Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-1/checkpoint-71220/config.json +25 -0
- run-1/checkpoint-71220/model.safetensors +3 -0
- run-1/checkpoint-71220/optimizer.pt +3 -0
- run-1/checkpoint-71220/rng_state.pth +3 -0
- run-1/checkpoint-71220/scheduler.pt +3 -0
- run-1/checkpoint-71220/special_tokens_map.json +7 -0
- run-1/checkpoint-71220/tokenizer.json +0 -0
- run-1/checkpoint-71220/tokenizer_config.json +55 -0
- run-1/checkpoint-71220/trainer_state.json +914 -0
- run-1/checkpoint-71220/training_args.bin +3 -0
- run-1/checkpoint-71220/vocab.txt +0 -0
- run-1/checkpoint-89025/config.json +25 -0
- run-1/checkpoint-89025/model.safetensors +3 -0
- run-1/checkpoint-89025/optimizer.pt +3 -0
- run-1/checkpoint-89025/rng_state.pth +3 -0
- run-1/checkpoint-89025/scheduler.pt +3 -0
- run-1/checkpoint-89025/special_tokens_map.json +7 -0
- run-1/checkpoint-89025/tokenizer.json +0 -0
- run-1/checkpoint-89025/tokenizer_config.json +55 -0
- run-1/checkpoint-89025/trainer_state.json +1139 -0
- run-1/checkpoint-89025/training_args.bin +3 -0
- run-1/checkpoint-89025/vocab.txt +0 -0
- training_args.bin +1 -1
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 267832560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b3ec6988cd675d795198926d0049485f4aa0f3ee5536474ac860408ad112caa5
|
| 3 |
size 267832560
|
run-1/checkpoint-71220/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"problem_type": "single_label_classification",
|
| 18 |
+
"qa_dropout": 0.1,
|
| 19 |
+
"seq_classif_dropout": 0.2,
|
| 20 |
+
"sinusoidal_pos_embds": false,
|
| 21 |
+
"tie_weights_": true,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.37.2",
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
+
}
|
run-1/checkpoint-71220/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ae165d1fdb1975fbecc14059659f9034eb5a1eb03c3c64d701ddbe9df34d6c6
|
| 3 |
+
size 267832560
|
run-1/checkpoint-71220/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20baf01ba69abeea1f01c8051fa33679dcecd7ad4fab5eb050ff77fb88bb7a63
|
| 3 |
+
size 535727290
|
run-1/checkpoint-71220/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b0ae6b438a433176d5b4a1ef9fef44c43a010d458c42c8761adb79a9b4ab57c2
|
| 3 |
+
size 14244
|
run-1/checkpoint-71220/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e67620fc64569a10047cdb3855916a14319e993e85039af5210ab17d8fa2f50
|
| 3 |
+
size 1064
|
run-1/checkpoint-71220/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-1/checkpoint-71220/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-1/checkpoint-71220/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
run-1/checkpoint-71220/trainer_state.json
ADDED
|
@@ -0,0 +1,914 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8682891911238368,
|
| 3 |
+
"best_model_checkpoint": "relevant_model/run-1/checkpoint-71220",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 71220,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 4.101665655728474e-06,
|
| 14 |
+
"loss": 0.5111,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"learning_rate": 4.078498947704027e-06,
|
| 20 |
+
"loss": 0.4216,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.08,
|
| 25 |
+
"learning_rate": 4.0553322396795785e-06,
|
| 26 |
+
"loss": 0.4711,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.11,
|
| 31 |
+
"learning_rate": 4.0321655316551306e-06,
|
| 32 |
+
"loss": 0.4472,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.14,
|
| 37 |
+
"learning_rate": 4.0089988236306835e-06,
|
| 38 |
+
"loss": 0.4429,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.17,
|
| 43 |
+
"learning_rate": 3.985832115606236e-06,
|
| 44 |
+
"loss": 0.5083,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.2,
|
| 49 |
+
"learning_rate": 3.962665407581788e-06,
|
| 50 |
+
"loss": 0.469,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.22,
|
| 55 |
+
"learning_rate": 3.93949869955734e-06,
|
| 56 |
+
"loss": 0.4424,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.25,
|
| 61 |
+
"learning_rate": 3.916331991532892e-06,
|
| 62 |
+
"loss": 0.472,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.28,
|
| 67 |
+
"learning_rate": 3.893165283508445e-06,
|
| 68 |
+
"loss": 0.4344,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.31,
|
| 73 |
+
"learning_rate": 3.869998575483997e-06,
|
| 74 |
+
"loss": 0.4255,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.34,
|
| 79 |
+
"learning_rate": 3.846831867459549e-06,
|
| 80 |
+
"loss": 0.4293,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.37,
|
| 85 |
+
"learning_rate": 3.823665159435101e-06,
|
| 86 |
+
"loss": 0.4581,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.39,
|
| 91 |
+
"learning_rate": 3.8004984514106537e-06,
|
| 92 |
+
"loss": 0.4235,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.42,
|
| 97 |
+
"learning_rate": 3.777331743386206e-06,
|
| 98 |
+
"loss": 0.4334,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.45,
|
| 103 |
+
"learning_rate": 3.7541650353617583e-06,
|
| 104 |
+
"loss": 0.3703,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.48,
|
| 109 |
+
"learning_rate": 3.7309983273373104e-06,
|
| 110 |
+
"loss": 0.4415,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.51,
|
| 115 |
+
"learning_rate": 3.7078316193128626e-06,
|
| 116 |
+
"loss": 0.4234,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.53,
|
| 121 |
+
"learning_rate": 3.684664911288415e-06,
|
| 122 |
+
"loss": 0.4184,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.56,
|
| 127 |
+
"learning_rate": 3.661498203263967e-06,
|
| 128 |
+
"loss": 0.3912,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.59,
|
| 133 |
+
"learning_rate": 3.6383314952395193e-06,
|
| 134 |
+
"loss": 0.4158,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.62,
|
| 139 |
+
"learning_rate": 3.615164787215072e-06,
|
| 140 |
+
"loss": 0.3966,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.65,
|
| 145 |
+
"learning_rate": 3.591998079190624e-06,
|
| 146 |
+
"loss": 0.4171,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.67,
|
| 151 |
+
"learning_rate": 3.568831371166176e-06,
|
| 152 |
+
"loss": 0.381,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.7,
|
| 157 |
+
"learning_rate": 3.5456646631417285e-06,
|
| 158 |
+
"loss": 0.3867,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.73,
|
| 163 |
+
"learning_rate": 3.5224979551172806e-06,
|
| 164 |
+
"loss": 0.4438,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.76,
|
| 169 |
+
"learning_rate": 3.4993312470928328e-06,
|
| 170 |
+
"loss": 0.3806,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.79,
|
| 175 |
+
"learning_rate": 3.4761645390683853e-06,
|
| 176 |
+
"loss": 0.391,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.81,
|
| 181 |
+
"learning_rate": 3.4529978310439374e-06,
|
| 182 |
+
"loss": 0.3947,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.84,
|
| 187 |
+
"learning_rate": 3.42983112301949e-06,
|
| 188 |
+
"loss": 0.397,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.87,
|
| 193 |
+
"learning_rate": 3.406664414995042e-06,
|
| 194 |
+
"loss": 0.4048,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.9,
|
| 199 |
+
"learning_rate": 3.383497706970594e-06,
|
| 200 |
+
"loss": 0.4648,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.93,
|
| 205 |
+
"learning_rate": 3.3603309989461466e-06,
|
| 206 |
+
"loss": 0.3751,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.95,
|
| 211 |
+
"learning_rate": 3.3371642909216987e-06,
|
| 212 |
+
"loss": 0.3951,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.98,
|
| 217 |
+
"learning_rate": 3.313997582897251e-06,
|
| 218 |
+
"loss": 0.4386,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0,
|
| 223 |
+
