043,
|
| 1467 |
+
"step": 103000
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 2.7096368824776818,
|
| 1471 |
+
"grad_norm": 0.16327758133411407,
|
| 1472 |
+
"learning_rate": 1.935754116815457e-06,
|
| 1473 |
+
"loss": 0.0044,
|
| 1474 |
+
"step": 103500
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 2.722726915726366,
|
| 1478 |
+
"grad_norm": 0.11214172095060349,
|
| 1479 |
+
"learning_rate": 1.848487228490894e-06,
|
| 1480 |
+
"loss": 0.0044,
|
| 1481 |
+
"step": 104000
|
| 1482 |
+
},
|
| 1483 |
+
{
|
| 1484 |
+
"epoch": 2.7358169489750503,
|
| 1485 |
+
"grad_norm": 0.270905077457428,
|
| 1486 |
+
"learning_rate": 1.7612203401663309e-06,
|
| 1487 |
+
"loss": 0.0046,
|
| 1488 |
+
"step": 104500
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"epoch": 2.748906982223735,
|
| 1492 |
+
"grad_norm": 0.14749902486801147,
|
| 1493 |
+
"learning_rate": 1.6739534518417678e-06,
|
| 1494 |
+
"loss": 0.0046,
|
| 1495 |
+
"step": 105000
|
| 1496 |
+
},
|
| 1497 |
+
{
|
| 1498 |
+
"epoch": 2.7619970154724194,
|
| 1499 |
+
"grad_norm": 0.058535072952508926,
|
| 1500 |
+
"learning_rate": 1.586686563517205e-06,
|
| 1501 |
+
"loss": 0.0043,
|
| 1502 |
+
"step": 105500
|
| 1503 |
+
},
|
| 1504 |
+
{
|
| 1505 |
+
"epoch": 2.7750870487211037,
|
| 1506 |
+
"grad_norm": 0.03967679664492607,
|
| 1507 |
+
"learning_rate": 1.4994196751926419e-06,
|
| 1508 |
+
"loss": 0.0043,
|
| 1509 |
+
"step": 106000
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 2.7881770819697884,
|
| 1513 |
+
"grad_norm": 0.22382740676403046,
|
| 1514 |
+
"learning_rate": 1.4121527868680788e-06,
|
| 1515 |
+
"loss": 0.0044,
|
| 1516 |
+
"step": 106500
|
| 1517 |
+
},
|
| 1518 |
+
{
|
| 1519 |
+
"epoch": 2.8012671152184727,
|
| 1520 |
+
"grad_norm": 0.19118061661720276,
|
| 1521 |
+
"learning_rate": 1.3248858985435155e-06,
|
| 1522 |
+
"loss": 0.004,
|
| 1523 |
+
"step": 107000
|
| 1524 |
+
},
|
| 1525 |
+
{
|
| 1526 |
+
"epoch": 2.814357148467157,
|
| 1527 |
+
"grad_norm": 0.18843971192836761,
|
| 1528 |
+
"learning_rate": 1.2376190102189527e-06,
|
| 1529 |
+
"loss": 0.0043,
|
| 1530 |
+
"step": 107500
|
| 1531 |
+
},
|
| 1532 |
+
{
|
| 1533 |
+
"epoch": 2.8274471817158418,
|
| 1534 |
+
"grad_norm": 0.22385017573833466,
|
| 1535 |
+
"learning_rate": 1.1503521218943898e-06,
|
| 1536 |
+
"loss": 0.0044,
|
| 1537 |
+
"step": 108000
|
| 1538 |
+
},
|
| 1539 |
+
{
|
| 1540 |
+
"epoch": 2.840537214964526,
|
| 1541 |
+
"grad_norm": 0.0888708084821701,
|
| 1542 |
+
"learning_rate": 1.0630852335698265e-06,
|
| 1543 |
+
"loss": 0.0045,
|
| 1544 |
+
"step": 108500
|
| 1545 |
+
},
|
| 1546 |
+
{
|
| 1547 |
+
"epoch": 2.8536272482132103,
|
| 1548 |
+
"grad_norm": 0.0975847914814949,
|
| 1549 |
+
"learning_rate": 9.758183452452637e-07,
|
| 1550 |
+
"loss": 0.0047,
|
| 1551 |
+
"step": 109000
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 2.866717281461895,
|
| 1555 |
+
"grad_norm": 0.09466837346553802,
|
| 1556 |
+
"learning_rate": 8.885514569207007e-07,
|
| 1557 |
+
"loss": 0.0046,
|
| 1558 |
+
"step": 109500
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 2.8798073147105794,
|
| 1562 |
+
"grad_norm": 0.18789631128311157,
|
| 1563 |
+
"learning_rate": 8.012845685961376e-07,
|
| 1564 |
+
"loss": 0.0044,
|
| 1565 |
+
"step": 110000
|
| 1566 |
+
},
|
| 1567 |
+
{
|
| 1568 |
+
"epoch": 2.8928973479592637,
|
| 1569 |
+
"grad_norm": 0.12237800657749176,
|
| 1570 |
+
"learning_rate": 7.140176802715747e-07,
|
| 1571 |
+
"loss": 0.004,
|
| 1572 |
+
"step": 110500
|
| 1573 |
+
},
|
| 1574 |
+
{
|
| 1575 |
+
"epoch": 2.9059873812079484,
|
| 1576 |
+
"grad_norm": 0.13793490827083588,
|
| 1577 |
+
"learning_rate": 6.267507919470116e-07,
|
| 1578 |
+
"loss": 0.0046,
|
| 1579 |
+
"step": 111000
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"epoch": 2.9190774144566327,
|
| 1583 |
+
"grad_norm": 0.1080477237701416,
|
| 1584 |
+
"learning_rate": 5.394839036224485e-07,
|
| 1585 |
+
"loss": 0.0041,
|
| 1586 |
+
"step": 111500
|
| 1587 |
+
},
|
| 1588 |
+
{
|
| 1589 |
+
"epoch": 2.932167447705317,
|
| 1590 |
+
"grad_norm": 0.20041316747665405,
|
| 1591 |
+
"learning_rate": 4.5221701529788553e-07,
|
| 1592 |
+
"loss": 0.0043,
|
| 1593 |
+
"step": 112000
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 2.9452574809540017,
|
| 1597 |
+
"grad_norm": 0.3370501399040222,
|
| 1598 |
+
"learning_rate": 3.649501269733225e-07,
|
| 1599 |
+
"loss": 0.0045,
|
| 1600 |
+
"step": 112500
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 2.958347514202686,
|
| 1604 |
+
"grad_norm": 0.011929438449442387,
|
| 1605 |
+
"learning_rate": 2.776832386487595e-07,
|
| 1606 |
+
"loss": 0.0042,
|
| 1607 |
+
"step": 113000
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 2.9714375474513703,
|
| 1611 |
+
"grad_norm": 0.3616108000278473,
|
| 1612 |
+
"learning_rate": 1.904163503241965e-07,
|
| 1613 |
+
"loss": 0.0042,
|
| 1614 |
+
"step": 113500
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 2.984527580700055,
|
| 1618 |
+
"grad_norm": 0.04300173744559288,
|
| 1619 |
+
"learning_rate": 1.0314946199963349e-07,
|
| 1620 |
+
"loss": 0.0046,
|
| 1621 |
+
"step": 114000
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 2.9976176139487394,
|
| 1625 |
+
"grad_norm": 0.2760555148124695,
|
| 1626 |
+
"learning_rate": 1.588257367507047e-08,
|
| 1627 |
+
"loss": 0.0043,
|
| 1628 |
+
"step": 114500
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 3.0,
|
| 1632 |
+
"eval_loss": 0.002946872031316161,
|
| 1633 |
+
"eval_runtime": 2297.682,
|
| 1634 |
+
"eval_samples_per_second": 132.992,
|
| 1635 |
+
"eval_steps_per_second": 16.624,
|
| 1636 |
+
"step": 114591
|
| 1637 |
+
}
|
| 1638 |
+
],
|
| 1639 |
+
"logging_steps": 500,
|
| 1640 |
+
"max_steps": 114591,
|
| 1641 |
+
"num_input_tokens_seen": 0,
|
| 1642 |
+
"num_train_epochs": 3,
|
| 1643 |
+
"save_steps": 500,
|
| 1644 |
+
"stateful_callbacks": {
|
| 1645 |
+
"TrainerControl": {
|
| 1646 |
+
"args": {
|
| 1647 |
+
"should_epoch_stop": false,
|
| 1648 |
+
"should_evaluate": false,
|
| 1649 |
+
"should_log": false,
|
| 1650 |
+
"should_save": true,
|
| 1651 |
+
"should_training_stop": true
|
| 1652 |
+
},
|
| 1653 |
+
"attributes": {}
|
| 1654 |
+
}
|
| 1655 |
+
},
|
| 1656 |
+
"total_flos": 6.986962453266432e+16,
|
| 1657 |
+
"train_batch_size": 8,
|
| 1658 |
+
"trial_name": null,
|
| 1659 |
+
"trial_params": null
|
| 1660 |
+
}
|
checkpoint-114591/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d54a045f207a6e96a5980be3103fb572390bb8f4d93e00dba90dcfdee06f7fd
|
| 3 |
+
size 5304
|
checkpoint-114591/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-38197/config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": null,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_eos_token_id": 2,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_position_embeddings": 1024,
|
| 42 |
+
"model_type": "bart",
|
| 43 |
+
"no_repeat_ngram_size": null,
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"normalize_embedding": true,
|
| 46 |
+
"num_beams": null,
|
| 47 |
+
"num_hidden_layers": 6,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"scale_embedding": false,
|
| 50 |
+
"task_specific_params": {
|
| 51 |
+
"summarization": {
|
| 52 |
+
"length_penalty": 1.0,
|
| 53 |
+
"max_length": 128,
|
| 54 |
+
"min_length": 12,
|
| 55 |
+
"num_beams": 4
|
| 56 |
+
},
|
| 57 |
+
"summarization_cnn": {
|
| 58 |
+
"length_penalty": 2.0,
|
| 59 |
+
"max_length": 142,
|
| 60 |
+
"min_length": 56,
|
| 61 |
+
"num_beams": 4
|
| 62 |
+
},
|
| 63 |
+
"summarization_xsum": {
|
| 64 |
+
"length_penalty": 1.0,
|
| 65 |
+
"max_length": 62,
|
| 66 |
+
"min_length": 11,
|
| 67 |
+
"num_beams": 6
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"torch_dtype": "float32",
|
| 71 |
+
"transformers_version": "4.48.3",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"vocab_size": 50265
|
| 74 |
+
}
|
checkpoint-38197/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.48.3"
|
| 13 |
+
}
|
checkpoint-38197/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-38197/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78665e85ebbabcf97bf5c82234afaeb40ebd2db0e728846f8e27e0fc99fe17a5
|
| 3 |
+
size 557912620
|
checkpoint-38197/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4cc1e85195064d8eb5eba375ada0319e199afa3e44122d80a2da673366248169
|
| 3 |
+
size 1115579898
|
checkpoint-38197/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84acd42a1baa290f13b1cff21e117e3702e11769079efb404c2a462abb37da4c
|
| 3 |
+
size 14244
|
checkpoint-38197/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12b02c3ed83c2198c5d2e06f8afead79a647865ea859dd4a8a322ac3b9bfcc83
|
| 3 |
+
size 1064
|
checkpoint-38197/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
checkpoint-38197/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-38197/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "BartTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-38197/trainer_state.json
ADDED
|
@@ -0,0 +1,573 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 38197,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.013090033248684452,
|
| 13 |
+
"grad_norm": 0.4367656707763672,
|
| 14 |
+
"learning_rate": 1.991273311167544e-05,
|
| 15 |
+
"loss": 1.32,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.026180066497368905,
