Training in progress, epoch 1
Browse files- model.safetensors +1 -1
- run-3/checkpoint-26709/config.json +25 -0
- run-3/checkpoint-26709/model.safetensors +3 -0
- run-3/checkpoint-26709/optimizer.pt +3 -0
- run-3/checkpoint-26709/rng_state.pth +3 -0
- run-3/checkpoint-26709/scheduler.pt +3 -0
- run-3/checkpoint-26709/special_tokens_map.json +7 -0
- run-3/checkpoint-26709/tokenizer.json +0 -0
- run-3/checkpoint-26709/tokenizer_config.json +55 -0
- run-3/checkpoint-26709/trainer_state.json +371 -0
- run-3/checkpoint-26709/training_args.bin +3 -0
- run-3/checkpoint-26709/vocab.txt +0 -0
- run-3/checkpoint-35612/config.json +25 -0
- run-3/checkpoint-35612/model.safetensors +3 -0
- run-3/checkpoint-35612/optimizer.pt +3 -0
- run-3/checkpoint-35612/rng_state.pth +3 -0
- run-3/checkpoint-35612/scheduler.pt +3 -0
- run-3/checkpoint-35612/special_tokens_map.json +7 -0
- run-3/checkpoint-35612/tokenizer.json +0 -0
- run-3/checkpoint-35612/tokenizer_config.json +55 -0
- run-3/checkpoint-35612/trainer_state.json +488 -0
- run-3/checkpoint-35612/training_args.bin +3 -0
- run-3/checkpoint-35612/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 sha256:369a9c12ed6162f9841ee96b21a47cdaa5921b66d8e72eb6a26c01451caf4359
|
| 3 |
size 267832560
|
run-3/checkpoint-26709/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-3/checkpoint-26709/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6bd56a52ddc8288639d76850224052d388cd6562d4045a616ba7cca4d4420dba
|
| 3 |
+
size 267832560
|
run-3/checkpoint-26709/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed899d9bf64e4342f003b2f909d66e21d6ee7df498c4c74b2d92a46618fa700f
|
| 3 |
+
size 535727290
|
run-3/checkpoint-26709/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60d703d8013ce7d7c6fc62c02706a8487e57106bd3cfc1f1098eacd5381ba54f
|
| 3 |
+
size 14244
|
run-3/checkpoint-26709/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8083b435983514b7c215e202ee3d4b3b5cbb547b9c8ff1822cb186b046625eb
|
| 3 |
+
size 1064
|
run-3/checkpoint-26709/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-3/checkpoint-26709/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-3/checkpoint-26709/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-3/checkpoint-26709/trainer_state.json
ADDED
|
@@ -0,0 +1,371 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8519724936663048,
|
| 3 |
+
"best_model_checkpoint": "retrieval_model/run-3/checkpoint-26709",
|
| 4 |
+
"epoch": 3.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 26709,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 3.4704519236458057e-06,
|
| 14 |
+
"loss": 0.4686,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.11,
|
| 19 |
+
"learning_rate": 3.4210321821949366e-06,
|
| 20 |
+
"loss": 0.3929,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.17,
|
| 25 |
+
"learning_rate": 3.3716124407440683e-06,
|
| 26 |
+
"loss": 0.3526,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.22,
|
| 31 |
+
"learning_rate": 3.3221926992931996e-06,
|
| 32 |
+
"loss": 0.3448,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.28,
|
| 37 |
+
"learning_rate": 3.272772957842331e-06,
|
| 38 |
+
"loss": 0.3648,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.34,
|
| 43 |
+
"learning_rate": 3.223353216391462e-06,
|
| 44 |
+
"loss": 0.3417,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.39,
|
| 49 |
+
"learning_rate": 3.173933474940593e-06,
|
| 50 |
+