"eval_f1": 0.8416666666666667,
|
| 224 |
+
"eval_loss": 0.3926413059234619,
|
| 225 |
+
"eval_runtime": 7.7212,
|
| 226 |
+
"eval_samples_per_second": 512.357,
|
| 227 |
+
"eval_steps_per_second": 8.03,
|
| 228 |
+
"step": 17805
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.01,
|
| 232 |
+
"learning_rate": 3.2908308748728034e-06,
|
| 233 |
+
"loss": 0.3639,
|
| 234 |
+
"step": 18000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.04,
|
| 238 |
+
"learning_rate": 3.2676641668483555e-06,
|
| 239 |
+
"loss": 0.372,
|
| 240 |
+
"step": 18500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.07,
|
| 244 |
+
"learning_rate": 3.2444974588239076e-06,
|
| 245 |
+
"loss": 0.3249,
|
| 246 |
+
"step": 19000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.1,
|
| 250 |
+
"learning_rate": 3.22133075079946e-06,
|
| 251 |
+
"loss": 0.3586,
|
| 252 |
+
"step": 19500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.12,
|
| 256 |
+
"learning_rate": 3.1981640427750122e-06,
|
| 257 |
+
"loss": 0.3595,
|
| 258 |
+
"step": 20000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.15,
|
| 262 |
+
"learning_rate": 3.1749973347505643e-06,
|
| 263 |
+
"loss": 0.3577,
|
| 264 |
+
"step": 20500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.18,
|
| 268 |
+
"learning_rate": 3.151830626726117e-06,
|
| 269 |
+
"loss": 0.3505,
|
| 270 |
+
"step": 21000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.21,
|
| 274 |
+
"learning_rate": 3.128663918701669e-06,
|
| 275 |
+
"loss": 0.3448,
|
| 276 |
+
"step": 21500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.24,
|
| 280 |
+
"learning_rate": 3.105497210677221e-06,
|
| 281 |
+
"loss": 0.3726,
|
| 282 |
+
"step": 22000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.26,
|
| 286 |
+
"learning_rate": 3.0823305026527736e-06,
|
| 287 |
+
"loss": 0.3522,
|
| 288 |
+
"step": 22500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.29,
|
| 292 |
+
"learning_rate": 3.0591637946283257e-06,
|
| 293 |
+
"loss": 0.3814,
|
| 294 |
+
"step": 23000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.32,
|
| 298 |
+
"learning_rate": 3.0359970866038778e-06,
|
| 299 |
+
"loss": 0.3641,
|
| 300 |
+
"step": 23500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.35,
|
| 304 |
+
"learning_rate": 3.0128303785794303e-06,
|
| 305 |
+
"loss": 0.343,
|
| 306 |
+
"step": 24000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.38,
|
| 310 |
+
"learning_rate": 2.9896636705549824e-06,
|
| 311 |
+
"loss": 0.331,
|
| 312 |
+
"step": 24500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.4,
|
| 316 |
+
"learning_rate": 2.966496962530535e-06,
|
| 317 |
+
"loss": 0.3737,
|
| 318 |
+
"step": 25000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.43,
|
| 322 |
+
"learning_rate": 2.943330254506087e-06,
|
| 323 |
+
"loss": 0.3437,
|
| 324 |
+
"step": 25500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.46,
|
| 328 |
+
"learning_rate": 2.920163546481639e-06,
|
| 329 |
+
"loss": 0.3648,
|
| 330 |
+
"step": 26000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.49,
|
| 334 |
+
"learning_rate": 2.8969968384571917e-06,
|
| 335 |
+
"loss": 0.3421,
|
| 336 |
+
"step": 26500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.52,
|
| 340 |
+
"learning_rate": 2.8738301304327438e-06,
|
| 341 |
+
"loss": 0.3344,
|
| 342 |
+
"step": 27000
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.54,
|
| 346 |
+
"learning_rate": 2.850663422408296e-06,
|
| 347 |
+
"loss": 0.3533,
|
| 348 |
+
"step": 27500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.57,
|
| 352 |
+
"learning_rate": 2.8274967143838484e-06,
|
| 353 |
+
"loss": 0.371,
|
| 354 |
+
"step": 28000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.6,
|
| 358 |
+
"learning_rate": 2.8043300063594005e-06,
|
| 359 |
+
"loss": 0.3526,
|
| 360 |
+
"step": 28500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.63,
|
| 364 |
+
"learning_rate": 2.7811632983349526e-06,
|
| 365 |
+
"loss": 0.3539,
|
| 366 |
+
"step": 29000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.66,
|
| 370 |
+
"learning_rate": 2.757996590310505e-06,
|
| 371 |
+
"loss": 0.3692,
|
| 372 |
+
"step": 29500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.68,
|
| 376 |
+
"learning_rate": 2.7348298822860572e-06,
|
| 377 |
+
"loss": 0.3104,
|
| 378 |
+
"step": 30000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.71,
|
| 382 |
+
"learning_rate": 2.7116631742616094e-06,
|
| 383 |
+
"loss": 0.3371,
|
| 384 |
+
"step": 30500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.74,
|
| 388 |
+
"learning_rate": 2.688496466237162e-06,
|
| 389 |
+
"loss": 0.3818,
|
| 390 |
+
"step": 31000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.77,
|
| 394 |
+
"learning_rate": 2.665329758212714e-06,
|
| 395 |
+
"loss": 0.384,
|
| 396 |
+
"step": 31500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.8,
|
| 400 |
+
"learning_rate": 2.6421630501882657e-06,
|
| 401 |
+
"loss": 0.3249,
|
| 402 |
+
"step": 32000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.83,
|
| 406 |
+
"learning_rate": 2.6189963421638186e-06,
|
| 407 |
+
"loss": 0.3385,
|
| 408 |
+
"step": 32500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.85,
|
| 412 |
+
"learning_rate": 2.5958296341393703e-06,
|
| 413 |
+
"loss": 0.3837,
|
| 414 |
+
"step": 33000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.88,
|
| 418 |
+
"learning_rate": 2.5726629261149224e-06,
|
| 419 |
+
"loss": 0.3224,
|
| 420 |
+
"step": 33500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.91,
|
| 424 |
+
"learning_rate": 2.549496218090475e-06,
|
| 425 |
+
"loss": 0.3555,
|
| 426 |
+
"step": 34000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.94,
|
| 430 |
+
"learning_rate": 2.526329510066027e-06,
|
| 431 |
+
"loss": 0.3555,
|
| 432 |
+
"step": 34500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.97,
|
| 436 |
+
"learning_rate": 2.50316280204158e-06,
|
| 437 |
+
"loss": 0.3487,
|
| 438 |
+
"step": 35000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.99,
|
| 442 |
+
"learning_rate": 2.4799960940171317e-06,
|
| 443 |
+
"loss": 0.3847,
|
| 444 |
+
"step": 35500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.0,
|
| 448 |
+
"eval_f1": 0.8587530820711519,
|
| 449 |
+
"eval_loss": 0.37445908784866333,
|
| 450 |
+
"eval_runtime": 7.6778,
|
| 451 |
+
"eval_samples_per_second": 515.253,
|
| 452 |
+
"eval_steps_per_second": 8.075,
|
| 453 |
+
"step": 35610
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.02,
|
| 457 |
+
"learning_rate": 2.4568293859926838e-06,
|
| 458 |
+
"loss": 0.3372,
|
| 459 |
+
"step": 36000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.05,
|
| 463 |
+
"learning_rate": 2.4336626779682363e-06,
|
| 464 |
+
"loss": 0.2759,
|
| 465 |
+
"step": 36500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.08,
|
| 469 |
+
"learning_rate": 2.4104959699437884e-06,
|
| 470 |
+
"loss": 0.2711,
|
| 471 |
+
"step": 37000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.11,
|
| 475 |
+
"learning_rate": 2.3873292619193405e-06,
|
| 476 |
+
"loss": 0.2879,
|
| 477 |
+
"step": 37500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.13,
|
| 481 |
+
"learning_rate": 2.364162553894893e-06,
|
| 482 |
+
"loss": 0.3026,
|
| 483 |
+
"step": 38000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.16,
|
| 487 |
+
"learning_rate": 2.340995845870445e-06,
|
| 488 |
+
"loss": 0.3108,
|
| 489 |
+
"step": 38500
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.19,
|
| 493 |
+
"learning_rate": 2.3178291378459972e-06,
|
| 494 |
+
"loss": 0.2571,
|
| 495 |
+
"step": 39000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.22,
|
| 499 |
+
"learning_rate": 2.2946624298215498e-06,