|
| 20 |
+
"grad_norm": 0.39482298493385315,
|
| 21 |
+
"learning_rate": 1.9825466223350874e-05,
|
| 22 |
+
"loss": 0.0594,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.039270099746053354,
|
| 27 |
+
"grad_norm": 0.47824403643608093,
|
| 28 |
+
"learning_rate": 1.9738199335026312e-05,
|
| 29 |
+
"loss": 0.0497,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05236013299473781,
|
| 34 |
+
"grad_norm": 0.3971627652645111,
|
| 35 |
+
"learning_rate": 1.965093244670175e-05,
|
| 36 |
+
"loss": 0.043,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06545016624342226,
|
| 41 |
+
"grad_norm": 0.5000212788581848,
|
| 42 |
+
"learning_rate": 1.9563665558377188e-05,
|
| 43 |
+
"loss": 0.0374,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07854019949210671,
|
| 48 |
+
"grad_norm": 0.9078471064567566,
|
| 49 |
+
"learning_rate": 1.9476398670052623e-05,
|
| 50 |
+
"loss": 0.0357,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09163023274079116,
|
| 55 |
+
"grad_norm": 0.35205739736557007,
|
| 56 |
+
"learning_rate": 1.938913178172806e-05,
|
| 57 |
+
"loss": 0.0317,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.10472026598947562,
|
| 62 |
+
"grad_norm": 0.19642357528209686,
|
| 63 |
+
"learning_rate": 1.9301864893403495e-05,
|
| 64 |
+
"loss": 0.0304,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.11781029923816007,
|
| 69 |
+
"grad_norm": 0.5134682655334473,
|
| 70 |
+
"learning_rate": 1.9214598005078933e-05,
|
| 71 |
+
"loss": 0.0281,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.13090033248684452,
|
| 76 |
+
"grad_norm": 0.23212824761867523,
|
| 77 |
+
"learning_rate": 1.912733111675437e-05,
|
| 78 |
+
"loss": 0.0274,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.14399036573552898,
|
| 83 |
+
"grad_norm": 0.4254980981349945,
|
| 84 |
+
"learning_rate": 1.904006422842981e-05,
|
| 85 |
+
"loss": 0.0247,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.15708039898421342,
|
| 90 |
+
"grad_norm": 0.4024842083454132,
|
| 91 |
+
"learning_rate": 1.8952797340105244e-05,
|
| 92 |
+
"loss": 0.0235,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.17017043223289788,
|
| 97 |
+
"grad_norm": 0.40947026014328003,
|
| 98 |
+
"learning_rate": 1.8865530451780682e-05,
|
| 99 |
+
"loss": 0.0235,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1832604654815823,
|
| 104 |
+
"grad_norm": 0.366158127784729,
|
| 105 |
+
"learning_rate": 1.877826356345612e-05,
|
| 106 |
+
"loss": 0.0225,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.19635049873026678,
|
| 111 |
+
"grad_norm": 0.4678824841976166,
|
| 112 |
+
"learning_rate": 1.8690996675131558e-05,
|
| 113 |
+
"loss": 0.0219,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.20944053197895124,
|
| 118 |
+
"grad_norm": 0.21004918217658997,
|
| 119 |
+
"learning_rate": 1.8603729786806996e-05,
|
| 120 |
+
"loss": 0.0198,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.22253056522763567,
|
| 125 |
+
"grad_norm": 0.2192375510931015,
|
| 126 |
+
"learning_rate": 1.851646289848243e-05,
|
| 127 |
+
"loss": 0.0201,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.23562059847632014,
|
| 132 |
+
"grad_norm": 0.15161575376987457,
|
| 133 |
+
"learning_rate": 1.842919601015787e-05,
|
| 134 |
+
"loss": 0.0192,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.24871063172500457,
|
| 139 |
+
"grad_norm": 0.3270639181137085,
|
| 140 |
+
"learning_rate": 1.8341929121833303e-05,
|
| 141 |
+
"loss": 0.0186,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.26180066497368903,
|
| 146 |
+
"grad_norm": 0.25447696447372437,
|
| 147 |
+
"learning_rate": 1.825466223350874e-05,
|
| 148 |
+
"loss": 0.0182,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2748906982223735,
|
| 153 |
+
"grad_norm": 0.1797029674053192,
|
| 154 |
+
"learning_rate": 1.816739534518418e-05,
|
| 155 |
+
"loss": 0.0182,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.28798073147105796,
|
| 160 |
+
"grad_norm": 0.4422529637813568,
|
| 161 |
+
"learning_rate": 1.8080128456859617e-05,
|
| 162 |
+
"loss": 0.0175,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.30107076471974237,
|
| 167 |
+
"grad_norm": 0.19019261002540588,
|
| 168 |
+
"learning_rate": 1.7992861568535052e-05,
|
| 169 |
+
"loss": 0.0159,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.31416079796842683,
|
| 174 |
+
"grad_norm": 0.12262561917304993,
|
| 175 |
+
"learning_rate": 1.790559468021049e-05,
|
| 176 |
+
"loss": 0.0162,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3272508312171113,
|
| 181 |
+
"grad_norm": 0.5514086484909058,
|
| 182 |
+
"learning_rate": 1.7818327791885924e-05,
|
| 183 |
+
"loss": 0.0159,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.34034086446579576,
|
| 188 |
+
"grad_norm": 0.3397659957408905,
|
| 189 |
+
"learning_rate": 1.7731060903561362e-05,
|
| 190 |
+
"loss": 0.0163,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.3534308977144802,
|
| 195 |
+
"grad_norm": 0.3542526364326477,
|
| 196 |
+
"learning_rate": 1.76437940152368e-05,
|
| 197 |
+
"loss": 0.0161,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3665209309631646,
|
| 202 |
+
"grad_norm": 0.22688041627407074,
|
| 203 |
+
"learning_rate": 1.7556527126912238e-05,
|
| 204 |
+
"loss": 0.0155,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3796109642118491,
|
| 209 |
+
"grad_norm": 0.20115447044372559,
|
| 210 |
+
"learning_rate": 1.7469260238587673e-05,
|
| 211 |
+
"loss": 0.0148,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.39270099746053355,
|
| 216 |
+
"grad_norm": 0.09773228317499161,
|
| 217 |
+
"learning_rate": 1.738199335026311e-05,
|
| 218 |
+
"loss": 0.0149,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.405791030709218,
|
| 223 |
+
"grad_norm": 0.41297146677970886,
|
| 224 |
+
"learning_rate": 1.729472646193855e-05,
|
| 225 |
+
"loss": 0.0146,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4188810639579025,
|
| 230 |
+
"grad_norm": 0.6495208740234375,
|
| 231 |
+
"learning_rate": 1.7207459573613983e-05,
|
| 232 |
+
"loss": 0.0136,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4319710972065869,
|
| 237 |
+
"grad_norm": 0.35930490493774414,
|
| 238 |
+
"learning_rate": 1.712019268528942e-05,
|
| 239 |
+
"loss": 0.0137,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.44506113045527135,
|
| 244 |
+
"grad_norm": 0.22953346371650696,
|
| 245 |
+
"learning_rate": 1.703292579696486e-05,
|
| 246 |
+
"loss": 0.0139,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4581511637039558,
|
| 251 |
+
"grad_norm": 0.41518378257751465,
|
| 252 |
+
"learning_rate": 1.6945658908640297e-05,
|
| 253 |
+
"loss": 0.0135,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4712411969526403,
|
| 258 |
+
"grad_norm": 0.2171572744846344,
|
| 259 |
+
"learning_rate": 1.6858392020315732e-05,
|
| 260 |
+
"loss": 0.0129,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.48433123020132474,
|
| 265 |
+
"grad_norm": 0.2897777557373047,
|
| 266 |
+
"learning_rate": 1.677112513199117e-05,
|
| 267 |
+
"loss": 0.0122,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.49742126345000914,
|
| 272 |
+
"grad_norm": 0.4209305942058563,
|
| 273 |
+
"learning_rate": 1.6683858243666608e-05,
|
| 274 |
+
"loss": 0.0128,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5105112966986937,
|
| 279 |
+
"grad_norm": 0.08220311999320984,
|
| 280 |
+
"learning_rate": 1.6596591355342046e-05,
|
| 281 |
+
"loss": 0.0123,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5236013299473781,
|
| 286 |
+
"grad_norm": 0.09847331047058105,
|
| 287 |
+
"learning_rate": 1.650932446701748e-05,
|
| 288 |
+
"loss": 0.0123,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5366913631960625,
|
| 293 |
+
"grad_norm": 0.41798558831214905,
|
| 294 |
+
"learning_rate": 1.642205757869292e-05,
|
| 295 |
+
"loss": 0.0128,
|
| 296 |
+
"step": 20500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.549781396444747,
|
| 300 |
+
"grad_norm": 0.2177186757326126,
|
| 301 |
+
"learning_rate": 1.6334790690368353e-05,
|
| 302 |
+
"loss": 0.0124,
|
| 303 |
+
"step": 21000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5628714296934314,
|
| 307 |
+
"grad_norm": 0.16467055678367615,
|
| 308 |
+
"learning_rate": 1.624752380204379e-05,
|
| 309 |
+
"loss": 0.0118,
|
| 310 |
+
"step": 21500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5759614629421159,
|
| 314 |
+
"grad_norm": 0.3392176330089569,
|
| 315 |
+
"learning_rate": 1.616025691371923e-05,
|
| 316 |
+
"loss": 0.0121,
|
| 317 |
+
"step": 22000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5890514961908003,
|
| 321 |
+
"grad_norm": 0.14208835363388062,
|
| 322 |
+
"learning_rate": 1.6072990025394667e-05,
|
| 323 |
+
"loss": 0.0118,
|
| 324 |
+
"step": 22500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6021415294394847,
|
| 328 |
+
"grad_norm": 0.18248602747917175,
|
| 329 |
+
"learning_rate": 1.5985723137070105e-05,
|
| 330 |
+
"loss": 0.0118,
|
| 331 |
+
"step": 23000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6152315626881693,
|
| 335 |
+
"grad_norm": 0.32215237617492676,
|
| 336 |
+
"learning_rate": 1.589845624874554e-05,
|
| 337 |
+
"loss": 0.0111,
|
| 338 |
+
"step": 23500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6283215959368537,
|
| 342 |
+