"loss": 0.3259,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.45,
|
| 55 |
+
"learning_rate": 3.124513733489725e-06,
|
| 56 |
+
"loss": 0.3513,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.51,
|
| 61 |
+
"learning_rate": 3.0750939920388557e-06,
|
| 62 |
+
"loss": 0.3343,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.56,
|
| 67 |
+
"learning_rate": 3.025674250587987e-06,
|
| 68 |
+
"loss": 0.3465,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.62,
|
| 73 |
+
"learning_rate": 2.9762545091371184e-06,
|
| 74 |
+
"loss": 0.3218,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.67,
|
| 79 |
+
"learning_rate": 2.9268347676862497e-06,
|
| 80 |
+
"loss": 0.3134,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.73,
|
| 85 |
+
"learning_rate": 2.877415026235381e-06,
|
| 86 |
+
"loss": 0.3115,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.79,
|
| 91 |
+
"learning_rate": 2.8279952847845123e-06,
|
| 92 |
+
"loss": 0.3143,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.84,
|
| 97 |
+
"learning_rate": 2.7785755433336436e-06,
|
| 98 |
+
"loss": 0.3086,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.9,
|
| 103 |
+
"learning_rate": 2.7291558018827745e-06,
|
| 104 |
+
"loss": 0.3295,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.95,
|
| 109 |
+
"learning_rate": 2.679736060431906e-06,
|
| 110 |
+
"loss": 0.3056,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.0,
|
| 115 |
+
"eval_f1": 0.8321005917159763,
|
| 116 |
+
"eval_loss": 0.32298120856285095,
|
| 117 |
+
"eval_runtime": 8.1227,
|
| 118 |
+
"eval_samples_per_second": 487.029,
|
| 119 |
+
"eval_steps_per_second": 7.633,
|
| 120 |
+
"step": 8903
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.01,
|
| 124 |
+
"learning_rate": 2.630316318981037e-06,
|
| 125 |
+
"loss": 0.318,
|
| 126 |
+
"step": 9000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.07,
|
| 130 |
+
"learning_rate": 2.580896577530169e-06,
|
| 131 |
+
"loss": 0.2982,
|
| 132 |
+
"step": 9500
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.12,
|
| 136 |
+
"learning_rate": 2.5314768360792997e-06,
|
| 137 |
+
"loss": 0.2874,
|
| 138 |
+
"step": 10000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.18,
|
| 142 |
+
"learning_rate": 2.482057094628431e-06,
|
| 143 |
+
"loss": 0.2856,
|
| 144 |
+
"step": 10500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.24,
|
| 148 |
+
"learning_rate": 2.4326373531775623e-06,
|
| 149 |
+
"loss": 0.3088,
|
| 150 |
+
"step": 11000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.29,
|
| 154 |
+
"learning_rate": 2.3832176117266936e-06,
|
| 155 |
+
"loss": 0.2887,
|
| 156 |
+
"step": 11500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.35,
|
| 160 |
+
"learning_rate": 2.333797870275825e-06,
|
| 161 |
+
"loss": 0.2844,
|
| 162 |
+
"step": 12000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.4,
|
| 166 |
+
"learning_rate": 2.2843781288249563e-06,
|
| 167 |
+
"loss": 0.2884,
|
| 168 |
+
"step": 12500
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.46,
|
| 172 |
+
"learning_rate": 2.2349583873740876e-06,
|
| 173 |
+
"loss": 0.2838,
|
| 174 |
+
"step": 13000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.52,
|
| 178 |
+
"learning_rate": 2.1855386459232185e-06,
|
| 179 |
+
"loss": 0.2988,
|
| 180 |
+
"step": 13500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.57,
|
| 184 |
+
"learning_rate": 2.1361189044723498e-06,
|
| 185 |
+
"loss": 0.2881,