|
| 500 |
+
"loss": 0.3241,
|
| 501 |
+
"step": 39500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.25,
|
| 505 |
+
"learning_rate": 2.271495721797102e-06,
|
| 506 |
+
"loss": 0.2841,
|
| 507 |
+
"step": 40000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.27,
|
| 511 |
+
"learning_rate": 2.248329013772654e-06,
|
| 512 |
+
"loss": 0.2532,
|
| 513 |
+
"step": 40500
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.3,
|
| 517 |
+
"learning_rate": 2.2251623057482065e-06,
|
| 518 |
+
"loss": 0.3058,
|
| 519 |
+
"step": 41000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.33,
|
| 523 |
+
"learning_rate": 2.2019955977237586e-06,
|
| 524 |
+
"loss": 0.3036,
|
| 525 |
+
"step": 41500
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.36,
|
| 529 |
+
"learning_rate": 2.1788288896993107e-06,
|
| 530 |
+
"loss": 0.3087,
|
| 531 |
+
"step": 42000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.39,
|
| 535 |
+
"learning_rate": 2.1556621816748632e-06,
|
| 536 |
+
"loss": 0.2701,
|
| 537 |
+
"step": 42500
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.42,
|
| 541 |
+
"learning_rate": 2.1324954736504153e-06,
|
| 542 |
+
"loss": 0.3051,
|
| 543 |
+
"step": 43000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.44,
|
| 547 |
+
"learning_rate": 2.1093287656259674e-06,
|
| 548 |
+
"loss": 0.3005,
|
| 549 |
+
"step": 43500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.47,
|
| 553 |
+
"learning_rate": 2.08616205760152e-06,
|
| 554 |
+
"loss": 0.304,
|
| 555 |
+
"step": 44000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.5,
|
| 559 |
+
"learning_rate": 2.062995349577072e-06,
|
| 560 |
+
"loss": 0.2895,
|
| 561 |
+
"step": 44500
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.53,
|
| 565 |
+
"learning_rate": 2.0398286415526246e-06,
|
| 566 |
+
"loss": 0.2984,
|
| 567 |
+
"step": 45000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.56,
|
| 571 |
+
"learning_rate": 2.0166619335281767e-06,
|
| 572 |
+
"loss": 0.3043,
|
| 573 |
+
"step": 45500
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.58,
|
| 577 |
+
"learning_rate": 1.993495225503729e-06,
|
| 578 |
+
"loss": 0.2959,
|
| 579 |
+
"step": 46000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.61,
|
| 583 |
+
"learning_rate": 1.9703285174792813e-06,
|
| 584 |
+
"loss": 0.2765,
|
| 585 |
+
"step": 46500
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.64,
|
| 589 |
+
"learning_rate": 1.9471618094548334e-06,
|
| 590 |
+
"loss": 0.3272,
|
| 591 |
+
"step": 47000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.67,
|
| 595 |
+
"learning_rate": 1.923995101430386e-06,
|
| 596 |
+
"loss": 0.2409,
|
| 597 |
+
"step": 47500
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.7,
|
| 601 |
+
"learning_rate": 1.900828393405938e-06,
|
| 602 |
+
"loss": 0.3259,
|
| 603 |
+
"step": 48000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.72,
|
| 607 |
+
"learning_rate": 1.8776616853814904e-06,
|
| 608 |
+
"loss": 0.2934,
|
| 609 |
+
"step": 48500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.75,
|
| 613 |
+
"learning_rate": 1.8544949773570427e-06,
|
| 614 |
+
"loss": 0.2824,
|
| 615 |
+
"step": 49000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.78,
|
| 619 |
+
"learning_rate": 1.8313282693325946e-06,
|
| 620 |
+
"loss": 0.2821,
|
| 621 |
+
"step": 49500
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.81,
|
| 625 |
+
"learning_rate": 1.8081615613081469e-06,
|
| 626 |
+
"loss": 0.2954,
|
| 627 |
+
"step": 50000
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.84,
|
| 631 |
+
"learning_rate": 1.7849948532836992e-06,
|
| 632 |
+
"loss": 0.3067,
|
| 633 |
+
"step": 50500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.86,
|
| 637 |
+
"learning_rate": 1.7618281452592513e-06,
|
| 638 |
+
"loss": 0.3159,
|
| 639 |
+
"step": 51000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.89,
|
| 643 |
+
"learning_rate": 1.7386614372348036e-06,
|
| 644 |
+
"loss": 0.3052,
|
| 645 |
+
"step": 51500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 2.92,
|
| 649 |
+
"learning_rate": 1.715494729210356e-06,
|
| 650 |
+
"loss": 0.2831,
|
| 651 |
+
"step": 52000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 2.95,
|
| 655 |
+
"learning_rate": 1.6923280211859083e-06,
|
| 656 |
+
"loss": 0.3139,
|
| 657 |
+
"step": 52500
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 2.98,
|
| 661 |
+
"learning_rate": 1.6691613131614604e-06,
|
| 662 |
+
"loss": 0.2793,
|
| 663 |
+
"step": 53000
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 3.0,
|
| 667 |
+
"eval_f1": 0.8650239058477381,
|
| 668 |
+
"eval_loss": 0.42799684405326843,
|
| 669 |
+
"eval_runtime": 7.6499,
|
| 670 |
+
"eval_samples_per_second": 517.128,
|
| 671 |
+
"eval_steps_per_second": 8.105,
|
| 672 |
+
"step": 53415
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 3.0,
|
| 676 |
+
"learning_rate": 1.6459946051370127e-06,
|
| 677 |
+
"loss": 0.2997,
|
| 678 |
+
"step": 53500
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 3.03,
|
| 682 |
+
"learning_rate": 1.622827897112565e-06,
|
| 683 |
+
"loss": 0.2635,
|
| 684 |
+
"step": 54000
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 3.06,
|
| 688 |
+
"learning_rate": 1.599661189088117e-06,
|
| 689 |
+
"loss": 0.2274,
|
| 690 |
+
"step": 54500
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 3.09,
|
| 694 |
+
"learning_rate": 1.5764944810636694e-06,
|
| 695 |
+
"loss": 0.2295,
|
| 696 |
+
"step": 55000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 3.12,
|
| 700 |
+
"learning_rate": 1.5533277730392217e-06,
|
| 701 |
+
"loss": 0.2545,
|
| 702 |
+
"step": 55500
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 3.15,
|
| 706 |
+
"learning_rate": 1.5301610650147738e-06,
|
| 707 |
+
"loss": 0.2876,
|
| 708 |
+
"step": 56000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 3.17,
|
| 712 |
+
"learning_rate": 1.5069943569903261e-06,
|
| 713 |
+
"loss": 0.2196,
|
| 714 |
+
"step": 56500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 3.2,
|
| 718 |
+
"learning_rate": 1.4838276489658785e-06,
|
| 719 |
+
"loss": 0.2114,
|
| 720 |
+
"step": 57000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 3.23,
|
| 724 |
+
"learning_rate": 1.4606609409414308e-06,
|
| 725 |
+
"loss": 0.2751,
|
| 726 |
+
"step": 57500
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 3.26,
|
| 730 |
+
"learning_rate": 1.4374942329169829e-06,
|
| 731 |
+
"loss": 0.2434,
|
| 732 |
+
"step": 58000
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 3.29,
|
| 736 |
+
"learning_rate": 1.4143275248925352e-06,
|
| 737 |
+
"loss": 0.2522,
|
| 738 |
+
"step": 58500
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 3.31,
|
| 742 |
+
"learning_rate": 1.3911608168680875e-06,
|
| 743 |
+
"loss": 0.2401,
|
| 744 |
+
"step": 59000
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 3.34,
|
| 748 |
+
"learning_rate": 1.3679941088436396e-06,
|
| 749 |
+
"loss": 0.2415,
|
| 750 |
+
"step": 59500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 3.37,
|
| 754 |
+
"learning_rate": 1.344827400819192e-06,
|
| 755 |
+
"loss": 0.2367,
|
| 756 |
+
"step": 60000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 3.4,
|
| 760 |
+
"learning_rate": 1.3216606927947442e-06,
|
| 761 |
+
"loss": 0.2814,
|
| 762 |
+
"step": 60500
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 3.43,
|
| 766 |
+
"learning_rate": 1.2984939847702963e-06,
|
| 767 |
+
"loss": 0.2575,
|
| 768 |
+
"step": 61000
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 3.45,
|
| 772 |
+
"learning_rate": 1.2753272767458487e-06,
|
| 773 |
+
"loss": 0.2205,
|
| 774 |
+
"step": 61500
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 3.48,