"grad_norm": 0.35770946741104126,
|
| 343 |
+
"learning_rate": 1.5811189360420978e-05,
|
| 344 |
+
"loss": 0.0111,
|
| 345 |
+
"step": 24000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6414116291855382,
|
| 349 |
+
"grad_norm": 0.21091119945049286,
|
| 350 |
+
"learning_rate": 1.5723922472096412e-05,
|
| 351 |
+
"loss": 0.0115,
|
| 352 |
+
"step": 24500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6545016624342226,
|
| 356 |
+
"grad_norm": 0.215097576379776,
|
| 357 |
+
"learning_rate": 1.563665558377185e-05,
|
| 358 |
+
"loss": 0.0107,
|
| 359 |
+
"step": 25000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.667591695682907,
|
| 363 |
+
"grad_norm": 0.15477751195430756,
|
| 364 |
+
"learning_rate": 1.554938869544729e-05,
|
| 365 |
+
"loss": 0.0105,
|
| 366 |
+
"step": 25500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.6806817289315915,
|
| 370 |
+
"grad_norm": 0.1576426774263382,
|
| 371 |
+
"learning_rate": 1.5462121807122726e-05,
|
| 372 |
+
"loss": 0.0105,
|
| 373 |
+
"step": 26000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6937717621802759,
|
| 377 |
+
"grad_norm": 0.19675689935684204,
|
| 378 |
+
"learning_rate": 1.537485491879816e-05,
|
| 379 |
+
"loss": 0.0096,
|
| 380 |
+
"step": 26500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.7068617954289604,
|
| 384 |
+
"grad_norm": 0.480955570936203,
|
| 385 |
+
"learning_rate": 1.52875880304736e-05,
|
| 386 |
+
"loss": 0.0104,
|
| 387 |
+
"step": 27000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7199518286776448,
|
| 391 |
+
"grad_norm": 0.2651515603065491,
|
| 392 |
+
"learning_rate": 1.5200321142149035e-05,
|
| 393 |
+
"loss": 0.0106,
|
| 394 |
+
"step": 27500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7330418619263293,
|
| 398 |
+
"grad_norm": 0.21407313644886017,
|
| 399 |
+
"learning_rate": 1.5113054253824473e-05,
|
| 400 |
+
"loss": 0.0102,
|
| 401 |
+
"step": 28000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.7461318951750138,
|
| 405 |
+
"grad_norm": 0.13915963470935822,
|
| 406 |
+
"learning_rate": 1.502578736549991e-05,
|
| 407 |
+
"loss": 0.0098,
|
| 408 |
+
"step": 28500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7592219284236982,
|
| 412 |
+
"grad_norm": 0.09625498950481415,
|
| 413 |
+
"learning_rate": 1.4938520477175348e-05,
|
| 414 |
+
"loss": 0.0099,
|
| 415 |
+
"step": 29000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7723119616723827,
|
| 419 |
+
"grad_norm": 0.26766207814216614,
|
| 420 |
+
"learning_rate": 1.4851253588850782e-05,
|
| 421 |
+
"loss": 0.01,
|
| 422 |
+
"step": 29500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7854019949210671,
|
| 426 |
+
"grad_norm": 0.03729819133877754,
|
| 427 |
+
"learning_rate": 1.476398670052622e-05,
|
| 428 |
+
"loss": 0.0092,
|
| 429 |
+
"step": 30000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7984920281697515,
|
| 433 |
+
"grad_norm": 0.19327211380004883,
|
| 434 |
+
"learning_rate": 1.4676719812201658e-05,
|
| 435 |
+
"loss": 0.0094,
|
| 436 |
+
"step": 30500
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.811582061418436,
|
| 440 |
+
"grad_norm": 0.27896180748939514,
|
| 441 |
+
"learning_rate": 1.4589452923877094e-05,
|
| 442 |
+
"loss": 0.01,
|
| 443 |
+
"step": 31000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.8246720946671204,
|
| 447 |
+
"grad_norm": 0.1490613967180252,
|
| 448 |
+
"learning_rate": 1.4502186035552532e-05,
|
| 449 |
+
"loss": 0.0092,
|
| 450 |
+
"step": 31500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.837762127915805,
|
| 454 |
+
"grad_norm": 0.22722095251083374,
|
| 455 |
+
"learning_rate": 1.4414919147227969e-05,
|
| 456 |
+
"loss": 0.0093,
|
| 457 |
+
"step": 32000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.8508521611644894,
|
| 461 |
+
"grad_norm": 0.2942313849925995,
|
| 462 |
+
"learning_rate": 1.4327652258903407e-05,
|
| 463 |
+
"loss": 0.0098,
|
| 464 |
+
"step": 32500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8639421944131738,
|
| 468 |
+
"grad_norm": 0.37654176354408264,
|
| 469 |
+
"learning_rate": 1.4240385370578841e-05,
|
| 470 |
+
"loss": 0.0095,
|
| 471 |
+
"step": 33000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8770322276618583,
|
| 475 |
+
"grad_norm": 0.21543939411640167,
|
| 476 |
+
"learning_rate": 1.415311848225428e-05,
|
| 477 |
+
"loss": 0.0097,
|
| 478 |
+
"step": 33500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8901222609105427,
|
| 482 |
+
"grad_norm": 0.4608267843723297,
|
| 483 |
+
"learning_rate": 1.4065851593929716e-05,
|
| 484 |
+
"loss": 0.0093,
|
| 485 |
+
"step": 34000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.9032122941592272,
|
| 489 |
+
"grad_norm": 0.1784515380859375,
|
| 490 |
+
"learning_rate": 1.3978584705605154e-05,
|
| 491 |
+
"loss": 0.009,
|
| 492 |
+
"step": 34500
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.9163023274079116,
|
| 496 |
+
"grad_norm": 0.3353884518146515,
|
| 497 |
+
"learning_rate": 1.389131781728059e-05,
|
| 498 |
+
"loss": 0.009,
|
| 499 |
+
"step": 35000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.929392360656596,
|
| 503 |
+
"grad_norm": 0.2330337017774582,
|
| 504 |
+
"learning_rate": 1.3804050928956028e-05,
|
| 505 |
+
"loss": 0.009,
|
| 506 |
+
"step": 35500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.9424823939052805,
|
| 510 |
+
"grad_norm": 0.32975077629089355,
|
| 511 |
+
"learning_rate": 1.3716784040631464e-05,
|
| 512 |
+
"loss": 0.0092,
|
| 513 |
+
"step": 36000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.955572427153965,
|
| 517 |
+
"grad_norm": 0.03280099481344223,
|
| 518 |
+
"learning_rate": 1.3629517152306902e-05,
|
| 519 |
+
"loss": 0.0084,
|
| 520 |
+
"step": 36500
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.9686624604026495,
|
| 524 |
+
"grad_norm": 0.22344884276390076,
|
| 525 |
+
"learning_rate": 1.3542250263982337e-05,
|
| 526 |
+
"loss": 0.0089,
|
| 527 |
+
"step": 37000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.9817524936513339,
|
| 531 |
+
"grad_norm": 0.361147403717041,
|
| 532 |
+
"learning_rate": 1.3454983375657775e-05,
|
| 533 |
+
"loss": 0.0084,
|
| 534 |
+
"step": 37500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.9948425269000183,
|
| 538 |
+
"grad_norm": 0.2099611908197403,
|
| 539 |
+
"learning_rate": 1.3367716487333213e-05,
|
| 540 |
+
"loss": 0.0088,
|
| 541 |
+
"step": 38000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.0,
|
| 545 |
+
"eval_loss": 0.005731215700507164,
|
| 546 |
+
"eval_runtime": 2297.4971,
|
| 547 |
+
"eval_samples_per_second": 133.003,
|
| 548 |
+
"eval_steps_per_second": 16.625,
|
| 549 |
+
"step": 38197
|
| 550 |
+
}
|
| 551 |
+
],
|
| 552 |
+
"logging_steps": 500,
|
| 553 |
+
"max_steps": 114591,
|
| 554 |
+
"num_input_tokens_seen": 0,
|
| 555 |
+
"num_train_epochs": 3,
|
| 556 |
+
"save_steps": 500,
|
| 557 |
+
"stateful_callbacks": {
|
| 558 |
+
"TrainerControl": {
|
| 559 |
+
"args": {
|
| 560 |
+
"should_epoch_stop": false,
|
| 561 |
+
"should_evaluate": false,
|
| 562 |
+
"should_log": false,
|
| 563 |
+
"should_save": true,
|
| 564 |
+
"should_training_stop": false
|
| 565 |
+
},
|
| 566 |
+
"attributes": {}
|
| 567 |
+
}
|
| 568 |
+
},
|
| 569 |
+
"total_flos": 2.328987484422144e+16,
|
| 570 |
+
"train_batch_size": 8,
|
| 571 |
+
"trial_name": null,
|
| 572 |
+
"trial_params": null
|
| 573 |
+
}
|
checkpoint-38197/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d54a045f207a6e96a5980be3103fb572390bb8f4d93e00dba90dcfdee06f7fd
|
| 3 |
+
size 5304
|
checkpoint-38197/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-76394/config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": null,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_eos_token_id": 2,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_position_embeddings": 1024,
|
| 42 |
+
"model_type": "bart",
|
| 43 |
+
"no_repeat_ngram_size": null,
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"normalize_embedding": true,
|
| 46 |
+
"num_beams": null,
|
| 47 |
+
"num_hidden_layers": 6,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"scale_embedding": false,
|
| 50 |
+
"task_specific_params": {
|
| 51 |
+
"summarization": {
|
| 52 |
+
"length_penalty": 1.0,
|
| 53 |
+
"max_length": 128,
|
| 54 |
+
"min_length": 12,
|
| 55 |
+
"num_beams": 4
|
| 56 |
+
},
|
| 57 |
+
"summarization_cnn": {
|
| 58 |
+
"length_penalty": 2.0,
|
| 59 |
+
"max_length": 142,
|
| 60 |
+
"min_length": 56,
|
| 61 |
+
"num_beams": 4
|
| 62 |
+
},
|
| 63 |
+
"summarization_xsum": {
|
| 64 |
+
"length_penalty": 1.0,
|
| 65 |
+
"max_length": 62,
|
| 66 |
+
"min_length": 11,
|
| 67 |
+
"num_beams": 6
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"torch_dtype": "float32",
|
| 71 |
+
"transformers_version": "4.48.3",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"vocab_size": 50265
|
| 74 |
+
}
|
checkpoint-76394/generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.48.3"
|
| 13 |
+
}
|
checkpoint-76394/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-76394/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:793dbfa40185cab7e2924281e00d9209c1b7dd78d1ddd916d391080c3e3edbae
|
| 3 |
+
size 557912620
|
checkpoint-76394/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10c17bc00685a1d6b9c97380e8acebf28bbf0acb6ab84c03eea83bc1f70e8498
