Upload 11 files
Browse files- config.json +24 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +7 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- trainer_state.json +492 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation": "gelu",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"DistilBertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.1,
|
| 7 |
+
"dim": 768,
|
| 8 |
+
"dropout": 0.1,
|
| 9 |
+
"dtype": "float32",
|
| 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 |
+
"transformers_version": "4.57.1",
|
| 23 |
+
"vocab_size": 30522
|
| 24 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26a07749947cfb9451d94b4729136f91c77e7693347b70d3a2d93a2bf323b5d3
|
| 3 |
+
size 267832560
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cd79bf0440ec220ded47eba7196c6d19aa467fa48dae7d7b34e468a5970bd6a
|
| 3 |
+
size 535727290
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eccc79033ff1721f959f10ca6eb4051161fbd9aab15254374ecce8964c06274e
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:02d8fa1df71a1342214660ec1e65a5868d1c3bc681808f231d5ba92d6be6da14
|
| 3 |
+
size 1064
|
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 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": false,
|
| 45 |
+
"cls_token": "[CLS]",
|
| 46 |
+
"do_lower_case": true,
|
| 47 |
+
"extra_special_tokens": {},
|
| 48 |
+
"mask_token": "[MASK]",
|
| 49 |
+
"model_max_length": 512,
|
| 50 |
+
"pad_token": "[PAD]",
|
| 51 |
+
"sep_token": "[SEP]",
|
| 52 |
+
"strip_accents": null,
|
| 53 |
+
"tokenize_chinese_chars": true,
|
| 54 |
+
"tokenizer_class": "DistilBertTokenizer",
|
| 55 |
+
"unk_token": "[UNK]"
|
| 56 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,492 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 5628,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.053304904051172705,
|
| 14 |
+
"grad_norm": 2.3143041133880615,
|
| 15 |
+
"learning_rate": 9.900000000000002e-06,
|
| 16 |
+
"loss": 0.6637,
|
| 17 |
+
"step": 100
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.10660980810234541,
|
| 21 |
+
"grad_norm": 6.371345043182373,
|
| 22 |
+
"learning_rate": 1.9900000000000003e-05,
|
| 23 |
+
"loss": 0.505,
|
| 24 |
+
"step": 200
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.15991471215351813,
|
| 28 |
+
"grad_norm": 4.748474597930908,
|
| 29 |
+
"learning_rate": 2.9900000000000002e-05,
|
| 30 |
+
"loss": 0.4336,
|
| 31 |
+
"step": 300
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.21321961620469082,
|
| 35 |
+
"grad_norm": 4.305647373199463,
|
| 36 |
+
"learning_rate": 3.99e-05,
|
| 37 |
+
"loss": 0.4183,
|
| 38 |
+
"step": 400
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.26652452025586354,
|
| 42 |
+
"grad_norm": 4.751767635345459,
|
| 43 |
+
"learning_rate": 4.99e-05,
|
| 44 |
+
"loss": 0.4119,
|
| 45 |
+
"step": 500
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.31982942430703626,
|
| 49 |
+
"grad_norm": 2.5453217029571533,
|
| 50 |
+
"learning_rate": 4.903471138845554e-05,
|
| 51 |
+
"loss": 0.421,
|
| 52 |
+
"step": 600
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.373134328358209,
|
| 56 |
+
"grad_norm": 2.3192925453186035,
|
| 57 |
+
"learning_rate": 4.805967238689548e-05,
|
| 58 |
+
"loss": 0.423,
|
| 59 |
+
"step": 700
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.42643923240938164,
|
| 63 |
+
"grad_norm": 2.352053642272949,