|
| 186 |
+
"step": 14000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.63,
|
| 190 |
+
"learning_rate": 2.0866991630214815e-06,
|
| 191 |
+
"loss": 0.2822,
|
| 192 |
+
"step": 14500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.68,
|
| 196 |
+
"learning_rate": 2.0372794215706124e-06,
|
| 197 |
+
"loss": 0.2904,
|
| 198 |
+
"step": 15000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.74,
|
| 202 |
+
"learning_rate": 1.9878596801197437e-06,
|
| 203 |
+
"loss": 0.289,
|
| 204 |
+
"step": 15500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.8,
|
| 208 |
+
"learning_rate": 1.938439938668875e-06,
|
| 209 |
+
"loss": 0.3042,
|
| 210 |
+
"step": 16000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.85,
|
| 214 |
+
"learning_rate": 1.889020197218006e-06,
|
| 215 |
+
"loss": 0.286,
|
| 216 |
+
"step": 16500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.91,
|
| 220 |
+
"learning_rate": 1.8396004557671378e-06,
|
| 221 |
+
"loss": 0.2667,
|
| 222 |
+
"step": 17000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.97,
|
| 226 |
+
"learning_rate": 1.790180714316269e-06,
|
| 227 |
+
"loss": 0.3005,
|
| 228 |
+
"step": 17500
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.0,
|
| 232 |
+
"eval_f1": 0.8438514244500541,
|
| 233 |
+
"eval_loss": 0.33582502603530884,
|
| 234 |
+
"eval_runtime": 8.1185,
|
| 235 |
+
"eval_samples_per_second": 487.283,
|
| 236 |
+
"eval_steps_per_second": 7.637,
|
| 237 |
+
"step": 17806
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.02,
|
| 241 |
+
"learning_rate": 1.7407609728654002e-06,
|
| 242 |
+
"loss": 0.2686,
|
| 243 |
+
"step": 18000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.08,
|
| 247 |
+
"learning_rate": 1.6913412314145313e-06,
|
| 248 |
+
"loss": 0.2623,
|
| 249 |
+
"step": 18500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.13,
|
| 253 |
+
"learning_rate": 1.6419214899636626e-06,
|
| 254 |
+
"loss": 0.2821,
|
| 255 |
+
"step": 19000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.19,
|
| 259 |
+
"learning_rate": 1.592501748512794e-06,
|
| 260 |
+
"loss": 0.2601,
|
| 261 |
+
"step": 19500
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.25,
|
| 265 |
+
"learning_rate": 1.5430820070619253e-06,
|
| 266 |
+
"loss": 0.2689,
|
| 267 |
+
"step": 20000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.3,
|
| 271 |
+
"learning_rate": 1.4936622656110566e-06,
|
| 272 |
+
"loss": 0.2583,
|
| 273 |
+
"step": 20500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.36,
|
| 277 |
+
"learning_rate": 1.4442425241601877e-06,
|
| 278 |
+
"loss": 0.2699,
|
| 279 |
+
"step": 21000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.41,
|
| 283 |
+
"learning_rate": 1.3948227827093192e-06,
|
| 284 |
+
"loss": 0.2702,
|
| 285 |
+
"step": 21500
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.47,
|
| 289 |
+
"learning_rate": 1.3454030412584503e-06,
|
| 290 |
+
"loss": 0.2668,
|
| 291 |
+
"step": 22000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.53,
|
| 295 |
+
"learning_rate": 1.2959832998075814e-06,
|
| 296 |
+
"loss": 0.2564,
|
| 297 |
+
"step": 22500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.58,
|
| 301 |
+
"learning_rate": 1.2465635583567129e-06,
|
| 302 |
+
"loss": 0.2677,
|
| 303 |
+
"step": 23000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.64,
|
| 307 |
+
"learning_rate": 1.197143816905844e-06,
|
| 308 |
+
"loss": 0.2478,
|
| 309 |