|
| 3 |
+
size 1115579898
|
checkpoint-76394/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d74520de4fe8efbfea460bce1bab09e3b20f7bdf32e06342fb436a807aa6b28
|
| 3 |
+
size 14244
|
checkpoint-76394/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bea8ceb4f3d941608428a128a9f4982f007e23816e2844418fa71ddb273fc8d1
|
| 3 |
+
size 1064
|
checkpoint-76394/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
checkpoint-76394/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-76394/tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "BartTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
checkpoint-76394/trainer_state.json
ADDED
|
@@ -0,0 +1,1113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 76394,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.013090033248684452,
|
| 13 |
+
"grad_norm": 0.4367656707763672,
|
| 14 |
+
"learning_rate": 1.991273311167544e-05,
|
| 15 |
+
"loss": 1.32,
|
| 16 |
+
"step": 500
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.026180066497368905,
|
| 20 |
+
"grad_norm": 0.39482298493385315,
|
| 21 |
+
"learning_rate": 1.9825466223350874e-05,
|
| 22 |
+
"loss": 0.0594,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.039270099746053354,
|
| 27 |
+
"grad_norm": 0.47824403643608093,
|
| 28 |
+
"learning_rate": 1.9738199335026312e-05,
|
| 29 |
+
"loss": 0.0497,
|
| 30 |
+
"step": 1500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.05236013299473781,
|
| 34 |
+
"grad_norm": 0.3971627652645111,
|
| 35 |
+
"learning_rate": 1.965093244670175e-05,
|
| 36 |
+
"loss": 0.043,
|
| 37 |
+
"step": 2000
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.06545016624342226,
|
| 41 |
+
"grad_norm": 0.5000212788581848,
|
| 42 |
+
"learning_rate": 1.9563665558377188e-05,
|
| 43 |
+
"loss": 0.0374,
|
| 44 |
+
"step": 2500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.07854019949210671,
|
| 48 |
+
"grad_norm": 0.9078471064567566,
|
| 49 |
+
"learning_rate": 1.9476398670052623e-05,
|
| 50 |
+
"loss": 0.0357,
|
| 51 |
+
"step": 3000
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.09163023274079116,
|
| 55 |
+
"grad_norm": 0.35205739736557007,
|
| 56 |
+
"learning_rate": 1.938913178172806e-05,
|
| 57 |
+
"loss": 0.0317,
|
| 58 |
+
"step": 3500
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.10472026598947562,
|
| 62 |
+
"grad_norm": 0.19642357528209686,
|
| 63 |
+
"learning_rate": 1.9301864893403495e-05,
|
| 64 |
+
"loss": 0.0304,
|
| 65 |
+
"step": 4000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.11781029923816007,
|
| 69 |
+
"grad_norm": 0.5134682655334473,
|
| 70 |
+
"learning_rate": 1.9214598005078933e-05,
|
| 71 |
+
"loss": 0.0281,
|
| 72 |
+
"step": 4500
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.13090033248684452,
|
| 76 |
+
"grad_norm": 0.23212824761867523,
|
| 77 |
+
"learning_rate": 1.912733111675437e-05,
|
| 78 |
+
"loss": 0.0274,
|
| 79 |
+
"step": 5000
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.14399036573552898,
|
| 83 |
+
"grad_norm": 0.4254980981349945,
|
| 84 |
+
"learning_rate": 1.904006422842981e-05,
|
| 85 |
+
"loss": 0.0247,
|
| 86 |
+
"step": 5500
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.15708039898421342,
|
| 90 |
+
"grad_norm": 0.4024842083454132,
|
| 91 |
+
"learning_rate": 1.8952797340105244e-05,
|
| 92 |
+
"loss": 0.0235,
|
| 93 |
+
"step": 6000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.17017043223289788,
|
| 97 |
+
"grad_norm": 0.40947026014328003,
|
| 98 |
+
"learning_rate": 1.8865530451780682e-05,
|
| 99 |
+
"loss": 0.0235,
|
| 100 |
+
"step": 6500
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.1832604654815823,
|
| 104 |
+
"grad_norm": 0.366158127784729,
|
| 105 |
+
"learning_rate": 1.877826356345612e-05,
|
| 106 |
+
"loss": 0.0225,
|
| 107 |
+
"step": 7000
|
| 108 |
+
},
|
| 109 |
+
{
|
| 110 |
+
"epoch": 0.19635049873026678,
|
| 111 |
+
"grad_norm": 0.4678824841976166,
|
| 112 |
+
"learning_rate": 1.8690996675131558e-05,
|
| 113 |
+
"loss": 0.0219,
|
| 114 |
+
"step": 7500
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 0.20944053197895124,
|
| 118 |
+
"grad_norm": 0.21004918217658997,
|
| 119 |
+
"learning_rate": 1.8603729786806996e-05,
|
| 120 |
+
"loss": 0.0198,
|
| 121 |
+
"step": 8000
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"epoch": 0.22253056522763567,
|
| 125 |
+
"grad_norm": 0.2192375510931015,
|
| 126 |
+
"learning_rate": 1.851646289848243e-05,
|
| 127 |
+
"loss": 0.0201,
|
| 128 |
+
"step": 8500
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.23562059847632014,
|
| 132 |
+
"grad_norm": 0.15161575376987457,
|
| 133 |
+
"learning_rate": 1.842919601015787e-05,
|
| 134 |
+
"loss": 0.0192,
|
| 135 |
+
"step": 9000
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.24871063172500457,
|
| 139 |
+
"grad_norm": 0.3270639181137085,
|
| 140 |
+
"learning_rate": 1.8341929121833303e-05,
|
| 141 |
+
"loss": 0.0186,
|
| 142 |
+
"step": 9500
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.26180066497368903,
|
| 146 |
+
"grad_norm": 0.25447696447372437,
|
| 147 |
+
"learning_rate": 1.825466223350874e-05,
|
| 148 |
+
"loss": 0.0182,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.2748906982223735,
|
| 153 |
+
"grad_norm": 0.1797029674053192,
|
| 154 |
+
"learning_rate": 1.816739534518418e-05,
|
| 155 |
+
"loss": 0.0182,
|
| 156 |
+
"step": 10500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.28798073147105796,
|
| 160 |
+
"grad_norm": 0.4422529637813568,
|
| 161 |
+
"learning_rate": 1.8080128456859617e-05,
|
| 162 |
+
"loss": 0.0175,
|
| 163 |
+
"step": 11000
|
| 164 |
+
},
|
| 165 |
+
{
|
| 166 |
+
"epoch": 0.30107076471974237,
|
| 167 |
+
"grad_norm": 0.19019261002540588,
|
| 168 |
+
"learning_rate": 1.7992861568535052e-05,
|
| 169 |
+
"loss": 0.0159,
|
| 170 |
+
"step": 11500
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 0.31416079796842683,
|
| 174 |
+
"grad_norm": 0.12262561917304993,
|
| 175 |
+
"learning_rate": 1.790559468021049e-05,
|
| 176 |
+
"loss": 0.0162,
|
| 177 |
+
"step": 12000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.3272508312171113,
|
| 181 |
+
"grad_norm": 0.5514086484909058,
|
| 182 |
+
"learning_rate": 1.7818327791885924e-05,
|
| 183 |
+
"loss": 0.0159,
|
| 184 |
+
"step": 12500
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.34034086446579576,
|
| 188 |
+
"grad_norm": 0.3397659957408905,
|
| 189 |
+
"learning_rate": 1.7731060903561362e-05,
|
| 190 |
+
"loss": 0.0163,
|
| 191 |
+
"step": 13000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 0.3534308977144802,
|
| 195 |
+
"grad_norm": 0.3542526364326477,
|
| 196 |
+
"learning_rate": 1.76437940152368e-05,
|
| 197 |
+
"loss": 0.0161,
|
| 198 |
+
"step": 13500
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.3665209309631646,
|
| 202 |
+
"grad_norm": 0.22688041627407074,
|
| 203 |
+
"learning_rate": 1.7556527126912238e-05,
|
| 204 |
+
"loss": 0.0155,
|
| 205 |
+
"step": 14000
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"epoch": 0.3796109642118491,
|
| 209 |
+
"grad_norm": 0.20115447044372559,
|
| 210 |
+
"learning_rate": 1.7469260238587673e-05,
|
| 211 |
+
"loss": 0.0148,
|
| 212 |
+
"step": 14500
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.39270099746053355,
|
| 216 |
+
"grad_norm": 0.09773228317499161,
|
| 217 |
+
"learning_rate": 1.738199335026311e-05,
|
| 218 |
+
"loss": 0.0149,
|
| 219 |
+
"step": 15000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.405791030709218,
|
| 223 |
+
"grad_norm": 0.41297146677970886,
|
| 224 |
+
"learning_rate": 1.729472646193855e-05,
|
| 225 |
+
"loss": 0.0146,
|
| 226 |
+
"step": 15500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.4188810639579025,
|
| 230 |
+
"grad_norm": 0.6495208740234375,
|
| 231 |
+
"learning_rate": 1.7207459573613983e-05,
|
| 232 |
+
"loss": 0.0136,
|
| 233 |
+
"step": 16000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.4319710972065869,
|
| 237 |
+
"grad_norm": 0.35930490493774414,
|
| 238 |
+
"learning_rate": 1.712019268528942e-05,
|
| 239 |
+
"loss": 0.0137,
|
| 240 |
+
"step": 16500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 0.44506113045527135,
|
| 244 |
+
"grad_norm": 0.22953346371650696,
|
| 245 |
+
"learning_rate": 1.703292579696486e-05,
|
| 246 |
+
"loss": 0.0139,
|
| 247 |
+
"step": 17000
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"epoch": 0.4581511637039558,
|
| 251 |
+
"grad_norm": 0.41518378257751465,
|
| 252 |
+
"learning_rate": 1.6945658908640297e-05,
|
| 253 |
+
"loss": 0.0135,
|
| 254 |
+
"step": 17500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.4712411969526403,
|
| 258 |
+
"grad_norm": 0.2171572744846344,
|
| 259 |
+
"learning_rate": 1.6858392020315732e-05,
|
| 260 |
+
"loss": 0.0129,
|
| 261 |
+
"step": 18000
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.48433123020132474,
|
| 265 |
+
"grad_norm": 0.2897777557373047,
|
| 266 |
+
"learning_rate": 1.677112513199117e-05,
|
| 267 |
+
"loss": 0.0122,
|
| 268 |
+
"step": 18500
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.49742126345000914,
|
| 272 |
+
"grad_norm": 0.4209305942058563,
|
| 273 |
+
"learning_rate": 1.6683858243666608e-05,
|
| 274 |
+
"loss": 0.0128,
|
| 275 |
+
"step": 19000
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.5105112966986937,