|
| 64 |
+
"learning_rate": 4.708463338533542e-05,
|
| 65 |
+
"loss": 0.4051,
|
| 66 |
+
"step": 800
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.47974413646055436,
|
| 70 |
+
"grad_norm": 3.065234661102295,
|
| 71 |
+
"learning_rate": 4.610959438377535e-05,
|
| 72 |
+
"loss": 0.3808,
|
| 73 |
+
"step": 900
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.5330490405117271,
|
| 77 |
+
"grad_norm": 3.259699583053589,
|
| 78 |
+
"learning_rate": 4.513455538221529e-05,
|
| 79 |
+
"loss": 0.4178,
|
| 80 |
+
"step": 1000
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.5863539445628998,
|
| 84 |
+
"grad_norm": 5.711488723754883,
|
| 85 |
+
"learning_rate": 4.415951638065523e-05,
|
| 86 |
+
"loss": 0.3846,
|
| 87 |
+
"step": 1100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.6396588486140725,
|
| 91 |
+
"grad_norm": 3.5369982719421387,
|
| 92 |
+
"learning_rate": 4.318447737909517e-05,
|
| 93 |
+
"loss": 0.3724,
|
| 94 |
+
"step": 1200
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.6929637526652452,
|
| 98 |
+
"grad_norm": 1.9052191972732544,
|
| 99 |
+
"learning_rate": 4.220943837753511e-05,
|
| 100 |
+
"loss": 0.3885,
|
| 101 |
+
"step": 1300
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.746268656716418,
|
| 105 |
+
"grad_norm": 6.73522424697876,
|
| 106 |
+
"learning_rate": 4.123439937597504e-05,
|
| 107 |
+
"loss": 0.3776,
|
| 108 |
+
"step": 1400
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.7995735607675906,
|
| 112 |
+
"grad_norm": 4.6753387451171875,
|
| 113 |
+
"learning_rate": 4.025936037441498e-05,
|
| 114 |
+
"loss": 0.3469,
|
| 115 |
+
"step": 1500
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.8528784648187633,
|
| 119 |
+
"grad_norm": 3.484023094177246,
|
| 120 |
+
"learning_rate": 3.9284321372854915e-05,
|
| 121 |
+
"loss": 0.39,
|
| 122 |
+
"step": 1600
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.906183368869936,
|
| 126 |
+
"grad_norm": 3.9286551475524902,
|
| 127 |
+
"learning_rate": 3.830928237129485e-05,
|
| 128 |
+
"loss": 0.371,
|
| 129 |
+
"step": 1700
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.9594882729211087,
|
| 133 |
+
"grad_norm": 4.431338310241699,
|
| 134 |
+
"learning_rate": 3.733424336973479e-05,
|
| 135 |
+
"loss": 0.3573,
|
| 136 |
+
"step": 1800
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 1.0,
|
| 140 |
+
"eval_accuracy": 0.8105906313645621,
|
| 141 |
+
"eval_confusion_matrix": [
|
| 142 |
+
[
|
| 143 |
+
609,
|
| 144 |
+
296
|
| 145 |
+
],
|
| 146 |
+
[
|
| 147 |
+
76,
|
| 148 |
+
983
|
| 149 |
+
]
|
| 150 |
+
],
|
| 151 |
+
"eval_f1": 0.8063983144212725,
|
| 152 |
+
"eval_loss": 0.4077329933643341,
|
| 153 |
+
"eval_precision": 0.8240865672329818,
|
| 154 |
+
"eval_recall": 0.8105906313645621,
|
| 155 |
+
"eval_runtime": 37.6119,
|
| 156 |
+
"eval_samples_per_second": 52.218,
|
| 157 |
+
"eval_steps_per_second": 3.27,
|
| 158 |
+
"step": 1876
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.0127931769722816,
|
| 162 |
+
"grad_norm": 0.8932910561561584,
|
| 163 |
+
"learning_rate": 3.635920436817473e-05,
|
| 164 |
+
"loss": 0.3484,
|
| 165 |
+
"step": 1900
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 1.0660980810234542,
|
| 169 |
+
"grad_norm": 4.019241809844971,
|
| 170 |
+
"learning_rate": 3.538416536661467e-05,
|
| 171 |
+
"loss": 0.2809,
|
| 172 |
+
"step": 2000