|
| 778 |
+
"learning_rate": 1.252160568721401e-06,
|
| 779 |
+
"loss": 0.2591,
|
| 780 |
+
"step": 62000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 3.51,
|
| 784 |
+
"learning_rate": 1.2289938606969533e-06,
|
| 785 |
+
"loss": 0.2698,
|
| 786 |
+
"step": 62500
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 3.54,
|
| 790 |
+
"learning_rate": 1.2058271526725054e-06,
|
| 791 |
+
"loss": 0.2357,
|
| 792 |
+
"step": 63000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 3.57,
|
| 796 |
+
"learning_rate": 1.1826604446480577e-06,
|
| 797 |
+
"loss": 0.2996,
|
| 798 |
+
"step": 63500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 3.59,
|
| 802 |
+
"learning_rate": 1.15949373662361e-06,
|
| 803 |
+
"loss": 0.2376,
|
| 804 |
+
"step": 64000
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 3.62,
|
| 808 |
+
"learning_rate": 1.1363270285991621e-06,
|
| 809 |
+
"loss": 0.2669,
|
| 810 |
+
"step": 64500
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 3.65,
|
| 814 |
+
"learning_rate": 1.1131603205747144e-06,
|
| 815 |
+
"loss": 0.2397,
|
| 816 |
+
"step": 65000
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 3.68,
|
| 820 |
+
"learning_rate": 1.0899936125502668e-06,
|
| 821 |
+
"loss": 0.2992,
|
| 822 |
+
"step": 65500
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 3.71,
|
| 826 |
+
"learning_rate": 1.0668269045258189e-06,
|
| 827 |
+
"loss": 0.2461,
|
| 828 |
+
"step": 66000
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 3.73,
|
| 832 |
+
"learning_rate": 1.0436601965013712e-06,
|
| 833 |
+
"loss": 0.2428,
|
| 834 |
+
"step": 66500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 3.76,
|
| 838 |
+
"learning_rate": 1.0204934884769235e-06,
|
| 839 |
+
"loss": 0.247,
|
| 840 |
+
"step": 67000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 3.79,
|
| 844 |
+
"learning_rate": 9.973267804524756e-07,
|
| 845 |
+
"loss": 0.2314,
|
| 846 |
+
"step": 67500
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 3.82,
|
| 850 |
+
"learning_rate": 9.74160072428028e-07,
|
| 851 |
+
"loss": 0.2612,
|
| 852 |
+
"step": 68000
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 3.85,
|
| 856 |
+
"learning_rate": 9.509933644035802e-07,
|
| 857 |
+
"loss": 0.2359,
|
| 858 |
+
"step": 68500
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 3.88,
|
| 862 |
+
"learning_rate": 9.278266563791324e-07,
|
| 863 |
+
"loss": 0.2528,
|
| 864 |
+
"step": 69000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.9,
|
| 868 |
+
"learning_rate": 9.046599483546847e-07,
|
| 869 |
+
"loss": 0.2561,
|
| 870 |
+
"step": 69500
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 3.93,
|
| 874 |
+
"learning_rate": 8.81493240330237e-07,
|
| 875 |
+
"loss": 0.2419,
|
| 876 |
+
"step": 70000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 3.96,
|
| 880 |
+
"learning_rate": 8.583265323057893e-07,
|
| 881 |
+
"loss": 0.2497,
|
| 882 |
+
"step": 70500
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 3.99,
|
| 886 |
+
"learning_rate": 8.351598242813415e-07,
|
| 887 |
+
"loss": 0.2443,
|
| 888 |
+
"step": 71000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 4.0,
|
| 892 |
+
"eval_f1": 0.8682891911238368,
|
| 893 |
+
"eval_loss": 0.45183292031288147,
|
| 894 |
+
"eval_runtime": 7.6556,
|
| 895 |
+
"eval_samples_per_second": 516.746,
|
| 896 |
+
"eval_steps_per_second": 8.099,
|
| 897 |
+
"step": 71220
|
| 898 |
+
}
|
| 899 |
+
],
|
| 900 |
+
"logging_steps": 500,
|
| 901 |
+
"max_steps": 89025,
|
| 902 |
+
"num_input_tokens_seen": 0,
|
| 903 |
+
"num_train_epochs": 5,
|
| 904 |
+
"save_steps": 500,
|
| 905 |
+
"total_flos": 1.1179145500237356e+16,
|
| 906 |
+
"train_batch_size": 4,
|
| 907 |
+
"trial_name": null,
|
| 908 |
+
"trial_params": {
|
| 909 |
+
"learning_rate": 4.124832363752922e-06,
|
| 910 |
+
"num_train_epochs": 5,
|
| 911 |
+
"per_device_train_batch_size": 4,
|
| 912 |
+
"seed": 40
|
| 913 |
+
}
|
| 914 |
+
}
|
run-1/checkpoint-71220/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1edfb4d32c4b440688a42ad772fd577e72d0a24c0764a9f6c27730006d6a58ce
|
| 3 |
+
size 4664
|
run-1/checkpoint-71220/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-1/checkpoint-89025/config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "distilbert-base-uncased",
|
| 3 |
+
"activation": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"DistilBertForSequenceClassification"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.1,
|
| 8 |
+
"dim": 768,
|
| 9 |
+
"dropout": 0.1,
|
| 10 |
+
"hidden_dim": 3072,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"max_position_embeddings": 512,
|
| 13 |
+
"model_type": "distilbert",
|
| 14 |
+
"n_heads": 12,
|
| 15 |
+
"n_layers": 6,
|
| 16 |
+
"pad_token_id": 0,
|
| 17 |
+
"problem_type": "single_label_classification",
|
| 18 |
+
"qa_dropout": 0.1,
|
| 19 |
+
"seq_classif_dropout": 0.2,
|
| 20 |
+
"sinusoidal_pos_embds": false,
|
| 21 |
+
"tie_weights_": true,
|
| 22 |
+
"torch_dtype": "float32",
|
| 23 |
+
"transformers_version": "4.37.2",
|
| 24 |
+
"vocab_size": 30522
|
| 25 |
+
}
|
run-1/checkpoint-89025/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f01f7cef356e9f7dd9016e977775fbe8615620db02eef11a9e70f7f65a1d6705
|
| 3 |
+
size 267832560
|
run-1/checkpoint-89025/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cd6ddb893fd8ec24d3db2c41201e233043a7793133f63e4086307fd6a0458d12
|
| 3 |
+
size 535727290
|
run-1/checkpoint-89025/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc0fbd2aabcfe56b22e15f0bfea8c0c2a9d9d82f977cb072cfa8491491df7c60
|
| 3 |
+
size 14244
|
run-1/checkpoint-89025/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c4d57929db090339d74faed2e919e91be55722366a5e016712fc41c4c0415a68
|
| 3 |
+
size 1064
|
run-1/checkpoint-89025/special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
run-1/checkpoint-89025/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-1/checkpoint-89025/tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"100": {
|
| 12 |
+
"content": "[UNK]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"101": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"102": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"103": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
+
"clean_up_tokenization_spaces": true,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"mask_token": "[MASK]",
|
| 48 |
+
"model_max_length": 512,
|
| 49 |
+
"pad_token": "[PAD]",
|
| 50 |
+
"sep_token": "[SEP]",
|
| 51 |
+
"strip_accents": null,
|
| 52 |
+
"tokenize_chinese_chars": true,
|
| 53 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 54 |
+
"unk_token": "[UNK]"
|
| 55 |
+
}
|
run-1/checkpoint-89025/trainer_state.json
ADDED
|
@@ -0,0 +1,1139 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8682891911238368,
|
| 3 |
+
"best_model_checkpoint": "relevant_model/run-1/checkpoint-71220",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 89025,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 4.101665655728474e-06,
|
| 14 |
+
"loss": 0.5111,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"learning_rate": 4.078498947704027e-06,
|
| 20 |
+
"loss": 0.4216,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.08,
|
| 25 |
+
"learning_rate": 4.0553322396795785e-06,
|
| 26 |
+
"loss": 0.4711,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.11,
|
| 31 |
+
"learning_rate": 4.0321655316551306e-06,
|
| 32 |
+
"loss": 0.4472,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.14,
|
| 37 |
+
"learning_rate": 4.0089988236306835e-06,
|
| 38 |
+
"loss": 0.4429,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.17,
|
| 43 |
+
"learning_rate": 3.985832115606236e-06,
|
| 44 |
+