|
| 279 |
+
"grad_norm": 0.08220311999320984,
|
| 280 |
+
"learning_rate": 1.6596591355342046e-05,
|
| 281 |
+
"loss": 0.0123,
|
| 282 |
+
"step": 19500
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.5236013299473781,
|
| 286 |
+
"grad_norm": 0.09847331047058105,
|
| 287 |
+
"learning_rate": 1.650932446701748e-05,
|
| 288 |
+
"loss": 0.0123,
|
| 289 |
+
"step": 20000
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.5366913631960625,
|
| 293 |
+
"grad_norm": 0.41798558831214905,
|
| 294 |
+
"learning_rate": 1.642205757869292e-05,
|
| 295 |
+
"loss": 0.0128,
|
| 296 |
+
"step": 20500
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.549781396444747,
|
| 300 |
+
"grad_norm": 0.2177186757326126,
|
| 301 |
+
"learning_rate": 1.6334790690368353e-05,
|
| 302 |
+
"loss": 0.0124,
|
| 303 |
+
"step": 21000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.5628714296934314,
|
| 307 |
+
"grad_norm": 0.16467055678367615,
|
| 308 |
+
"learning_rate": 1.624752380204379e-05,
|
| 309 |
+
"loss": 0.0118,
|
| 310 |
+
"step": 21500
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.5759614629421159,
|
| 314 |
+
"grad_norm": 0.3392176330089569,
|
| 315 |
+
"learning_rate": 1.616025691371923e-05,
|
| 316 |
+
"loss": 0.0121,
|
| 317 |
+
"step": 22000
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.5890514961908003,
|
| 321 |
+
"grad_norm": 0.14208835363388062,
|
| 322 |
+
"learning_rate": 1.6072990025394667e-05,
|
| 323 |
+
"loss": 0.0118,
|
| 324 |
+
"step": 22500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.6021415294394847,
|
| 328 |
+
"grad_norm": 0.18248602747917175,
|
| 329 |
+
"learning_rate": 1.5985723137070105e-05,
|
| 330 |
+
"loss": 0.0118,
|
| 331 |
+
"step": 23000
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.6152315626881693,
|
| 335 |
+
"grad_norm": 0.32215237617492676,
|
| 336 |
+
"learning_rate": 1.589845624874554e-05,
|
| 337 |
+
"loss": 0.0111,
|
| 338 |
+
"step": 23500
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.6283215959368537,
|
| 342 |
+
"grad_norm": 0.35770946741104126,
|
| 343 |
+
"learning_rate": 1.5811189360420978e-05,
|
| 344 |
+
"loss": 0.0111,
|
| 345 |
+
"step": 24000
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.6414116291855382,
|
| 349 |
+
"grad_norm": 0.21091119945049286,
|
| 350 |
+
"learning_rate": 1.5723922472096412e-05,
|
| 351 |
+
"loss": 0.0115,
|
| 352 |
+
"step": 24500
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.6545016624342226,
|
| 356 |
+
"grad_norm": 0.215097576379776,
|
| 357 |
+
"learning_rate": 1.563665558377185e-05,
|
| 358 |
+
"loss": 0.0107,
|
| 359 |
+
"step": 25000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.667591695682907,
|
| 363 |
+
"grad_norm": 0.15477751195430756,
|
| 364 |
+
"learning_rate": 1.554938869544729e-05,
|
| 365 |
+
"loss": 0.0105,
|
| 366 |
+
"step": 25500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.6806817289315915,
|
| 370 |
+
"grad_norm": 0.1576426774263382,
|
| 371 |
+
"learning_rate": 1.5462121807122726e-05,
|
| 372 |
+
"loss": 0.0105,
|
| 373 |
+
"step": 26000
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"epoch": 0.6937717621802759,
|
| 377 |
+
"grad_norm": 0.19675689935684204,
|
| 378 |
+
"learning_rate": 1.537485491879816e-05,
|
| 379 |
+
"loss": 0.0096,
|
| 380 |
+
"step": 26500
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 0.7068617954289604,
|
| 384 |
+
"grad_norm": 0.480955570936203,
|
| 385 |
+
"learning_rate": 1.52875880304736e-05,
|
| 386 |
+
"loss": 0.0104,
|
| 387 |
+
"step": 27000
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.7199518286776448,
|
| 391 |
+
"grad_norm": 0.2651515603065491,
|
| 392 |
+
"learning_rate": 1.5200321142149035e-05,
|
| 393 |
+
"loss": 0.0106,
|
| 394 |
+
"step": 27500
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.7330418619263293,
|
| 398 |
+
"grad_norm": 0.21407313644886017,
|
| 399 |
+
"learning_rate": 1.5113054253824473e-05,
|
| 400 |
+
"loss": 0.0102,
|
| 401 |
+
"step": 28000
|
| 402 |
+
},
|
| 403 |
+
{
|
| 404 |
+
"epoch": 0.7461318951750138,
|
| 405 |
+
"grad_norm": 0.13915963470935822,
|
| 406 |
+
"learning_rate": 1.502578736549991e-05,
|
| 407 |
+
"loss": 0.0098,
|
| 408 |
+
"step": 28500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.7592219284236982,
|
| 412 |
+
"grad_norm": 0.09625498950481415,
|
| 413 |
+
"learning_rate": 1.4938520477175348e-05,
|
| 414 |
+
"loss": 0.0099,
|
| 415 |
+
"step": 29000
|
| 416 |
+
},
|
| 417 |
+
{
|
| 418 |
+
"epoch": 0.7723119616723827,
|
| 419 |
+
"grad_norm": 0.26766207814216614,
|
| 420 |
+
"learning_rate": 1.4851253588850782e-05,
|
| 421 |
+
"loss": 0.01,
|
| 422 |
+
"step": 29500
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 0.7854019949210671,
|
| 426 |
+
"grad_norm": 0.03729819133877754,
|
| 427 |
+
"learning_rate": 1.476398670052622e-05,
|
| 428 |
+
"loss": 0.0092,
|
| 429 |
+
"step": 30000
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.7984920281697515,
|
| 433 |
+
"grad_norm": 0.19327211380004883,
|
| 434 |
+
"learning_rate": 1.4676719812201658e-05,
|
| 435 |
+
"loss": 0.0094,
|
| 436 |
+
"step": 30500
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.811582061418436,
|
| 440 |
+
"grad_norm": 0.27896180748939514,
|
| 441 |
+
"learning_rate": 1.4589452923877094e-05,
|
| 442 |
+
"loss": 0.01,
|
| 443 |
+
"step": 31000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.8246720946671204,
|
| 447 |
+
"grad_norm": 0.1490613967180252,
|
| 448 |
+
"learning_rate": 1.4502186035552532e-05,
|
| 449 |
+
"loss": 0.0092,
|
| 450 |
+
"step": 31500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.837762127915805,
|
| 454 |
+
"grad_norm": 0.22722095251083374,
|
| 455 |
+
"learning_rate": 1.4414919147227969e-05,
|
| 456 |
+
"loss": 0.0093,
|
| 457 |
+
"step": 32000
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 0.8508521611644894,
|
| 461 |
+
"grad_norm": 0.2942313849925995,
|
| 462 |
+
"learning_rate": 1.4327652258903407e-05,
|
| 463 |
+
"loss": 0.0098,
|
| 464 |
+
"step": 32500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 0.8639421944131738,
|
| 468 |
+
"grad_norm": 0.37654176354408264,
|
| 469 |
+
"learning_rate": 1.4240385370578841e-05,
|
| 470 |
+
"loss": 0.0095,
|
| 471 |
+
"step": 33000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 0.8770322276618583,
|
| 475 |
+
"grad_norm": 0.21543939411640167,
|
| 476 |
+
"learning_rate": 1.415311848225428e-05,
|
| 477 |
+
"loss": 0.0097,
|
| 478 |
+
"step": 33500
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.8901222609105427,
|
| 482 |
+
"grad_norm": 0.4608267843723297,
|
| 483 |
+
"learning_rate": 1.4065851593929716e-05,
|
| 484 |
+
"loss": 0.0093,
|
| 485 |
+
"step": 34000
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.9032122941592272,
|
| 489 |
+
"grad_norm": 0.1784515380859375,
|
| 490 |
+
"learning_rate": 1.3978584705605154e-05,
|
| 491 |
+
"loss": 0.009,
|
| 492 |
+
"step": 34500
|
| 493 |
+
},
|
| 494 |
+
{
|
| 495 |
+
"epoch": 0.9163023274079116,
|
| 496 |
+
"grad_norm": 0.3353884518146515,
|
| 497 |
+
"learning_rate": 1.389131781728059e-05,
|
| 498 |
+
"loss": 0.009,
|
| 499 |
+
"step": 35000
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"epoch": 0.929392360656596,
|
| 503 |
+
"grad_norm": 0.2330337017774582,
|
| 504 |
+
"learning_rate": 1.3804050928956028e-05,
|
| 505 |
+
"loss": 0.009,
|
| 506 |
+
"step": 35500
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.9424823939052805,
|
| 510 |
+
"grad_norm": 0.32975077629089355,
|
| 511 |
+
"learning_rate": 1.3716784040631464e-05,
|
| 512 |
+
"loss": 0.0092,
|
| 513 |
+
"step": 36000
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.955572427153965,
|
| 517 |
+
"grad_norm": 0.03280099481344223,
|
| 518 |
+
"learning_rate": 1.3629517152306902e-05,
|
| 519 |
+
"loss": 0.0084,
|
| 520 |
+
"step": 36500
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.9686624604026495,
|
| 524 |
+
"grad_norm": 0.22344884276390076,
|
| 525 |
+
"learning_rate": 1.3542250263982337e-05,
|
| 526 |
+
"loss": 0.0089,
|
| 527 |
+
"step": 37000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.9817524936513339,
|
| 531 |
+
"grad_norm": 0.361147403717041,
|
| 532 |
+
"learning_rate": 1.3454983375657775e-05,
|
| 533 |
+
"loss": 0.0084,
|
| 534 |
+
"step": 37500
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.9948425269000183,
|
| 538 |
+
"grad_norm": 0.2099611908197403,
|
| 539 |
+
"learning_rate": 1.3367716487333213e-05,
|
| 540 |
+
"loss": 0.0088,
|
| 541 |
+
"step": 38000
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"epoch": 1.0,
|
| 545 |
+
"eval_loss": 0.005731215700507164,
|
| 546 |
+
"eval_runtime": 2297.4971,
|
| 547 |
+
"eval_samples_per_second": 133.003,
|
| 548 |
+
"eval_steps_per_second": 16.625,
|
| 549 |
+
"step": 38197
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.0079325601487028,
|
| 553 |
+
"grad_norm": 0.24136124551296234,
|
| 554 |
+
"learning_rate": 1.3280449599008649e-05,
|
| 555 |
+
"loss": 0.0078,
|
| 556 |
+
"step": 38500
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.0210225933973873,
|
| 560 |
+
"grad_norm": 0.42886942625045776,
|
| 561 |
+
"learning_rate": 1.3193182710684087e-05,
|
| 562 |
+
"loss": 0.0082,
|
| 563 |
+
"step": 39000
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.0341126266460716,