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 1.1194029850746268,
|
| 176 |
+
"grad_norm": 7.529379367828369,
|
| 177 |
+
"learning_rate": 3.4409126365054605e-05,
|
| 178 |
+
"loss": 0.2562,
|
| 179 |
+
"step": 2100
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.1727078891257996,
|
| 183 |
+
"grad_norm": 2.790593147277832,
|
| 184 |
+
"learning_rate": 3.343408736349454e-05,
|
| 185 |
+
"loss": 0.2552,
|
| 186 |
+
"step": 2200
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.2260127931769722,
|
| 190 |
+
"grad_norm": 1.8328346014022827,
|
| 191 |
+
"learning_rate": 3.245904836193448e-05,
|
| 192 |
+
"loss": 0.2582,
|
| 193 |
+
"step": 2300
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.279317697228145,
|
| 197 |
+
"grad_norm": 7.493434429168701,
|
| 198 |
+
"learning_rate": 3.148400936037442e-05,
|
| 199 |
+
"loss": 0.246,
|
| 200 |
+
"step": 2400
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.3326226012793176,
|
| 204 |
+
"grad_norm": 6.164539813995361,
|
| 205 |
+
"learning_rate": 3.0508970358814354e-05,
|
| 206 |
+
"loss": 0.2494,
|
| 207 |
+
"step": 2500
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.3859275053304905,
|
| 211 |
+
"grad_norm": 4.088465690612793,
|
| 212 |
+
"learning_rate": 2.9533931357254292e-05,
|
| 213 |
+
"loss": 0.2625,
|
| 214 |
+
"step": 2600
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 1.439232409381663,
|
| 218 |
+
"grad_norm": 3.8281686305999756,
|
| 219 |
+
"learning_rate": 2.8558892355694227e-05,
|
| 220 |
+
"loss": 0.2886,
|
| 221 |
+
"step": 2700
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.4925373134328357,
|
| 225 |
+
"grad_norm": 5.0964226722717285,
|
| 226 |
+
"learning_rate": 2.7583853354134165e-05,
|
| 227 |
+
"loss": 0.2443,
|
| 228 |
+
"step": 2800
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 1.5458422174840085,
|
| 232 |
+
"grad_norm": 4.0434370040893555,
|
| 233 |
+
"learning_rate": 2.6608814352574103e-05,
|
| 234 |
+
"loss": 0.244,
|
| 235 |
+
"step": 2900
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 1.5991471215351813,
|
| 239 |
+
"grad_norm": 1.8725121021270752,
|
| 240 |
+
"learning_rate": 2.5633775351014045e-05,
|
| 241 |
+
"loss": 0.2589,
|
| 242 |
+
"step": 3000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.652452025586354,
|
| 246 |
+
"grad_norm": 4.799729824066162,
|
| 247 |
+
"learning_rate": 2.465873634945398e-05,
|
| 248 |
+
"loss": 0.2568,
|
| 249 |
+
"step": 3100
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.7057569296375266,
|
| 253 |
+
"grad_norm": 6.433875560760498,
|
| 254 |
+
"learning_rate": 2.3683697347893914e-05,
|
| 255 |
+
"loss": 0.2319,
|
| 256 |
+
"step": 3200
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 1.7590618336886994,
|
| 260 |
+
"grad_norm": 5.887631893157959,
|
| 261 |
+
"learning_rate": 2.2708658346333856e-05,
|
| 262 |
+
"loss": 0.2581,
|
| 263 |
+
"step": 3300
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.8123667377398722,
|
| 267 |
+
"grad_norm": 4.89068078994751,
|
| 268 |
+
"learning_rate": 2.1733619344773794e-05,
|
| 269 |
+
"loss": 0.234,
|
| 270 |
+
"step": 3400
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 1.8656716417910446,
|
| 274 |
+
"grad_norm": 8.370274543762207,
|
| 275 |
+
"learning_rate": 2.075858034321373e-05,
|
| 276 |
+
"loss": 0.2487,
|
| 277 |
+
"step": 3500
|
| 278 |
+
},
|
| 279 |
+
{
|
| 280 |
+
"epoch": 1.9189765458422174,