"loss": 0.5083,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.2,
|
| 49 |
+
"learning_rate": 3.962665407581788e-06,
|
| 50 |
+
"loss": 0.469,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.22,
|
| 55 |
+
"learning_rate": 3.93949869955734e-06,
|
| 56 |
+
"loss": 0.4424,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.25,
|
| 61 |
+
"learning_rate": 3.916331991532892e-06,
|
| 62 |
+
"loss": 0.472,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.28,
|
| 67 |
+
"learning_rate": 3.893165283508445e-06,
|
| 68 |
+
"loss": 0.4344,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.31,
|
| 73 |
+
"learning_rate": 3.869998575483997e-06,
|
| 74 |
+
"loss": 0.4255,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.34,
|
| 79 |
+
"learning_rate": 3.846831867459549e-06,
|
| 80 |
+
"loss": 0.4293,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.37,
|
| 85 |
+
"learning_rate": 3.823665159435101e-06,
|
| 86 |
+
"loss": 0.4581,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.39,
|
| 91 |
+
"learning_rate": 3.8004984514106537e-06,
|
| 92 |
+
"loss": 0.4235,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.42,
|
| 97 |
+
"learning_rate": 3.777331743386206e-06,
|
| 98 |
+
"loss": 0.4334,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.45,
|
| 103 |
+
"learning_rate": 3.7541650353617583e-06,
|
| 104 |
+
"loss": 0.3703,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.48,
|
| 109 |
+
"learning_rate": 3.7309983273373104e-06,
|
| 110 |
+
"loss": 0.4415,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.51,
|
| 115 |
+
"learning_rate": 3.7078316193128626e-06,
|
| 116 |
+
"loss": 0.4234,
|
| 117 |
+
"step": 9000
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.53,
|
| 121 |
+
"learning_rate": 3.684664911288415e-06,
|
| 122 |
+
"loss": 0.4184,
|
| 123 |
+
"step": 9500
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.56,
|
| 127 |
+
"learning_rate": 3.661498203263967e-06,
|
| 128 |
+
"loss": 0.3912,
|
| 129 |
+
"step": 10000
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.59,
|
| 133 |
+
"learning_rate": 3.6383314952395193e-06,
|
| 134 |
+
"loss": 0.4158,
|
| 135 |
+
"step": 10500
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.62,
|
| 139 |
+
"learning_rate": 3.615164787215072e-06,
|
| 140 |
+
"loss": 0.3966,
|
| 141 |
+
"step": 11000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.65,
|
| 145 |
+
"learning_rate": 3.591998079190624e-06,
|
| 146 |
+
"loss": 0.4171,
|
| 147 |
+
"step": 11500
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.67,
|
| 151 |
+
"learning_rate": 3.568831371166176e-06,
|
| 152 |
+
"loss": 0.381,
|
| 153 |
+
"step": 12000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.7,
|
| 157 |
+
"learning_rate": 3.5456646631417285e-06,
|
| 158 |
+
"loss": 0.3867,
|
| 159 |
+
"step": 12500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.73,
|
| 163 |
+
"learning_rate": 3.5224979551172806e-06,
|
| 164 |
+
"loss": 0.4438,
|
| 165 |
+
"step": 13000
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.76,
|
| 169 |
+
"learning_rate": 3.4993312470928328e-06,
|
| 170 |
+
"loss": 0.3806,
|
| 171 |
+
"step": 13500
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.79,
|
| 175 |
+
"learning_rate": 3.4761645390683853e-06,
|
| 176 |
+
"loss": 0.391,
|
| 177 |
+
"step": 14000
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.81,
|
| 181 |
+
"learning_rate": 3.4529978310439374e-06,
|
| 182 |
+
"loss": 0.3947,
|
| 183 |
+
"step": 14500
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.84,
|
| 187 |
+
"learning_rate": 3.42983112301949e-06,
|
| 188 |
+
"loss": 0.397,
|
| 189 |
+
"step": 15000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.87,
|
| 193 |
+
"learning_rate": 3.406664414995042e-06,
|
| 194 |
+
"loss": 0.4048,
|
| 195 |
+
"step": 15500
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.9,
|
| 199 |
+
"learning_rate": 3.383497706970594e-06,
|
| 200 |
+
"loss": 0.4648,
|
| 201 |
+
"step": 16000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.93,
|
| 205 |
+
"learning_rate": 3.3603309989461466e-06,
|
| 206 |
+
"loss": 0.3751,
|
| 207 |
+
"step": 16500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.95,
|
| 211 |
+
"learning_rate": 3.3371642909216987e-06,
|
| 212 |
+
"loss": 0.3951,
|
| 213 |
+
"step": 17000
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.98,
|
| 217 |
+
"learning_rate": 3.313997582897251e-06,
|
| 218 |
+
"loss": 0.4386,
|
| 219 |
+
"step": 17500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.0,
|
| 223 |
+
"eval_f1": 0.8416666666666667,
|
| 224 |
+
"eval_loss": 0.3926413059234619,
|
| 225 |
+
"eval_runtime": 7.7212,
|
| 226 |
+
"eval_samples_per_second": 512.357,
|
| 227 |
+
"eval_steps_per_second": 8.03,
|
| 228 |
+
"step": 17805
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.01,
|
| 232 |
+
"learning_rate": 3.2908308748728034e-06,
|
| 233 |
+
"loss": 0.3639,
|
| 234 |
+
"step": 18000
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 1.04,
|
| 238 |
+
"learning_rate": 3.2676641668483555e-06,
|
| 239 |
+
"loss": 0.372,
|
| 240 |
+
"step": 18500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.07,
|
| 244 |
+
"learning_rate": 3.2444974588239076e-06,
|
| 245 |
+
"loss": 0.3249,
|
| 246 |
+
"step": 19000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 1.1,
|
| 250 |
+
"learning_rate": 3.22133075079946e-06,
|
| 251 |
+
"loss": 0.3586,
|
| 252 |
+
"step": 19500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.12,
|
| 256 |
+
"learning_rate": 3.1981640427750122e-06,
|
| 257 |
+
"loss": 0.3595,
|
| 258 |
+
"step": 20000
|
| 259 |
+
},
|
| 260 |
+
{
|
| 261 |
+
"epoch": 1.15,
|
| 262 |
+
"learning_rate": 3.1749973347505643e-06,
|
| 263 |
+
"loss": 0.3577,
|
| 264 |
+
"step": 20500
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 1.18,
|
| 268 |
+
"learning_rate": 3.151830626726117e-06,
|
| 269 |
+
"loss": 0.3505,
|
| 270 |
+
"step": 21000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.21,
|
| 274 |
+
"learning_rate": 3.128663918701669e-06,
|
| 275 |
+
"loss": 0.3448,
|
| 276 |
+
"step": 21500
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 1.24,
|
| 280 |
+
"learning_rate": 3.105497210677221e-06,
|
| 281 |
+
"loss": 0.3726,
|
| 282 |
+
"step": 22000
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 1.26,
|
| 286 |
+
"learning_rate": 3.0823305026527736e-06,
|
| 287 |
+
"loss": 0.3522,
|
| 288 |
+
"step": 22500
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.29,
|
| 292 |
+
"learning_rate": 3.0591637946283257e-06,
|
| 293 |
+
"loss": 0.3814,
|
| 294 |
+
"step": 23000
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 1.32,
|
| 298 |
+
"learning_rate": 3.0359970866038778e-06,
|
| 299 |
+
"loss": 0.3641,
|
| 300 |
+
"step": 23500
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 1.35,
|
| 304 |
+
"learning_rate": 3.0128303785794303e-06,
|
| 305 |
+
"loss": 0.343,
|
| 306 |
+
"step": 24000
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.38,
|
| 310 |
+
"learning_rate": 2.9896636705549824e-06,
|
| 311 |
+
"loss": 0.331,
|
| 312 |
+
"step": 24500
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 1.4,
|
| 316 |
+
"learning_rate": 2.966496962530535e-06,
|
| 317 |
+
"loss": 0.3737,
|
| 318 |
+
"step": 25000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.43,
|
| 322 |
+
"learning_rate": 2.943330254506087e-06,
|
| 323 |
+
"loss": 0.3437,
|
| 324 |
+
"step": 25500
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 1.46,
|
| 328 |
+
"learning_rate": 2.920163546481639e-06,
|
| 329 |
+
"loss": 0.3648,
|
| 330 |
+
"step": 26000
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"epoch": 1.49,
|
| 334 |
+
"learning_rate": 2.8969968384571917e-06,