|
| 567 |
+
"grad_norm": 0.10831937938928604,
|
| 568 |
+
"learning_rate": 1.3105915822359523e-05,
|
| 569 |
+
"loss": 0.0071,
|
| 570 |
+
"step": 39500
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.0472026598947561,
|
| 574 |
+
"grad_norm": 0.20537184178829193,
|
| 575 |
+
"learning_rate": 1.3018648934034961e-05,
|
| 576 |
+
"loss": 0.0081,
|
| 577 |
+
"step": 40000
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.0602926931434407,
|
| 581 |
+
"grad_norm": 0.28797346353530884,
|
| 582 |
+
"learning_rate": 1.2931382045710396e-05,
|
| 583 |
+
"loss": 0.0075,
|
| 584 |
+
"step": 40500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.073382726392125,
|
| 588 |
+
"grad_norm": 0.22928300499916077,
|
| 589 |
+
"learning_rate": 1.2844115157385834e-05,
|
| 590 |
+
"loss": 0.0076,
|
| 591 |
+
"step": 41000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.0864727596408095,
|
| 595 |
+
"grad_norm": 0.003099123015999794,
|
| 596 |
+
"learning_rate": 1.275684826906127e-05,
|
| 597 |
+
"loss": 0.0079,
|
| 598 |
+
"step": 41500
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.099562792889494,
|
| 602 |
+
"grad_norm": 0.287396639585495,
|
| 603 |
+
"learning_rate": 1.2669581380736708e-05,
|
| 604 |
+
"loss": 0.0075,
|
| 605 |
+
"step": 42000
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.1126528261381785,
|
| 609 |
+
"grad_norm": 0.07049620896577835,
|
| 610 |
+
"learning_rate": 1.2582314492412144e-05,
|
| 611 |
+
"loss": 0.007,
|
| 612 |
+
"step": 42500
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.1257428593868628,
|
| 616 |
+
"grad_norm": 0.2029752880334854,
|
| 617 |
+
"learning_rate": 1.2495047604087582e-05,
|
| 618 |
+
"loss": 0.0076,
|
| 619 |
+
"step": 43000
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.1388328926355473,
|
| 623 |
+
"grad_norm": 0.04248388856649399,
|
| 624 |
+
"learning_rate": 1.2407780715763019e-05,
|
| 625 |
+
"loss": 0.0072,
|
| 626 |
+
"step": 43500
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.1519229258842318,
|
| 630 |
+
"grad_norm": 0.4174834191799164,
|
| 631 |
+
"learning_rate": 1.2320513827438457e-05,
|
| 632 |
+
"loss": 0.0077,
|
| 633 |
+
"step": 44000
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.1650129591329161,
|
| 637 |
+
"grad_norm": 0.25623586773872375,
|
| 638 |
+
"learning_rate": 1.2233246939113891e-05,
|
| 639 |
+
"loss": 0.0069,
|
| 640 |
+
"step": 44500
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.1781029923816007,
|
| 644 |
+
"grad_norm": 0.12231756001710892,
|
| 645 |
+
"learning_rate": 1.214598005078933e-05,
|
| 646 |
+
"loss": 0.0076,
|
| 647 |
+
"step": 45000
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.1911930256302852,
|
| 651 |
+
"grad_norm": 0.24928466975688934,
|
| 652 |
+
"learning_rate": 1.2058713162464767e-05,
|
| 653 |
+
"loss": 0.0072,
|
| 654 |
+
"step": 45500
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.2042830588789695,
|
| 658 |
+
"grad_norm": 0.11469607055187225,
|
| 659 |
+
"learning_rate": 1.1971446274140204e-05,
|
| 660 |
+
"loss": 0.0068,
|
| 661 |
+
"step": 46000
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.217373092127654,
|
| 665 |
+
"grad_norm": 0.389217734336853,
|
| 666 |
+
"learning_rate": 1.1884179385815642e-05,
|
| 667 |
+
"loss": 0.0072,
|
| 668 |
+
"step": 46500
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.2304631253763385,
|
| 672 |
+
"grad_norm": 0.1249752938747406,
|
| 673 |
+
"learning_rate": 1.1796912497491078e-05,
|
| 674 |
+
"loss": 0.0065,
|
| 675 |
+
"step": 47000
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.2435531586250228,
|
| 679 |
+
"grad_norm": 0.2189619392156601,
|
| 680 |
+
"learning_rate": 1.1709645609166516e-05,
|
| 681 |
+
"loss": 0.0073,
|
| 682 |
+
"step": 47500
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.2566431918737073,
|
| 686 |
+
"grad_norm": 0.3927897810935974,
|
| 687 |
+
"learning_rate": 1.1622378720841952e-05,
|
| 688 |
+
"loss": 0.0069,
|
| 689 |
+
"step": 48000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.2697332251223918,
|
| 693 |
+
"grad_norm": 0.07470349222421646,
|
| 694 |
+
"learning_rate": 1.153511183251739e-05,
|
| 695 |
+
"loss": 0.0076,
|
| 696 |
+
"step": 48500
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.2828232583710761,
|
| 700 |
+
"grad_norm": 0.3911282420158386,
|
| 701 |
+
"learning_rate": 1.1447844944192825e-05,
|
| 702 |
+
"loss": 0.0071,
|
| 703 |
+
"step": 49000
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.2959132916197607,
|
| 707 |
+
"grad_norm": 0.2361019402742386,
|
| 708 |
+
"learning_rate": 1.1360578055868263e-05,
|
| 709 |
+
"loss": 0.0074,
|
| 710 |
+
"step": 49500
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.3090033248684452,
|
| 714 |
+
"grad_norm": 0.1682516634464264,
|
| 715 |
+
"learning_rate": 1.1273311167543699e-05,
|
| 716 |
+
"loss": 0.0076,
|
| 717 |
+
"step": 50000
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.3220933581171297,
|
| 721 |
+
"grad_norm": 0.1294177621603012,
|
| 722 |
+
"learning_rate": 1.1186044279219137e-05,
|
| 723 |
+
"loss": 0.0065,
|
| 724 |
+
"step": 50500
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.335183391365814,
|
| 728 |
+
"grad_norm": 0.5710951685905457,
|
| 729 |
+
"learning_rate": 1.1098777390894573e-05,
|
| 730 |
+
"loss": 0.0068,
|
| 731 |
+
"step": 51000
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.3482734246144985,
|
| 735 |
+
"grad_norm": 0.12587948143482208,
|
| 736 |
+
"learning_rate": 1.1011510502570011e-05,
|
| 737 |
+
"loss": 0.0071,
|
| 738 |
+
"step": 51500
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.361363457863183,
|
| 742 |
+
"grad_norm": 0.37146255373954773,
|
| 743 |
+
"learning_rate": 1.0924243614245446e-05,
|
| 744 |
+
"loss": 0.0069,
|
| 745 |
+
"step": 52000
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.3744534911118675,
|
| 749 |
+
"grad_norm": 0.29824337363243103,
|
| 750 |
+
"learning_rate": 1.0836976725920884e-05,
|
| 751 |
+
"loss": 0.0069,
|
| 752 |
+
"step": 52500
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.3875435243605518,
|
| 756 |
+
"grad_norm": 0.10349422693252563,
|
| 757 |
+
"learning_rate": 1.0749709837596322e-05,
|
| 758 |
+
"loss": 0.007,
|
| 759 |
+
"step": 53000
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.4006335576092364,
|
| 763 |
+
"grad_norm": 0.2823665142059326,
|
| 764 |
+
"learning_rate": 1.0662442949271758e-05,
|
| 765 |
+
"loss": 0.0069,
|
| 766 |
+
"step": 53500
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.4137235908579209,
|
| 770 |
+
"grad_norm": 0.038343362510204315,
|
| 771 |
+
"learning_rate": 1.0575176060947196e-05,
|
| 772 |
+
"loss": 0.0061,
|
| 773 |
+
"step": 54000
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.4268136241066052,
|
| 777 |
+
"grad_norm": 0.2581956088542938,
|
| 778 |
+
"learning_rate": 1.0487909172622633e-05,
|
| 779 |
+
"loss": 0.0062,
|
| 780 |
+
"step": 54500
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.4399036573552897,
|
| 784 |
+
"grad_norm": 0.11447520554065704,
|
| 785 |
+
"learning_rate": 1.040064228429807e-05,
|
| 786 |
+
"loss": 0.0066,
|
| 787 |
+
"step": 55000
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.4529936906039742,
|
| 791 |
+
"grad_norm": 0.4050372838973999,
|
| 792 |
+
"learning_rate": 1.0313375395973507e-05,
|
| 793 |
+
"loss": 0.007,
|
| 794 |
+
"step": 55500
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.4660837238526585,
|
| 798 |
+
"grad_norm": 0.022968396544456482,
|
| 799 |
+
"learning_rate": 1.0226108507648945e-05,
|
| 800 |
+
"loss": 0.0066,
|
| 801 |
+
"step": 56000
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.479173757101343,
|
| 805 |
+
"grad_norm": 0.07500626146793365,
|
| 806 |
+
"learning_rate": 1.013884161932438e-05,
|
| 807 |
+
"loss": 0.0065,
|
| 808 |
+
"step": 56500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.4922637903500275,
|
| 812 |
+
"grad_norm": 0.031823791563510895,
|
| 813 |
+
"learning_rate": 1.0051574730999817e-05,
|
| 814 |
+
"loss": 0.0063,
|
| 815 |
+
"step": 57000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.5053538235987118,
|
| 819 |
+
"grad_norm": 0.19768255949020386,
|
| 820 |
+
"learning_rate": 9.964307842675255e-06,
|
| 821 |
+
"loss": 0.0068,
|
| 822 |
+
"step": 57500
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.5184438568473964,
|
| 826 |
+
"grad_norm": 0.210379958152771,
|
| 827 |
+
"learning_rate": 9.877040954350692e-06,
|
| 828 |
+
"loss": 0.0064,
|
| 829 |
+
"step": 58000
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.5315338900960809,
|
| 833 |
+
"grad_norm": 0.14373145997524261,
|
| 834 |
+
"learning_rate": 9.789774066026128e-06,
|
| 835 |
+
"loss": 0.007,
|
| 836 |
+
"step": 58500
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.5446239233447652,
|
| 840 |
+
"grad_norm": 0.2256031185388565,
|
| 841 |
+
"learning_rate": 9.702507177701566e-06,
|
| 842 |
+
"loss": 0.0063,
|
| 843 |
+
"step": 59000
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.55771395659345,
|
| 847 |
+
"grad_norm": 0.11486474424600601,
|
| 848 |
+
"learning_rate": 9.615240289377002e-06,
|
| 849 |
+
"loss": 0.0062,
|
| 850 |
+
"step": 59500
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.5708039898421342,
|
| 854 |
+
"grad_norm": 0.20883575081825256,
|