+
"step": 23500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.7,
|
| 313 |
+
"learning_rate": 1.1477240754549755e-06,
|
| 314 |
+
"loss": 0.268,
|
| 315 |
+
"step": 24000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.75,
|
| 319 |
+
"learning_rate": 1.0983043340041066e-06,
|
| 320 |
+
"loss": 0.2648,
|
| 321 |
+
"step": 24500
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.81,
|
| 325 |
+
"learning_rate": 1.048884592553238e-06,
|
| 326 |
+
"loss": 0.2334,
|
| 327 |
+
"step": 25000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.86,
|
| 331 |
+
"learning_rate": 9.994648511023692e-07,
|
| 332 |
+
"loss": 0.2636,
|
| 333 |
+
"step": 25500
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.92,
|
| 337 |
+
"learning_rate": 9.500451096515004e-07,
|
| 338 |
+
"loss": 0.276,
|
| 339 |
+
"step": 26000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.98,
|
| 343 |
+
"learning_rate": 9.006253682006318e-07,
|
| 344 |
+
"loss": 0.2459,
|
| 345 |
+
"step": 26500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.0,
|
| 349 |
+
"eval_f1": 0.8519724936663048,
|
| 350 |
+
"eval_loss": 0.351912260055542,
|
| 351 |
+
"eval_runtime": 8.1263,
|
| 352 |
+
"eval_samples_per_second": 486.814,
|
| 353 |
+
"eval_steps_per_second": 7.63,
|
| 354 |
+
"step": 26709
|
| 355 |
+
}
|
| 356 |
+
],
|
| 357 |
+
"logging_steps": 500,
|
| 358 |
+
"max_steps": 35612,
|
| 359 |
+
"num_input_tokens_seen": 0,
|
| 360 |
+
"num_train_epochs": 4,
|
| 361 |
+
"save_steps": 500,
|
| 362 |
+
"total_flos": 1.17553561752822e+16,
|
| 363 |
+
"train_batch_size": 8,
|
| 364 |
+
"trial_name": null,
|
| 365 |
+
"trial_params": {
|
| 366 |
+
"learning_rate": 3.5198716650966744e-06,
|
| 367 |
+
"num_train_epochs": 4,
|
| 368 |
+
"per_device_train_batch_size": 8,
|
| 369 |
+
"seed": 35
|
| 370 |
+
}
|
| 371 |
+
}
|
run-3/checkpoint-26709/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b03d5f520310321e5fcebd5cc86c2f3104bcd99312aa4df858df6b5d1cd412b2
|
| 3 |
+
size 4664
|
run-3/checkpoint-26709/vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-3/checkpoint-35612/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-3/checkpoint-35612/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f3f1e89ee83c13e266542f5b02f86bd9299d5f57fe7e2fc2d5a22a6585cd199
|
| 3 |
+
size 267832560
|
run-3/checkpoint-35612/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71bd8ce66b80de53f7b3c23806fbc52a0b452747cda90b2f558d94bacca318c5
|
| 3 |
+
size 535727290
|
run-3/checkpoint-35612/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fab2fe96d3fc904fe9ac39ad4709348031a03050e33e040e9aaf12c1e9865a57
|
| 3 |
+
size 14244
|
run-3/checkpoint-35612/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:23a72c7bde14e5c56826bbab6b86b927a9e243e431d931d768a97571d22ef4d1
|
| 3 |
+
size 1064
|
run-3/checkpoint-35612/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-3/checkpoint-35612/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
run-3/checkpoint-35612/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-3/checkpoint-35612/trainer_state.json
ADDED
|
@@ -0,0 +1,488 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8551470588235294,
|
| 3 |
+
"best_model_checkpoint": "retrieval_model/run-3/checkpoint-35612",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 35612,
|
| 7 |
+
"is_hyper_param_search": true,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.06,
|
| 13 |
+