|
| 281 |
+
"grad_norm": 4.509988307952881,
|
| 282 |
+
"learning_rate": 1.9783541341653667e-05,
|
| 283 |
+
"loss": 0.2591,
|
| 284 |
+
"step": 3600
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.9722814498933903,
|
| 288 |
+
"grad_norm": 3.838970184326172,
|
| 289 |
+
"learning_rate": 1.8808502340093605e-05,
|
| 290 |
+
"loss": 0.2392,
|
| 291 |
+
"step": 3700
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 2.0,
|
| 295 |
+
"eval_accuracy": 0.8411405295315683,
|
| 296 |
+
"eval_confusion_matrix": [
|
| 297 |
+
[
|
| 298 |
+
706,
|
| 299 |
+
199
|
| 300 |
+
],
|
| 301 |
+
[
|
| 302 |
+
113,
|
| 303 |
+
946
|
| 304 |
+
]
|
| 305 |
+
],
|
| 306 |
+
"eval_f1": 0.8402776027420387,
|
| 307 |
+
"eval_loss": 0.44446203112602234,
|
| 308 |
+
"eval_precision": 0.8427092846360184,
|
| 309 |
+
"eval_recall": 0.8411405295315683,
|
| 310 |
+
"eval_runtime": 36.7709,
|
| 311 |
+
"eval_samples_per_second": 53.412,
|
| 312 |
+
"eval_steps_per_second": 3.345,
|
| 313 |
+
"step": 3752
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"epoch": 2.025586353944563,
|
| 317 |
+
"grad_norm": 7.447359085083008,
|
| 318 |
+
"learning_rate": 1.7833463338533543e-05,
|
| 319 |
+
"loss": 0.1882,
|
| 320 |
+
"step": 3800
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.0788912579957355,
|
| 324 |
+
"grad_norm": 0.26925402879714966,
|
| 325 |
+
"learning_rate": 1.685842433697348e-05,
|
| 326 |
+
"loss": 0.1558,
|
| 327 |
+
"step": 3900
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 2.1321961620469083,
|
| 331 |
+
"grad_norm": 4.837244510650635,
|
| 332 |
+
"learning_rate": 1.5883385335413416e-05,
|
| 333 |
+
"loss": 0.1547,
|
| 334 |
+
"step": 4000
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 2.185501066098081,
|
| 338 |
+
"grad_norm": 0.8875559568405151,
|
| 339 |
+
"learning_rate": 1.4908346333853354e-05,
|
| 340 |
+
"loss": 0.161,
|
| 341 |
+
"step": 4100
|
| 342 |
+
},
|
| 343 |
+
{
|
| 344 |
+
"epoch": 2.2388059701492535,
|
| 345 |
+
"grad_norm": 4.033316612243652,
|
| 346 |
+
"learning_rate": 1.3933307332293292e-05,
|
| 347 |
+
"loss": 0.1724,
|
| 348 |
+
"step": 4200
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 2.2921108742004264,
|
| 352 |
+
"grad_norm": 15.54712200164795,
|
| 353 |
+
"learning_rate": 1.2958268330733232e-05,
|
| 354 |
+
"loss": 0.1586,
|
| 355 |
+
"step": 4300
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"epoch": 2.345415778251599,
|
| 359 |
+
"grad_norm": 12.946330070495605,
|
| 360 |
+
"learning_rate": 1.1983229329173168e-05,
|
| 361 |
+
"loss": 0.161,
|
| 362 |
+
"step": 4400
|
| 363 |
+
},
|
| 364 |
+
{
|
| 365 |
+
"epoch": 2.398720682302772,
|
| 366 |
+
"grad_norm": 3.7774710655212402,
|
| 367 |
+
"learning_rate": 1.1008190327613105e-05,
|
| 368 |
+
"loss": 0.1489,
|
| 369 |
+
"step": 4500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 2.4520255863539444,
|
| 373 |
+
"grad_norm": 9.51603889465332,
|
| 374 |
+
"learning_rate": 1.0033151326053043e-05,
|
| 375 |
+
"loss": 0.152,
|
| 376 |
+
"step": 4600
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 2.5053304904051172,
|
| 380 |
+
"grad_norm": 0.13294453918933868,
|
| 381 |
+
"learning_rate": 9.05811232449298e-06,
|
| 382 |
+
"loss": 0.1512,
|
| 383 |
+
"step": 4700
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.55863539445629,
|
| 387 |
+
"grad_norm": 2.5648090839385986,
|
| 388 |
+