|
| 335 |
+
"loss": 0.3421,
|
| 336 |
+
"step": 26500
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"epoch": 1.52,
|
| 340 |
+
"learning_rate": 2.8738301304327438e-06,
|
| 341 |
+
"loss": 0.3344,
|
| 342 |
+
"step": 27000
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 1.54,
|
| 346 |
+
"learning_rate": 2.850663422408296e-06,
|
| 347 |
+
"loss": 0.3533,
|
| 348 |
+
"step": 27500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 1.57,
|
| 352 |
+
"learning_rate": 2.8274967143838484e-06,
|
| 353 |
+
"loss": 0.371,
|
| 354 |
+
"step": 28000
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 1.6,
|
| 358 |
+
"learning_rate": 2.8043300063594005e-06,
|
| 359 |
+
"loss": 0.3526,
|
| 360 |
+
"step": 28500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.63,
|
| 364 |
+
"learning_rate": 2.7811632983349526e-06,
|
| 365 |
+
"loss": 0.3539,
|
| 366 |
+
"step": 29000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 1.66,
|
| 370 |
+
"learning_rate": 2.757996590310505e-06,
|
| 371 |
+
"loss": 0.3692,
|
| 372 |
+
"step": 29500
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 1.68,
|
| 376 |
+
"learning_rate": 2.7348298822860572e-06,
|
| 377 |
+
"loss": 0.3104,
|
| 378 |
+
"step": 30000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 1.71,
|
| 382 |
+
"learning_rate": 2.7116631742616094e-06,
|
| 383 |
+
"loss": 0.3371,
|
| 384 |
+
"step": 30500
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 1.74,
|
| 388 |
+
"learning_rate": 2.688496466237162e-06,
|
| 389 |
+
"loss": 0.3818,
|
| 390 |
+
"step": 31000
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 1.77,
|
| 394 |
+
"learning_rate": 2.665329758212714e-06,
|
| 395 |
+
"loss": 0.384,
|
| 396 |
+
"step": 31500
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 1.8,
|
| 400 |
+
"learning_rate": 2.6421630501882657e-06,
|
| 401 |
+
"loss": 0.3249,
|
| 402 |
+
"step": 32000
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 1.83,
|
| 406 |
+
"learning_rate": 2.6189963421638186e-06,
|
| 407 |
+
"loss": 0.3385,
|
| 408 |
+
"step": 32500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 1.85,
|
| 412 |
+
"learning_rate": 2.5958296341393703e-06,
|
| 413 |
+
"loss": 0.3837,
|
| 414 |
+
"step": 33000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 1.88,
|
| 418 |
+
"learning_rate": 2.5726629261149224e-06,
|
| 419 |
+
"loss": 0.3224,
|
| 420 |
+
"step": 33500
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 1.91,
|
| 424 |
+
"learning_rate": 2.549496218090475e-06,
|
| 425 |
+
"loss": 0.3555,
|
| 426 |
+
"step": 34000
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 1.94,
|
| 430 |
+
"learning_rate": 2.526329510066027e-06,
|
| 431 |
+
"loss": 0.3555,
|
| 432 |
+
"step": 34500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.97,
|
| 436 |
+
"learning_rate": 2.50316280204158e-06,
|
| 437 |
+
"loss": 0.3487,
|
| 438 |
+
"step": 35000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 1.99,
|
| 442 |
+
"learning_rate": 2.4799960940171317e-06,
|
| 443 |
+
"loss": 0.3847,
|
| 444 |
+
"step": 35500
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 2.0,
|
| 448 |
+
"eval_f1": 0.8587530820711519,
|
| 449 |
+
"eval_loss": 0.37445908784866333,
|
| 450 |
+
"eval_runtime": 7.6778,
|
| 451 |
+
"eval_samples_per_second": 515.253,
|
| 452 |
+
"eval_steps_per_second": 8.075,
|
| 453 |
+
"step": 35610
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.02,
|
| 457 |
+
"learning_rate": 2.4568293859926838e-06,
|
| 458 |
+
"loss": 0.3372,
|
| 459 |
+
"step": 36000
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.05,
|
| 463 |
+
"learning_rate": 2.4336626779682363e-06,
|
| 464 |
+
"loss": 0.2759,
|
| 465 |
+
"step": 36500
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.08,
|
| 469 |
+
"learning_rate": 2.4104959699437884e-06,
|
| 470 |
+
"loss": 0.2711,
|
| 471 |
+
"step": 37000
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.11,
|
| 475 |
+
"learning_rate": 2.3873292619193405e-06,
|
| 476 |
+
"loss": 0.2879,
|
| 477 |
+
"step": 37500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.13,
|
| 481 |
+
"learning_rate": 2.364162553894893e-06,
|
| 482 |
+
"loss": 0.3026,
|
| 483 |
+
"step": 38000
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.16,
|
| 487 |
+
"learning_rate": 2.340995845870445e-06,
|
| 488 |
+
"loss": 0.3108,
|
| 489 |
+
"step": 38500
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.19,
|
| 493 |
+
"learning_rate": 2.3178291378459972e-06,
|
| 494 |
+
"loss": 0.2571,
|
| 495 |
+
"step": 39000
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.22,
|
| 499 |
+
"learning_rate": 2.2946624298215498e-06,
|
| 500 |
+
"loss": 0.3241,
|
| 501 |
+
"step": 39500
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.25,
|
| 505 |
+
"learning_rate": 2.271495721797102e-06,
|
| 506 |
+
"loss": 0.2841,
|
| 507 |
+
"step": 40000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.27,
|
| 511 |
+
"learning_rate": 2.248329013772654e-06,
|
| 512 |
+
"loss": 0.2532,
|
| 513 |
+
"step": 40500
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.3,
|
| 517 |
+
"learning_rate": 2.2251623057482065e-06,
|
| 518 |
+
"loss": 0.3058,
|
| 519 |
+
"step": 41000
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.33,
|
| 523 |
+
"learning_rate": 2.2019955977237586e-06,
|
| 524 |
+
"loss": 0.3036,
|
| 525 |
+
"step": 41500
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.36,
|
| 529 |
+
"learning_rate": 2.1788288896993107e-06,
|
| 530 |
+
"loss": 0.3087,
|
| 531 |
+
"step": 42000
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.39,
|
| 535 |
+
"learning_rate": 2.1556621816748632e-06,
|
| 536 |
+
"loss": 0.2701,
|
| 537 |
+
"step": 42500
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.42,
|
| 541 |
+
"learning_rate": 2.1324954736504153e-06,
|
| 542 |
+
"loss": 0.3051,
|
| 543 |
+
"step": 43000
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.44,
|
| 547 |
+
"learning_rate": 2.1093287656259674e-06,
|
| 548 |
+
"loss": 0.3005,
|
| 549 |
+
"step": 43500
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.47,
|
| 553 |
+
"learning_rate": 2.08616205760152e-06,
|
| 554 |
+
"loss": 0.304,
|
| 555 |
+
"step": 44000
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.5,
|
| 559 |
+
"learning_rate": 2.062995349577072e-06,
|
| 560 |
+
"loss": 0.2895,
|
| 561 |
+
"step": 44500
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.53,
|
| 565 |
+
"learning_rate": 2.0398286415526246e-06,
|
| 566 |
+
"loss": 0.2984,
|
| 567 |
+
"step": 45000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.56,
|
| 571 |
+
"learning_rate": 2.0166619335281767e-06,
|
| 572 |
+
"loss": 0.3043,
|
| 573 |
+
"step": 45500
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.58,
|
| 577 |
+
"learning_rate": 1.993495225503729e-06,
|
| 578 |
+
"loss": 0.2959,
|
| 579 |
+
"step": 46000
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.61,
|
| 583 |
+
"learning_rate": 1.9703285174792813e-06,
|
| 584 |
+
"loss": 0.2765,
|
| 585 |
+
"step": 46500
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 2.64,
|
| 589 |
+
"learning_rate": 1.9471618094548334e-06,
|
| 590 |
+
"loss": 0.3272,
|
| 591 |
+
"step": 47000
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 2.67,
|
| 595 |
+
"learning_rate": 1.923995101430386e-06,
|
| 596 |
+
"loss": 0.2409,
|
| 597 |
+
"step": 47500
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 2.7,
|
| 601 |
+
"learning_rate": 1.900828393405938e-06,
|
| 602 |
+
"loss": 0.3259,
|
| 603 |
+
"step": 48000
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 2.72,
|
| 607 |
+
"learning_rate": 1.8776616853814904e-06,
|
| 608 |
+
"loss": 0.2934,
|
| 609 |
+
"step": 48500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 2.75,