"learning_rate": 3.4704519236458057e-06,
|
| 14 |
+
"loss": 0.4686,
|
| 15 |
+
"step": 500
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.11,
|
| 19 |
+
"learning_rate": 3.4210321821949366e-06,
|
| 20 |
+
"loss": 0.3929,
|
| 21 |
+
"step": 1000
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.17,
|
| 25 |
+
"learning_rate": 3.3716124407440683e-06,
|
| 26 |
+
"loss": 0.3526,
|
| 27 |
+
"step": 1500
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.22,
|
| 31 |
+
"learning_rate": 3.3221926992931996e-06,
|
| 32 |
+
"loss": 0.3448,
|
| 33 |
+
"step": 2000
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.28,
|
| 37 |
+
"learning_rate": 3.272772957842331e-06,
|
| 38 |
+
"loss": 0.3648,
|
| 39 |
+
"step": 2500
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.34,
|
| 43 |
+
"learning_rate": 3.223353216391462e-06,
|
| 44 |
+
"loss": 0.3417,
|
| 45 |
+
"step": 3000
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.39,
|
| 49 |
+
"learning_rate": 3.173933474940593e-06,
|
| 50 |
+
"loss": 0.3259,
|
| 51 |
+
"step": 3500
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.45,
|
| 55 |
+
"learning_rate": 3.124513733489725e-06,
|
| 56 |
+
"loss": 0.3513,
|
| 57 |
+
"step": 4000
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.51,
|
| 61 |
+
"learning_rate": 3.0750939920388557e-06,
|
| 62 |
+
"loss": 0.3343,
|
| 63 |
+
"step": 4500
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.56,
|
| 67 |
+
"learning_rate": 3.025674250587987e-06,
|
| 68 |
+
"loss": 0.3465,
|
| 69 |
+
"step": 5000
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.62,
|
| 73 |
+
"learning_rate": 2.9762545091371184e-06,
|
| 74 |
+
"loss": 0.3218,
|
| 75 |
+
"step": 5500
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.67,
|
| 79 |
+
"learning_rate": 2.9268347676862497e-06,
|
| 80 |
+
"loss": 0.3134,
|
| 81 |
+
"step": 6000
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.73,
|
| 85 |
+
"learning_rate": 2.877415026235381e-06,
|
| 86 |
+
"loss": 0.3115,
|
| 87 |
+
"step": 6500
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.79,
|
| 91 |
+
"learning_rate": 2.8279952847845123e-06,
|
| 92 |
+
"loss": 0.3143,
|
| 93 |
+
"step": 7000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.84,
|
| 97 |
+
"learning_rate": 2.7785755433336436e-06,
|
| 98 |
+
"loss": 0.3086,
|
| 99 |
+
"step": 7500
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.9,
|
| 103 |
+
"learning_rate": 2.7291558018827745e-06,
|
| 104 |
+
"loss": 0.3295,
|
| 105 |
+
"step": 8000
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.95,
|
| 109 |
+
"learning_rate": 2.679736060431906e-06,
|
| 110 |
+
"loss": 0.3056,
|
| 111 |
+
"step": 8500
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 1.0,
|
| 115 |
+
"eval_f1": 0.8321005917159763,
|
| 116 |
+
"eval_loss": 0.32298120856285095,
|
| 117 |
+
"eval_runtime": 8.1227,
|
| 118 |
+
"eval_samples_per_second": 487.029,
|
| 119 |
+
"eval_steps_per_second": 7.633,
|
| 120 |
+
"step": 8903
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 1.01,
|
| 124 |
+
"learning_rate": 2.630316318981037e-06,
|
| 125 |
+
"loss": 0.318,
|
| 126 |
+
"step": 9000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 1.07,
|
| 130 |
+
"learning_rate": 2.580896577530169e-06,
|
| 131 |
+
"loss": 0.2982,
|
| 132 |
+
"step": 9500
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 1.12,
|
| 136 |
+
"learning_rate": 2.5314768360792997e-06,
|
| 137 |
+
"loss": 0.2874,
|
| 138 |