| 855 |
+
"learning_rate": 9.527973401052439e-06,
|
| 856 |
+
"loss": 0.0061,
|
| 857 |
+
"step": 60000
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.5838940230908185,
|
| 861 |
+
"grad_norm": 0.15535525977611542,
|
| 862 |
+
"learning_rate": 9.440706512727877e-06,
|
| 863 |
+
"loss": 0.006,
|
| 864 |
+
"step": 60500
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.5969840563395032,
|
| 868 |
+
"grad_norm": 0.2790842652320862,
|
| 869 |
+
"learning_rate": 9.353439624403313e-06,
|
| 870 |
+
"loss": 0.0065,
|
| 871 |
+
"step": 61000
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.6100740895881875,
|
| 875 |
+
"grad_norm": 0.338480681180954,
|
| 876 |
+
"learning_rate": 9.266172736078751e-06,
|
| 877 |
+
"loss": 0.0066,
|
| 878 |
+
"step": 61500
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.623164122836872,
|
| 882 |
+
"grad_norm": 0.3213784098625183,
|
| 883 |
+
"learning_rate": 9.178905847754187e-06,
|
| 884 |
+
"loss": 0.0064,
|
| 885 |
+
"step": 62000
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.6362541560855566,
|
| 889 |
+
"grad_norm": 0.22697031497955322,
|
| 890 |
+
"learning_rate": 9.091638959429623e-06,
|
| 891 |
+
"loss": 0.0066,
|
| 892 |
+
"step": 62500
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.6493441893342409,
|
| 896 |
+
"grad_norm": 0.12834736704826355,
|
| 897 |
+
"learning_rate": 9.004372071105061e-06,
|
| 898 |
+
"loss": 0.0063,
|
| 899 |
+
"step": 63000
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.6624342225829254,
|
| 903 |
+
"grad_norm": 0.08631685376167297,
|
| 904 |
+
"learning_rate": 8.9171051827805e-06,
|
| 905 |
+
"loss": 0.0058,
|
| 906 |
+
"step": 63500
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.67552425583161,
|
| 910 |
+
"grad_norm": 0.12295836955308914,
|
| 911 |
+
"learning_rate": 8.829838294455936e-06,
|
| 912 |
+
"loss": 0.0054,
|
| 913 |
+
"step": 64000
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.6886142890802942,
|
| 917 |
+
"grad_norm": 0.3893487751483917,
|
| 918 |
+
"learning_rate": 8.742571406131372e-06,
|
| 919 |
+
"loss": 0.0062,
|
| 920 |
+
"step": 64500
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.7017043223289787,
|
| 924 |
+
"grad_norm": 0.14583726227283478,
|
| 925 |
+
"learning_rate": 8.65530451780681e-06,
|
| 926 |
+
"loss": 0.0063,
|
| 927 |
+
"step": 65000
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.7147943555776632,
|
| 931 |
+
"grad_norm": 0.3584669232368469,
|
| 932 |
+
"learning_rate": 8.568037629482246e-06,
|
| 933 |
+
"loss": 0.0064,
|
| 934 |
+
"step": 65500
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.7278843888263475,
|
| 938 |
+
"grad_norm": 0.05680006742477417,
|
| 939 |
+
"learning_rate": 8.480770741157683e-06,
|
| 940 |
+
"loss": 0.0061,
|
| 941 |
+
"step": 66000
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.740974422075032,
|
| 945 |
+
"grad_norm": 0.15972712635993958,
|
| 946 |
+
"learning_rate": 8.39350385283312e-06,
|
| 947 |
+
"loss": 0.0061,
|
| 948 |
+
"step": 66500
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.7540644553237166,
|
| 952 |
+
"grad_norm": 0.3504839837551117,
|
| 953 |
+
"learning_rate": 8.306236964508557e-06,
|
| 954 |
+
"loss": 0.0056,
|
| 955 |
+
"step": 67000
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.7671544885724009,
|
| 959 |
+
"grad_norm": 0.2058769315481186,
|
| 960 |
+
"learning_rate": 8.218970076183995e-06,
|
| 961 |
+
"loss": 0.0062,
|
| 962 |
+
"step": 67500
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.7802445218210854,
|
| 966 |
+
"grad_norm": 0.2028743475675583,
|
| 967 |
+
"learning_rate": 8.131703187859431e-06,
|
| 968 |
+
"loss": 0.0062,
|
| 969 |
+
"step": 68000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.79333455506977,
|
| 973 |
+
"grad_norm": 0.11009418964385986,
|
| 974 |
+
"learning_rate": 8.044436299534868e-06,
|
| 975 |
+
"loss": 0.0062,
|
| 976 |
+
"step": 68500
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.8064245883184542,
|
| 980 |
+
"grad_norm": 0.0618484802544117,
|
| 981 |
+
"learning_rate": 7.957169411210305e-06,
|
| 982 |
+
"loss": 0.0062,
|
| 983 |
+
"step": 69000
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.819514621567139,
|
| 987 |
+
"grad_norm": 0.08521759510040283,
|
| 988 |
+
"learning_rate": 7.869902522885742e-06,
|
| 989 |
+
"loss": 0.0059,
|
| 990 |
+
"step": 69500
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.8326046548158232,
|
| 994 |
+
"grad_norm": 0.3029402196407318,
|
| 995 |
+
"learning_rate": 7.782635634561178e-06,
|
| 996 |
+
"loss": 0.0059,
|
| 997 |
+
"step": 70000
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.8456946880645075,
|
| 1001 |
+
"grad_norm": 0.23642723262310028,
|
| 1002 |
+
"learning_rate": 7.695368746236616e-06,
|
| 1003 |
+
"loss": 0.006,
|
| 1004 |
+
"step": 70500
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.8587847213131923,
|
| 1008 |
+
"grad_norm": 0.14888063073158264,
|
| 1009 |
+
"learning_rate": 7.608101857912053e-06,
|
| 1010 |
+
"loss": 0.006,
|
| 1011 |
+
"step": 71000
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.8718747545618766,
|
| 1015 |
+
"grad_norm": 0.10285039246082306,
|
| 1016 |
+
"learning_rate": 7.52083496958749e-06,
|
| 1017 |
+
"loss": 0.0054,
|
| 1018 |
+
"step": 71500
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.884964787810561,
|
| 1022 |
+
"grad_norm": 0.1975327879190445,
|
| 1023 |
+
"learning_rate": 7.4335680812629275e-06,
|
| 1024 |
+
"loss": 0.0059,
|
| 1025 |
+
"step": 72000
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.8980548210592456,
|
| 1029 |
+
"grad_norm": 0.24295471608638763,
|
| 1030 |
+
"learning_rate": 7.346301192938365e-06,
|
| 1031 |
+
"loss": 0.0058,
|
| 1032 |
+
"step": 72500
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.91114485430793,
|
| 1036 |
+
"grad_norm": 0.03384074568748474,
|
| 1037 |
+
"learning_rate": 7.259034304613801e-06,
|
| 1038 |
+
"loss": 0.0058,
|
| 1039 |
+
"step": 73000
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.9242348875566144,
|
| 1043 |
+
"grad_norm": 0.18082177639007568,
|
| 1044 |
+
"learning_rate": 7.171767416289238e-06,
|
| 1045 |
+
"loss": 0.0058,
|
| 1046 |
+
"step": 73500
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.937324920805299,
|
| 1050 |
+
"grad_norm": 0.33321407437324524,
|
| 1051 |
+
"learning_rate": 7.084500527964675e-06,
|
| 1052 |
+
"loss": 0.0057,
|
| 1053 |
+
"step": 74000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.9504149540539832,
|
| 1057 |
+
"grad_norm": 0.0694960206747055,
|
| 1058 |
+
"learning_rate": 6.9972336396401115e-06,
|
| 1059 |
+
"loss": 0.0058,
|
| 1060 |
+
"step": 74500
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.9635049873026678,
|
| 1064 |
+
"grad_norm": 0.11903239041566849,
|
| 1065 |
+
"learning_rate": 6.909966751315549e-06,
|
| 1066 |
+
"loss": 0.0057,
|
| 1067 |
+
"step": 75000
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.9765950205513523,
|
| 1071 |
+
"grad_norm": 0.28279566764831543,
|
| 1072 |
+
"learning_rate": 6.822699862990986e-06,
|
| 1073 |
+
"loss": 0.0054,
|
| 1074 |
+
"step": 75500
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.9896850538000366,
|
| 1078 |
+
"grad_norm": 0.12491460144519806,
|
| 1079 |
+
"learning_rate": 6.735432974666423e-06,
|
| 1080 |
+
"loss": 0.0055,
|
| 1081 |
+
"step": 76000
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.0,
|
| 1085 |
+
"eval_loss": 0.0037132962606847286,
|
| 1086 |
+
"eval_runtime": 2298.3508,
|
| 1087 |
+
"eval_samples_per_second": 132.953,
|
| 1088 |
+
"eval_steps_per_second": 16.619,
|
| 1089 |
+
"step": 76394
|
| 1090 |
+
}
|
| 1091 |
+
],
|
| 1092 |
+
"logging_steps": 500,
|
| 1093 |
+
"max_steps": 114591,
|
| 1094 |
+
"num_input_tokens_seen": 0,
|
| 1095 |
+
"num_train_epochs": 3,
|
| 1096 |
+
"save_steps": 500,
|
| 1097 |
+
"stateful_callbacks": {
|
| 1098 |
+
"TrainerControl": {
|
| 1099 |
+
"args": {
|
| 1100 |
+
"should_epoch_stop": false,
|
| 1101 |
+
"should_evaluate": false,
|
| 1102 |
+
"should_log": false,
|
| 1103 |
+
"should_save": true,
|
| 1104 |
+
"should_training_stop": false
|
| 1105 |
+
},
|
| 1106 |
+
"attributes": {}
|
| 1107 |
+
}
|
| 1108 |
+
},
|
| 1109 |
+
"total_flos": 4.657974968844288e+16,
|
| 1110 |
+
"train_batch_size": 8,
|
| 1111 |
+
"trial_name": null,
|
| 1112 |
+
"trial_params": null
|
| 1113 |
+
}
|
checkpoint-76394/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d54a045f207a6e96a5980be3103fb572390bb8f4d93e00dba90dcfdee06f7fd
|
| 3 |
+
size 5304
|
checkpoint-76394/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForConditionalGeneration"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": null,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"forced_eos_token_id": 2,
|
| 28 |
+
"gradient_checkpointing": false,
|
| 29 |
+
"id2label": {
|
| 30 |
+
"0": "LABEL_0",
|
| 31 |
+
"1": "LABEL_1",
|
| 32 |
+
"2": "LABEL_2"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 1,
|
| 39 |
+
"LABEL_2": 2
|
| 40 |
+
},
|
| 41 |
+
"max_position_embeddings": 1024,
|
| 42 |
+
"model_type": "bart",
|
| 43 |
+
"no_repeat_ngram_size": null,
|
| 44 |
+
"normalize_before": false,
|
| 45 |
+
"normalize_embedding": true,
|
| 46 |
+
"num_beams": null,
|
| 47 |
+
"num_hidden_layers": 6,
|
| 48 |
+
"pad_token_id": 1,
|
| 49 |
+
"scale_embedding": false,