"learning_rate": 8.083073322932917e-06,
|
| 389 |
+
"loss": 0.1647,
|
| 390 |
+
"step": 4800
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 2.611940298507463,
|
| 394 |
+
"grad_norm": 3.1670095920562744,
|
| 395 |
+
"learning_rate": 7.108034321372855e-06,
|
| 396 |
+
"loss": 0.1397,
|
| 397 |
+
"step": 4900
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 2.6652452025586353,
|
| 401 |
+
"grad_norm": 0.7597922086715698,
|
| 402 |
+
"learning_rate": 6.1329953198127925e-06,
|
| 403 |
+
"loss": 0.1567,
|
| 404 |
+
"step": 5000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.718550106609808,
|
| 408 |
+
"grad_norm": 24.864763259887695,
|
| 409 |
+
"learning_rate": 5.157956318252731e-06,
|
| 410 |
+
"loss": 0.1653,
|
| 411 |
+
"step": 5100
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.771855010660981,
|
| 415 |
+
"grad_norm": 11.073485374450684,
|
| 416 |
+
"learning_rate": 4.182917316692668e-06,
|
| 417 |
+
"loss": 0.1287,
|
| 418 |
+
"step": 5200
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 2.8251599147121533,
|
| 422 |
+
"grad_norm": 0.2030704915523529,
|
| 423 |
+
"learning_rate": 3.2078783151326056e-06,
|
| 424 |
+
"loss": 0.128,
|
| 425 |
+
"step": 5300
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 2.878464818763326,
|
| 429 |
+
"grad_norm": 4.208672523498535,
|
| 430 |
+
"learning_rate": 2.232839313572543e-06,
|
| 431 |
+
"loss": 0.1525,
|
| 432 |
+
"step": 5400
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 2.931769722814499,
|
| 436 |
+
"grad_norm": 13.611940383911133,
|
| 437 |
+
"learning_rate": 1.2578003120124805e-06,
|
| 438 |
+
"loss": 0.1539,
|
| 439 |
+
"step": 5500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 2.9850746268656714,
|
| 443 |
+
"grad_norm": 12.76778507232666,
|
| 444 |
+
"learning_rate": 2.827613104524181e-07,
|
| 445 |
+
"loss": 0.1568,
|
| 446 |
+
"step": 5600
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.0,
|
| 450 |
+
"eval_accuracy": 0.8441955193482689,
|
| 451 |
+
"eval_confusion_matrix": [
|
| 452 |
+
[
|
| 453 |
+
738,
|
| 454 |
+
167
|
| 455 |
+
],
|
| 456 |
+
[
|
| 457 |
+
139,
|
| 458 |
+
920
|
| 459 |
+
]
|
| 460 |
+
],
|
| 461 |
+
"eval_f1": 0.8439878980296145,
|
| 462 |
+
"eval_loss": 0.5926053524017334,
|
| 463 |
+
"eval_precision": 0.8441262177198018,
|
| 464 |
+
"eval_recall": 0.8441955193482689,
|
| 465 |
+
"eval_runtime": 36.4848,
|
| 466 |
+
"eval_samples_per_second": 53.831,
|
| 467 |
+
"eval_steps_per_second": 3.371,
|
| 468 |
+
"step": 5628
|
| 469 |
+
}
|
| 470 |
+
],
|
| 471 |
+
"logging_steps": 100,
|
| 472 |
+
"max_steps": 5628,
|
| 473 |
+
"num_input_tokens_seen": 0,
|
| 474 |
+
"num_train_epochs": 3,
|
| 475 |
+
"save_steps": 500,
|
| 476 |
+
"stateful_callbacks": {
|
| 477 |
+
"TrainerControl": {
|
| 478 |
+
"args": {
|
| 479 |
+
"should_epoch_stop": false,
|
| 480 |
+
"should_evaluate": false,
|
| 481 |
+
"should_log": false,
|
| 482 |
+
"should_save": true,
|
| 483 |
+
"should_training_stop": true
|
| 484 |
+
},
|
| 485 |
+
"attributes": {}
|
| 486 |
+
}
|
| 487 |
+
},
|
| 488 |
+
"total_flos": 1.1924847694411776e+16,
|
| 489 |
+
"train_batch_size": 16,
|
| 490 |
+
"trial_name": null,
|
| 491 |
+
"trial_params": null
|
| 492 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0dd502d0f5ecea78370e91a9ffb7be8da59cabf897e0045351baee36c3d2825
|
| 3 |
+
size 5368
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|