+
"step": 10000
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 1.18,
|
| 142 |
+
"learning_rate": 2.482057094628431e-06,
|
| 143 |
+
"loss": 0.2856,
|
| 144 |
+
"step": 10500
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 1.24,
|
| 148 |
+
"learning_rate": 2.4326373531775623e-06,
|
| 149 |
+
"loss": 0.3088,
|
| 150 |
+
"step": 11000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 1.29,
|
| 154 |
+
"learning_rate": 2.3832176117266936e-06,
|
| 155 |
+
"loss": 0.2887,
|
| 156 |
+
"step": 11500
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 1.35,
|
| 160 |
+
"learning_rate": 2.333797870275825e-06,
|
| 161 |
+
"loss": 0.2844,
|
| 162 |
+
"step": 12000
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 1.4,
|
| 166 |
+
"learning_rate": 2.2843781288249563e-06,
|
| 167 |
+
"loss": 0.2884,
|
| 168 |
+
"step": 12500
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 1.46,
|
| 172 |
+
"learning_rate": 2.2349583873740876e-06,
|
| 173 |
+
"loss": 0.2838,
|
| 174 |
+
"step": 13000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.52,
|
| 178 |
+
"learning_rate": 2.1855386459232185e-06,
|
| 179 |
+
"loss": 0.2988,
|
| 180 |
+
"step": 13500
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 1.57,
|
| 184 |
+
"learning_rate": 2.1361189044723498e-06,
|
| 185 |
+
"loss": 0.2881,
|
| 186 |
+
"step": 14000
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.63,
|
| 190 |
+
"learning_rate": 2.0866991630214815e-06,
|
| 191 |
+
"loss": 0.2822,
|
| 192 |
+
"step": 14500
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 1.68,
|
| 196 |
+
"learning_rate": 2.0372794215706124e-06,
|
| 197 |
+
"loss": 0.2904,
|
| 198 |
+
"step": 15000
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 1.74,
|
| 202 |
+
"learning_rate": 1.9878596801197437e-06,
|
| 203 |
+
"loss": 0.289,
|
| 204 |
+
"step": 15500
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 1.8,
|
| 208 |
+
"learning_rate": 1.938439938668875e-06,
|
| 209 |
+
"loss": 0.3042,
|
| 210 |
+
"step": 16000
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 1.85,
|
| 214 |
+
"learning_rate": 1.889020197218006e-06,
|
| 215 |
+
"loss": 0.286,
|
| 216 |
+
"step": 16500
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 1.91,
|
| 220 |
+
"learning_rate": 1.8396004557671378e-06,
|
| 221 |
+
"loss": 0.2667,
|
| 222 |
+
"step": 17000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 1.97,
|
| 226 |
+
"learning_rate": 1.790180714316269e-06,
|
| 227 |
+
"loss": 0.3005,
|
| 228 |
+
"step": 17500
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 2.0,
|
| 232 |
+
"eval_f1": 0.8438514244500541,
|
| 233 |
+
"eval_loss": 0.33582502603530884,
|
| 234 |
+
"eval_runtime": 8.1185,
|
| 235 |
+
"eval_samples_per_second": 487.283,
|
| 236 |
+
"eval_steps_per_second": 7.637,
|
| 237 |
+
"step": 17806
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 2.02,
|
| 241 |
+
"learning_rate": 1.7407609728654002e-06,
|
| 242 |
+
"loss": 0.2686,
|
| 243 |
+
"step": 18000
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 2.08,
|
| 247 |
+
"learning_rate": 1.6913412314145313e-06,
|
| 248 |
+
"loss": 0.2623,
|
| 249 |
+
"step": 18500
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 2.13,
|
| 253 |
+
"learning_rate": 1.6419214899636626e-06,
|
| 254 |
+
"loss": 0.2821,
|
| 255 |
+
"step": 19000
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 2.19,
|
| 259 |
+
"learning_rate": 1.592501748512794e-06,