|
| 613 |
+
"learning_rate": 1.8544949773570427e-06,
|
| 614 |
+
"loss": 0.2824,
|
| 615 |
+
"step": 49000
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 2.78,
|
| 619 |
+
"learning_rate": 1.8313282693325946e-06,
|
| 620 |
+
"loss": 0.2821,
|
| 621 |
+
"step": 49500
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 2.81,
|
| 625 |
+
"learning_rate": 1.8081615613081469e-06,
|
| 626 |
+
"loss": 0.2954,
|
| 627 |
+
"step": 50000
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 2.84,
|
| 631 |
+
"learning_rate": 1.7849948532836992e-06,
|
| 632 |
+
"loss": 0.3067,
|
| 633 |
+
"step": 50500
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 2.86,
|
| 637 |
+
"learning_rate": 1.7618281452592513e-06,
|
| 638 |
+
"loss": 0.3159,
|
| 639 |
+
"step": 51000
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 2.89,
|
| 643 |
+
"learning_rate": 1.7386614372348036e-06,
|
| 644 |
+
"loss": 0.3052,
|
| 645 |
+
"step": 51500
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 2.92,
|
| 649 |
+
"learning_rate": 1.715494729210356e-06,
|
| 650 |
+
"loss": 0.2831,
|
| 651 |
+
"step": 52000
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 2.95,
|
| 655 |
+
"learning_rate": 1.6923280211859083e-06,
|
| 656 |
+
"loss": 0.3139,
|
| 657 |
+
"step": 52500
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 2.98,
|
| 661 |
+
"learning_rate": 1.6691613131614604e-06,
|
| 662 |
+
"loss": 0.2793,
|
| 663 |
+
"step": 53000
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 3.0,
|
| 667 |
+
"eval_f1": 0.8650239058477381,
|
| 668 |
+
"eval_loss": 0.42799684405326843,
|
| 669 |
+
"eval_runtime": 7.6499,
|
| 670 |
+
"eval_samples_per_second": 517.128,
|
| 671 |
+
"eval_steps_per_second": 8.105,
|
| 672 |
+
"step": 53415
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 3.0,
|
| 676 |
+
"learning_rate": 1.6459946051370127e-06,
|
| 677 |
+
"loss": 0.2997,
|
| 678 |
+
"step": 53500
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 3.03,
|
| 682 |
+
"learning_rate": 1.622827897112565e-06,
|
| 683 |
+
"loss": 0.2635,
|
| 684 |
+
"step": 54000
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 3.06,
|
| 688 |
+
"learning_rate": 1.599661189088117e-06,
|
| 689 |
+
"loss": 0.2274,
|
| 690 |
+
"step": 54500
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 3.09,
|
| 694 |
+
"learning_rate": 1.5764944810636694e-06,
|
| 695 |
+
"loss": 0.2295,
|
| 696 |
+
"step": 55000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 3.12,
|
| 700 |
+
"learning_rate": 1.5533277730392217e-06,
|
| 701 |
+
"loss": 0.2545,
|
| 702 |
+
"step": 55500
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 3.15,
|
| 706 |
+
"learning_rate": 1.5301610650147738e-06,
|
| 707 |
+
"loss": 0.2876,
|
| 708 |
+
"step": 56000
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 3.17,
|
| 712 |
+
"learning_rate": 1.5069943569903261e-06,
|
| 713 |
+
"loss": 0.2196,
|
| 714 |
+
"step": 56500
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 3.2,
|
| 718 |
+
"learning_rate": 1.4838276489658785e-06,
|
| 719 |
+
"loss": 0.2114,
|
| 720 |
+
"step": 57000
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"epoch": 3.23,
|
| 724 |
+
"learning_rate": 1.4606609409414308e-06,
|
| 725 |
+
"loss": 0.2751,
|
| 726 |
+
"step": 57500
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 3.26,
|
| 730 |
+
"learning_rate": 1.4374942329169829e-06,
|
| 731 |
+
"loss": 0.2434,
|
| 732 |
+
"step": 58000
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 3.29,
|
| 736 |
+
"learning_rate": 1.4143275248925352e-06,
|
| 737 |
+
"loss": 0.2522,
|
| 738 |
+
"step": 58500
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 3.31,
|
| 742 |
+
"learning_rate": 1.3911608168680875e-06,
|
| 743 |
+
"loss": 0.2401,
|
| 744 |
+
"step": 59000
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 3.34,
|
| 748 |
+
"learning_rate": 1.3679941088436396e-06,
|
| 749 |
+
"loss": 0.2415,
|
| 750 |
+
"step": 59500
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 3.37,
|
| 754 |
+
"learning_rate": 1.344827400819192e-06,
|
| 755 |
+
"loss": 0.2367,
|
| 756 |
+
"step": 60000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 3.4,
|
| 760 |
+
"learning_rate": 1.3216606927947442e-06,
|
| 761 |
+
"loss": 0.2814,
|
| 762 |
+
"step": 60500
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 3.43,
|
| 766 |
+
"learning_rate": 1.2984939847702963e-06,
|
| 767 |
+
"loss": 0.2575,
|
| 768 |
+
"step": 61000
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 3.45,
|
| 772 |
+
"learning_rate": 1.2753272767458487e-06,
|
| 773 |
+
"loss": 0.2205,
|
| 774 |
+
"step": 61500
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 3.48,
|
| 778 |
+
"learning_rate": 1.252160568721401e-06,
|
| 779 |
+
"loss": 0.2591,
|
| 780 |
+
"step": 62000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 3.51,
|
| 784 |
+
"learning_rate": 1.2289938606969533e-06,
|
| 785 |
+
"loss": 0.2698,
|
| 786 |
+
"step": 62500
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"epoch": 3.54,
|
| 790 |
+
"learning_rate": 1.2058271526725054e-06,
|
| 791 |
+
"loss": 0.2357,
|
| 792 |
+
"step": 63000
|
| 793 |
+
},
|
| 794 |
+
{
|
| 795 |
+
"epoch": 3.57,
|
| 796 |
+
"learning_rate": 1.1826604446480577e-06,
|
| 797 |
+
"loss": 0.2996,
|
| 798 |
+
"step": 63500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 3.59,
|
| 802 |
+
"learning_rate": 1.15949373662361e-06,
|
| 803 |
+
"loss": 0.2376,
|
| 804 |
+
"step": 64000
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 3.62,
|
| 808 |
+
"learning_rate": 1.1363270285991621e-06,
|
| 809 |
+
"loss": 0.2669,
|
| 810 |
+
"step": 64500
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 3.65,
|
| 814 |
+
"learning_rate": 1.1131603205747144e-06,
|
| 815 |
+
"loss": 0.2397,
|
| 816 |
+
"step": 65000
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 3.68,
|
| 820 |
+
"learning_rate": 1.0899936125502668e-06,
|
| 821 |
+
"loss": 0.2992,
|
| 822 |
+
"step": 65500
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 3.71,
|
| 826 |
+
"learning_rate": 1.0668269045258189e-06,
|
| 827 |
+
"loss": 0.2461,
|
| 828 |
+
"step": 66000
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 3.73,
|
| 832 |
+
"learning_rate": 1.0436601965013712e-06,
|
| 833 |
+
"loss": 0.2428,
|
| 834 |
+
"step": 66500
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 3.76,
|
| 838 |
+
"learning_rate": 1.0204934884769235e-06,
|
| 839 |
+
"loss": 0.247,
|
| 840 |
+
"step": 67000
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 3.79,
|
| 844 |
+
"learning_rate": 9.973267804524756e-07,
|
| 845 |
+
"loss": 0.2314,
|
| 846 |
+
"step": 67500
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 3.82,
|
| 850 |
+
"learning_rate": 9.74160072428028e-07,
|
| 851 |
+
"loss": 0.2612,
|
| 852 |
+
"step": 68000
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 3.85,
|
| 856 |
+
"learning_rate": 9.509933644035802e-07,
|
| 857 |
+
"loss": 0.2359,
|
| 858 |
+
"step": 68500
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 3.88,
|
| 862 |
+
"learning_rate": 9.278266563791324e-07,
|
| 863 |
+
"loss": 0.2528,
|
| 864 |
+
"step": 69000
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 3.9,
|
| 868 |
+
"learning_rate": 9.046599483546847e-07,
|
| 869 |
+
"loss": 0.2561,
|
| 870 |
+
"step": 69500
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 3.93,
|
| 874 |
+
"learning_rate": 8.81493240330237e-07,
|
| 875 |
+
"loss": 0.2419,
|
| 876 |
+
"step": 70000
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 3.96,
|
| 880 |
+
"learning_rate": 8.583265323057893e-07,
|
| 881 |
+
"loss": 0.2497,
|
| 882 |
+
"step": 70500
|
| 883 |
+
},
|
| 884 |
+
{
|
| 885 |
+
"epoch": 3.99,
|