|
| 50 |
+
"task_specific_params": {
|
| 51 |
+
"summarization": {
|
| 52 |
+
"length_penalty": 1.0,
|
| 53 |
+
"max_length": 128,
|
| 54 |
+
"min_length": 12,
|
| 55 |
+
"num_beams": 4
|
| 56 |
+
},
|
| 57 |
+
"summarization_cnn": {
|
| 58 |
+
"length_penalty": 2.0,
|
| 59 |
+
"max_length": 142,
|
| 60 |
+
"min_length": 56,
|
| 61 |
+
"num_beams": 4
|
| 62 |
+
},
|
| 63 |
+
"summarization_xsum": {
|
| 64 |
+
"length_penalty": 1.0,
|
| 65 |
+
"max_length": 62,
|
| 66 |
+
"min_length": 11,
|
| 67 |
+
"num_beams": 6
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"torch_dtype": "float32",
|
| 71 |
+
"transformers_version": "4.48.3",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"vocab_size": 50265
|
| 74 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"decoder_start_token_id": 2,
|
| 5 |
+
"early_stopping": true,
|
| 6 |
+
"eos_token_id": 2,
|
| 7 |
+
"forced_bos_token_id": 0,
|
| 8 |
+
"forced_eos_token_id": 2,
|
| 9 |
+
"no_repeat_ngram_size": 3,
|
| 10 |
+
"num_beams": 4,
|
| 11 |
+
"pad_token_id": 1,
|
| 12 |
+
"transformers_version": "4.48.3"
|
| 13 |
+
}
|
load_model.ipynb
ADDED
|
@@ -0,0 +1,132 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "markdown",
|
| 5 |
+
"id": "0fc4c61a",
|
| 6 |
+
"metadata": {},
|
| 7 |
+
"source": [
|
| 8 |
+
"## Loading a model onto HF"
|
| 9 |
+
]
|
| 10 |
+
},
|
| 11 |
+
{
|
| 12 |
+
"cell_type": "code",
|
| 13 |
+
"execution_count": 1,
|
| 14 |
+
"id": "3c851cd5",
|
| 15 |
+
"metadata": {},
|
| 16 |
+
"outputs": [
|
| 17 |
+
{
|
| 18 |
+
"name": "stdout",
|
| 19 |
+
"output_type": "stream",
|
| 20 |
+
"text": [
|
| 21 |
+
"Requirement already satisfied: huggingface_hub in c:\\users\\ishan\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (0.30.2)\n",
|
| 22 |
+
"Requirement already satisfied: filelock in c:\\users\\ishan\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from huggingface_hub) (3.15.4)\n",
|
| 23 |
+
"Requirement already satisfied: fsspec>=2023.5.0 in c:\\users\\ishan\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from huggingface_hub) (2024.6.1)\n",
|
| 24 |
+
"Requirement already satisfied: packaging>=20.9 in c:\\users\\ishan\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from huggingface_hub) (24.2)\n",
|
| 25 |
+
"Requirement already satisfied: pyyaml>=5.1 in c:\\users\\ishan\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from huggingface_hub) (6.0.1)\n",
|
| 26 |
+
"Requirement already satisfied: requests in c:\\users\\ishan\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from huggingface_hub) (2.32.3)\n",
|
| 27 |
+
"Requirement already satisfied: tqdm>=4.42.1 in c:\\users\\ishan\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from huggingface_hub) (4.66.4)\n",
|
| 28 |
+
"Requirement already satisfied: typing-extensions>=3.7.4.3 in c:\\users\\ishan\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from huggingface_hub) (4.12.2)\n",
|
| 29 |
+
"Requirement already satisfied: colorama in c:\\users\\ishan\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from tqdm>=4.42.1->huggingface_hub) (0.4.6)\n",
|
| 30 |
+
"Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\ishan\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from requests->huggingface_hub) (3.3.2)\n",
|
| 31 |
+
"Requirement already satisfied: idna<4,>=2.5 in c:\\users\\ishan\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from requests->huggingface_hub) (3.7)\n",
|
| 32 |
+
"Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\ishan\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from requests->huggingface_hub) (2.0.7)\n",
|
| 33 |
+
"Requirement already satisfied: certifi>=2017.4.17 in c:\\users\\ishan\\appdata\\local\\packages\\pythonsoftwarefoundation.python.3.11_qbz5n2kfra8p0\\localcache\\local-packages\\python311\\site-packages (from requests->huggingface_hub) (2024.7.4)\n"
|
| 34 |
+
]
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"name": "stderr",
|
| 38 |
+
"output_type": "stream",
|
| 39 |
+
"text": [
|
| 40 |
+
"\n",
|
| 41 |
+
"[notice] A new release of pip is available: 24.3.1 -> 25.1.1\n",
|
| 42 |
+
"[notice] To update, run: C:\\Users\\ishan\\AppData\\Local\\Microsoft\\WindowsApps\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\python.exe -m pip install --upgrade pip\n"
|
| 43 |
+
]
|
| 44 |
+
}
|
| 45 |
+
],
|
| 46 |
+
"source": [
|
| 47 |
+
"# Install if you haven't already\n",
|
| 48 |
+
"!pip install huggingface_hub"
|
| 49 |
+
]
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"cell_type": "code",
|
| 53 |
+
"execution_count": 3,
|
| 54 |
+
"id": "85147dd3",
|
| 55 |
+
"metadata": {},
|
| 56 |
+
"outputs": [
|
| 57 |
+
{
|
| 58 |
+
"name": "stderr",
|
| 59 |
+
"output_type": "stream",
|
| 60 |
+
"text": [
|
| 61 |
+
"Consider using `hf_transfer` for faster uploads. This solution comes with some limitations. See https://huggingface.co/docs/huggingface_hub/hf_transfer for more details.\n",
|
| 62 |
+
"Traceback (most recent call last):\n",
|
| 63 |
+
" File \"C:\\Users\\ishan\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\huggingface_hub\\utils\\_http.py\", line 409, in hf_raise_for_status\n",
|
| 64 |
+
" response.raise_for_status()\n",
|
| 65 |
+
" File \"C:\\Users\\ishan\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\requests\\models.py\", line 1024, in raise_for_status\n",
|
| 66 |
+
" raise HTTPError(http_error_msg, response=self)\n",
|
| 67 |
+
"requests.exceptions.HTTPError: 403 Client Error: Forbidden for url: https://huggingface.co/api/repos/create\n",
|
| 68 |
+
"\n",
|
| 69 |
+
"The above exception was the direct cause of the following exception:\n",
|
| 70 |
+
"\n",
|
| 71 |
+
"Traceback (most recent call last):\n",
|
| 72 |
+
" File \"<frozen runpy>\", line 198, in _run_module_as_main\n",
|
| 73 |
+
" File \"<frozen runpy>\", line 88, in _run_code\n",
|
| 74 |
+
" File \"c:\\Users\\ishan\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\Scripts\\huggingface-cli.exe\\__main__.py\", line 7, in <module>\n",
|
| 75 |
+
" File \"C:\\Users\\ishan\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\huggingface_hub\\commands\\huggingface_cli.py\", line 57, in main\n",
|
| 76 |
+
" service.run()\n",
|
| 77 |
+
" File \"C:\\Users\\ishan\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\huggingface_hub\\commands\\upload.py\", line 206, in run\n",
|
| 78 |
+
" print(self._upload())\n",
|
| 79 |
+
" ^^^^^^^^^^^^^^\n",
|
| 80 |
+
" File \"C:\\Users\\ishan\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\huggingface_hub\\commands\\upload.py\", line 267, in _upload\n",
|
| 81 |
+
" repo_id = self.api.create_repo(\n",
|
| 82 |
+
" ^^^^^^^^^^^^^^^^^^^^^\n",
|
| 83 |
+
" File \"C:\\Users\\ishan\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\huggingface_hub\\utils\\_validators.py\", line 114, in _inner_fn\n",
|
| 84 |
+
" return fn(*args, **kwargs)\n",
|
| 85 |
+
" ^^^^^^^^^^^^^^^^^^^\n",
|
| 86 |
+
" File \"C:\\Users\\ishan\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\huggingface_hub\\hf_api.py\", line 3722, in create_repo\n",
|
| 87 |
+
" raise err\n",
|
| 88 |
+
" File \"C:\\Users\\ishan\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\huggingface_hub\\hf_api.py\", line 3709, in create_repo\n",
|
| 89 |
+
" hf_raise_for_status(r)\n",
|
| 90 |
+
" File \"C:\\Users\\ishan\\AppData\\Local\\Packages\\PythonSoftwareFoundation.Python.3.11_qbz5n2kfra8p0\\LocalCache\\local-packages\\Python311\\site-packages\\huggingface_hub\\utils\\_http.py\", line 473, in hf_raise_for_status\n",
|
| 91 |
+
" raise _format(HfHubHTTPError, message, response) from e\n",
|
| 92 |
+
"huggingface_hub.errors.HfHubHTTPError: 403 Forbidden: None.\n",
|
| 93 |
+
"Cannot access content at: https://huggingface.co/api/repos/create.\n",
|
| 94 |
+
"Make sure your token has the correct permissions.\n"
|
| 95 |
+
]
|
| 96 |
+
}
|
| 97 |
+
],
|
| 98 |
+
"source": [
|
| 99 |
+
"!huggingface-cli upload Ishanan/lemma-model . --repo-type model --token YOUR_HF_TOKEN_HERE"
|
| 100 |
+
]
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"cell_type": "code",
|
| 104 |
+
"execution_count": null,
|
| 105 |
+
"id": "360e19b7",
|
| 106 |
+
"metadata": {},
|
| 107 |
+
"outputs": [],
|
| 108 |
+
"source": []
|
| 109 |
+
}
|
| 110 |
+
],
|
| 111 |
+
"metadata": {
|
| 112 |
+
"kernelspec": {
|
| 113 |
+
"display_name": "Python 3",
|
| 114 |
+
"language": "python",
|
| 115 |
+
"name": "python3"
|
| 116 |
+
},
|
| 117 |
+
"language_info": {
|
| 118 |
+
"codemirror_mode": {
|
| 119 |
+
"name": "ipython",
|
| 120 |
+
"version": 3
|
| 121 |
+
},
|
| 122 |
+
"file_extension": ".py",
|
| 123 |
+
"mimetype": "text/x-python",
|
| 124 |
+
"name": "python",
|
| 125 |
+
"nbconvert_exporter": "python",
|
| 126 |
+
"pygments_lexer": "ipython3",
|
| 127 |
+
"version": "3.11.9"
|
| 128 |
+
}
|
| 129 |
+
},
|
| 130 |
+
"nbformat": 4,
|
| 131 |
+
"nbformat_minor": 5
|
| 132 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d51cfc04e9563e0bb5243172241fcae18435e6bf2f3345ac6a478f467d2b9a89
|
| 3 |
+
size 557912620
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "BartTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d54a045f207a6e96a5980be3103fb572390bb8f4d93e00dba90dcfdee06f7fd
|
| 3 |
+
size 5304
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|