|
| 260 |
+
"loss": 0.2601,
|
| 261 |
+
"step": 19500
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 2.25,
|
| 265 |
+
"learning_rate": 1.5430820070619253e-06,
|
| 266 |
+
"loss": 0.2689,
|
| 267 |
+
"step": 20000
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 2.3,
|
| 271 |
+
"learning_rate": 1.4936622656110566e-06,
|
| 272 |
+
"loss": 0.2583,
|
| 273 |
+
"step": 20500
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 2.36,
|
| 277 |
+
"learning_rate": 1.4442425241601877e-06,
|
| 278 |
+
"loss": 0.2699,
|
| 279 |
+
"step": 21000
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 2.41,
|
| 283 |
+
"learning_rate": 1.3948227827093192e-06,
|
| 284 |
+
"loss": 0.2702,
|
| 285 |
+
"step": 21500
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 2.47,
|
| 289 |
+
"learning_rate": 1.3454030412584503e-06,
|
| 290 |
+
"loss": 0.2668,
|
| 291 |
+
"step": 22000
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.53,
|
| 295 |
+
"learning_rate": 1.2959832998075814e-06,
|
| 296 |
+
"loss": 0.2564,
|
| 297 |
+
"step": 22500
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 2.58,
|
| 301 |
+
"learning_rate": 1.2465635583567129e-06,
|
| 302 |
+
"loss": 0.2677,
|
| 303 |
+
"step": 23000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 2.64,
|
| 307 |
+
"learning_rate": 1.197143816905844e-06,
|
| 308 |
+
"loss": 0.2478,
|
| 309 |
+
"step": 23500
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 2.7,
|
| 313 |
+
"learning_rate": 1.1477240754549755e-06,
|
| 314 |
+
"loss": 0.268,
|
| 315 |
+
"step": 24000
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 2.75,
|
| 319 |
+
"learning_rate": 1.0983043340041066e-06,
|
| 320 |
+
"loss": 0.2648,
|
| 321 |
+
"step": 24500
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 2.81,
|
| 325 |
+
"learning_rate": 1.048884592553238e-06,
|
| 326 |
+
"loss": 0.2334,
|
| 327 |
+
"step": 25000
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.86,
|
| 331 |
+
"learning_rate": 9.994648511023692e-07,
|
| 332 |
+
"loss": 0.2636,
|
| 333 |
+
"step": 25500
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 2.92,
|
| 337 |
+
"learning_rate": 9.500451096515004e-07,
|
| 338 |
+
"loss": 0.276,
|
| 339 |
+
"step": 26000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.98,
|
| 343 |
+
"learning_rate": 9.006253682006318e-07,
|
| 344 |
+
"loss": 0.2459,
|
| 345 |
+
"step": 26500
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 3.0,
|
| 349 |
+
"eval_f1": 0.8519724936663048,
|
| 350 |
+
"eval_loss": 0.351912260055542,
|
| 351 |
+
"eval_runtime": 8.1263,
|
| 352 |
+
"eval_samples_per_second": 486.814,
|
| 353 |
+
"eval_steps_per_second": 7.63,
|
| 354 |
+
"step": 26709
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 3.03,
|
| 358 |
+
"learning_rate": 8.51205626749763e-07,
|
| 359 |
+
"loss": 0.253,
|
| 360 |
+
"step": 27000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 3.09,
|
| 364 |
+
"learning_rate": 8.017858852988942e-07,
|
| 365 |
+
"loss": 0.2467,
|
| 366 |
+
"step": 27500
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 3.15,
|
| 370 |
+
"learning_rate": 7.523661438480254e-07,
|
| 371 |
+
"loss": 0.2241,
|
| 372 |
+
"step": 28000
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 3.2,
|
| 376 |
+
"learning_rate": 7.029464023971568e-07,
|
| 377 |
+
"loss": 0.2455,
|
| 378 |
+
"step": 28500
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 3.26,
|
| 382 |
+