| 886 |
+
"learning_rate": 8.351598242813415e-07,
|
| 887 |
+
"loss": 0.2443,
|
| 888 |
+
"step": 71000
|
| 889 |
+
},
|
| 890 |
+
{
|
| 891 |
+
"epoch": 4.0,
|
| 892 |
+
"eval_f1": 0.8682891911238368,
|
| 893 |
+
"eval_loss": 0.45183292031288147,
|
| 894 |
+
"eval_runtime": 7.6556,
|
| 895 |
+
"eval_samples_per_second": 516.746,
|
| 896 |
+
"eval_steps_per_second": 8.099,
|
| 897 |
+
"step": 71220
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 4.02,
|
| 901 |
+
"learning_rate": 8.119931162568937e-07,
|
| 902 |
+
"loss": 0.2433,
|
| 903 |
+
"step": 71500
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 4.04,
|
| 907 |
+
"learning_rate": 7.88826408232446e-07,
|
| 908 |
+
"loss": 0.2085,
|
| 909 |
+
"step": 72000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 4.07,
|
| 913 |
+
"learning_rate": 7.656597002079982e-07,
|
| 914 |
+
"loss": 0.2304,
|
| 915 |
+
"step": 72500
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 4.1,
|
| 919 |
+
"learning_rate": 7.424929921835505e-07,
|
| 920 |
+
"loss": 0.1944,
|
| 921 |
+
"step": 73000
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 4.13,
|
| 925 |
+
"learning_rate": 7.193262841591027e-07,
|
| 926 |
+
"loss": 0.2493,
|
| 927 |
+
"step": 73500
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 4.16,
|
| 931 |
+
"learning_rate": 6.961595761346548e-07,
|
| 932 |
+
"loss": 0.2177,
|
| 933 |
+
"step": 74000
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 4.18,
|
| 937 |
+
"learning_rate": 6.729928681102073e-07,
|
| 938 |
+
"loss": 0.2357,
|
| 939 |
+
"step": 74500
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 4.21,
|
| 943 |
+
"learning_rate": 6.498261600857594e-07,
|
| 944 |
+
"loss": 0.2238,
|
| 945 |
+
"step": 75000
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 4.24,
|
| 949 |
+
"learning_rate": 6.266594520613117e-07,
|
| 950 |
+
"loss": 0.2126,
|
| 951 |
+
"step": 75500
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 4.27,
|
| 955 |
+
"learning_rate": 6.034927440368639e-07,
|
| 956 |
+
"loss": 0.2088,
|
| 957 |
+
"step": 76000
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 4.3,
|
| 961 |
+
"learning_rate": 5.803260360124161e-07,
|
| 962 |
+
"loss": 0.2204,
|
| 963 |
+
"step": 76500
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 4.32,
|
| 967 |
+
"learning_rate": 5.571593279879684e-07,
|
| 968 |
+
"loss": 0.2542,
|
| 969 |
+
"step": 77000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 4.35,
|
| 973 |
+
"learning_rate": 5.339926199635206e-07,
|
| 974 |
+
"loss": 0.1956,
|
| 975 |
+
"step": 77500
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 4.38,
|
| 979 |
+
"learning_rate": 5.108259119390729e-07,
|
| 980 |
+
"loss": 0.2359,
|
| 981 |
+
"step": 78000
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 4.41,
|
| 985 |
+
"learning_rate": 4.876592039146252e-07,
|
| 986 |
+
"loss": 0.2,
|
| 987 |
+
"step": 78500
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 4.44,
|
| 991 |
+
"learning_rate": 4.644924958901774e-07,
|
| 992 |
+
"loss": 0.2304,
|
| 993 |
+
"step": 79000
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 4.47,
|
| 997 |
+
"learning_rate": 4.413257878657296e-07,
|
| 998 |
+
"loss": 0.2344,
|
| 999 |
+
"step": 79500
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 4.49,
|
| 1003 |
+
"learning_rate": 4.181590798412819e-07,
|
| 1004 |
+
"loss": 0.1942,
|
| 1005 |
+
"step": 80000
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 4.52,
|
| 1009 |
+
"learning_rate": 3.9499237181683415e-07,
|
| 1010 |
+
"loss": 0.2111,
|
| 1011 |
+
"step": 80500
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 4.55,
|
| 1015 |
+
"learning_rate": 3.718256637923864e-07,
|
| 1016 |
+
"loss": 0.1839,
|
| 1017 |
+
"step": 81000
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 4.58,
|
| 1021 |
+
"learning_rate": 3.4865895576793867e-07,
|
| 1022 |
+
"loss": 0.2171,
|
| 1023 |
+
"step": 81500
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 4.61,
|
| 1027 |
+
"learning_rate": 3.254922477434909e-07,
|
| 1028 |
+
"loss": 0.171,
|
| 1029 |
+
"step": 82000
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 4.63,
|
| 1033 |
+
"learning_rate": 3.0232553971904314e-07,
|
| 1034 |
+
"loss": 0.1955,
|
| 1035 |
+
"step": 82500
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 4.66,
|
| 1039 |
+
"learning_rate": 2.791588316945954e-07,
|
| 1040 |
+
"loss": 0.224,
|
| 1041 |
+
"step": 83000
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 4.69,
|
| 1045 |
+
"learning_rate": 2.5599212367014767e-07,
|
| 1046 |
+
"loss": 0.142,
|
| 1047 |
+
"step": 83500
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 4.72,
|
| 1051 |
+
"learning_rate": 2.328254156456999e-07,
|
| 1052 |
+
"loss": 0.2511,
|
| 1053 |
+
"step": 84000
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 4.75,
|
| 1057 |
+
"learning_rate": 2.0965870762125217e-07,
|
| 1058 |
+
"loss": 0.244,
|
| 1059 |
+
"step": 84500
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 4.77,
|
| 1063 |
+
"learning_rate": 1.8649199959680438e-07,
|
| 1064 |
+
"loss": 0.2133,
|
| 1065 |
+
"step": 85000
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 4.8,
|
| 1069 |
+
"learning_rate": 1.6332529157235664e-07,
|
| 1070 |
+
"loss": 0.1929,
|
| 1071 |
+
"step": 85500
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 4.83,
|
| 1075 |
+
"learning_rate": 1.401585835479089e-07,
|
| 1076 |
+
"loss": 0.1714,
|
| 1077 |
+
"step": 86000
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 4.86,
|
| 1081 |
+
"learning_rate": 1.1699187552346115e-07,
|
| 1082 |
+
"loss": 0.256,
|
| 1083 |
+
"step": 86500
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 4.89,
|
| 1087 |
+
"learning_rate": 9.38251674990134e-08,
|
| 1088 |
+
"loss": 0.2376,
|
| 1089 |
+
"step": 87000
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 4.91,
|
| 1093 |
+
"learning_rate": 7.065845947456565e-08,
|
| 1094 |
+
"loss": 0.1989,
|
| 1095 |
+
"step": 87500
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 4.94,
|
| 1099 |
+
"learning_rate": 4.749175145011789e-08,
|
| 1100 |
+
"loss": 0.1805,
|
| 1101 |
+
"step": 88000
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 4.97,
|
| 1105 |
+
"learning_rate": 2.432504342567014e-08,
|
| 1106 |
+
"loss": 0.1966,
|
| 1107 |
+
"step": 88500
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 5.0,
|
| 1111 |
+
"learning_rate": 1.1583354012223876e-09,
|
| 1112 |
+
"loss": 0.188,
|
| 1113 |
+
"step": 89000
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 5.0,
|
| 1117 |
+
"eval_f1": 0.8664518438954529,
|
| 1118 |
+
"eval_loss": 0.49096617102622986,
|
| 1119 |
+
"eval_runtime": 7.6764,
|
| 1120 |
+
"eval_samples_per_second": 515.346,
|
| 1121 |
+
"eval_steps_per_second": 8.077,
|
| 1122 |
+
"step": 89025
|
| 1123 |
+
}
|
| 1124 |
+
],
|
| 1125 |
+
"logging_steps": 500,
|
| 1126 |
+
"max_steps": 89025,
|
| 1127 |
+
"num_input_tokens_seen": 0,
|
| 1128 |
+
"num_train_epochs": 5,
|
| 1129 |
+
"save_steps": 500,
|
| 1130 |
+
"total_flos": 1.4010974818042248e+16,
|
| 1131 |
+
"train_batch_size": 4,
|
| 1132 |
+
"trial_name": null,
|
| 1133 |
+
"trial_params": {
|
| 1134 |
+
"learning_rate": 4.124832363752922e-06,
|
| 1135 |
+
"num_train_epochs": 5,
|
| 1136 |
+
"per_device_train_batch_size": 4,
|
| 1137 |
+
"seed": 40
|
| 1138 |
+
}
|
| 1139 |
+
}
|
run-1/checkpoint-89025/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1edfb4d32c4b440688a42ad772fd577e72d0a24c0764a9f6c27730006d6a58ce
|
| 3 |
+
size 4664
|
run-1/checkpoint-89025/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4664
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d9045585fb95426011b0d792bf161cc87b73c9aad66767bcf8d324024367c9c
|
| 3 |
size 4664
|