"learning_rate": 6.535266609462881e-07,
|
| 383 |
+
"loss": 0.2601,
|
| 384 |
+
"step": 29000
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 3.31,
|
| 388 |
+
"learning_rate": 6.041069194954194e-07,
|
| 389 |
+
"loss": 0.2436,
|
| 390 |
+
"step": 29500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 3.37,
|
| 394 |
+
"learning_rate": 5.546871780445507e-07,
|
| 395 |
+
"loss": 0.2563,
|
| 396 |
+
"step": 30000
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 3.43,
|
| 400 |
+
"learning_rate": 5.052674365936819e-07,
|
| 401 |
+
"loss": 0.236,
|
| 402 |
+
"step": 30500
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 3.48,
|
| 406 |
+
"learning_rate": 4.5584769514281314e-07,
|
| 407 |
+
"loss": 0.2366,
|
| 408 |
+
"step": 31000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 3.54,
|
| 412 |
+
"learning_rate": 4.0642795369194445e-07,
|
| 413 |
+
"loss": 0.2328,
|
| 414 |
+
"step": 31500
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 3.59,
|
| 418 |
+
"learning_rate": 3.570082122410757e-07,
|
| 419 |
+
"loss": 0.2576,
|
| 420 |
+
"step": 32000
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"epoch": 3.65,
|
| 424 |
+
"learning_rate": 3.0758847079020696e-07,
|
| 425 |
+
"loss": 0.2562,
|
| 426 |
+
"step": 32500
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"epoch": 3.71,
|
| 430 |
+
"learning_rate": 2.581687293393382e-07,
|
| 431 |
+
"loss": 0.2305,
|
| 432 |
+
"step": 33000
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 3.76,
|
| 436 |
+
"learning_rate": 2.087489878884695e-07,
|
| 437 |
+
"loss": 0.2405,
|
| 438 |
+
"step": 33500
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 3.82,
|
| 442 |
+
"learning_rate": 1.5932924643760078e-07,
|
| 443 |
+
"loss": 0.2642,
|
| 444 |
+
"step": 34000
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 3.88,
|
| 448 |
+
"learning_rate": 1.0990950498673206e-07,
|
| 449 |
+
"loss": 0.2582,
|
| 450 |
+
"step": 34500
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 3.93,
|
| 454 |
+
"learning_rate": 6.048976353586333e-08,
|
| 455 |
+
"loss": 0.2307,
|
| 456 |
+
"step": 35000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 3.99,
|
| 460 |
+
"learning_rate": 1.1070022084994596e-08,
|
| 461 |
+
"loss": 0.2361,
|
| 462 |
+
"step": 35500
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 4.0,
|
| 466 |
+
"eval_f1": 0.8551470588235294,
|
| 467 |
+
"eval_loss": 0.3704700767993927,
|
| 468 |
+
"eval_runtime": 8.3254,
|
| 469 |
+
"eval_samples_per_second": 475.172,
|
| 470 |
+
"eval_steps_per_second": 7.447,
|
| 471 |
+
"step": 35612
|
| 472 |
+
}
|
| 473 |
+
],
|
| 474 |
+
"logging_steps": 500,
|
| 475 |
+
"max_steps": 35612,
|
| 476 |
+
"num_input_tokens_seen": 0,
|
| 477 |
+
"num_train_epochs": 4,
|
| 478 |
+
"save_steps": 500,
|
| 479 |
+
"total_flos": 1.5744961941257604e+16,
|
| 480 |
+
"train_batch_size": 8,
|
| 481 |
+
"trial_name": null,
|
| 482 |
+
"trial_params": {
|
| 483 |
+
"learning_rate": 3.5198716650966744e-06,
|
| 484 |
+
"num_train_epochs": 4,
|
| 485 |
+
"per_device_train_batch_size": 8,
|
| 486 |
+
"seed": 35
|
| 487 |
+
}
|
| 488 |
+
}
|
run-3/checkpoint-35612/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b03d5f520310321e5fcebd5cc86c2f3104bcd99312aa4df858df6b5d1cd412b2
|
| 3 |
+
size 4664
|
run-3/checkpoint-35612/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 sha256:38803918182cee9f58463331c538b1704c52fb48b49366dff7f35059b08fbf3e
|
| 3 |
size 4664
|