Commit
•
72eafa9
1
Parent(s):
18c5269
Upload 8 files
Browse files- config.json +40 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scaler.pt +3 -0
- scheduler.pt +3 -0
- trainer_state.json +592 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "LABEL_0",
|
| 15 |
+
"1": "LABEL_1",
|
| 16 |
+
"2": "LABEL_2",
|
| 17 |
+
"3": "LABEL_3"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"LABEL_0": 0,
|
| 23 |
+
"LABEL_1": 1,
|
| 24 |
+
"LABEL_2": 2,
|
| 25 |
+
"LABEL_3": 3
|
| 26 |
+
},
|
| 27 |
+
"layer_norm_eps": 1e-05,
|
| 28 |
+
"max_position_embeddings": 514,
|
| 29 |
+
"model_type": "roberta",
|
| 30 |
+
"num_attention_heads": 12,
|
| 31 |
+
"num_hidden_layers": 12,
|
| 32 |
+
"pad_token_id": 1,
|
| 33 |
+
"position_embedding_type": "absolute",
|
| 34 |
+
"problem_type": "single_label_classification",
|
| 35 |
+
"torch_dtype": "float32",
|
| 36 |
+
"transformers_version": "4.27.4",
|
| 37 |
+
"type_vocab_size": 1,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 50265
|
| 40 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a3e1674b3faf8ea0e82886f28ee49a70ef6461af6b43029509947f2f96954a4
|
| 3 |
+
size 997307525
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:720eef0d05d24e8ff124366d6e5d500ed34b8b351418377e48f097b3abba6e6a
|
| 3 |
+
size 498668213
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ab451aa25eaaf03593b6363ba305a257dfcf29c488587543b3f7fcb8c6f4155
|
| 3 |
+
size 14575
|
scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ca867262d075cd763adcbb91df48ef4b716842eebb359f206cd355f75e4753f
|
| 3 |
+
size 557
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:835eb75bd5f9de1330d27eabf00fa58fc943ce35b545ca395f4bf46f33038f38
|
| 3 |
+
size 627
|
trainer_state.json
ADDED
|
@@ -0,0 +1,592 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.15928590297698975,
|
| 3 |
+
"best_model_checkpoint": "./output4/checkpoint-512",
|
| 4 |
+
"epoch": 4.6413597733711045,
|
| 5 |
+
"global_step": 512,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.07,
|
| 12 |
+
"learning_rate": 4.000000000000001e-06,
|
| 13 |
+
"loss": 1.3914,
|
| 14 |
+
"step": 8
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.15,
|
| 18 |
+
"learning_rate": 8.000000000000001e-06,
|
| 19 |
+
"loss": 1.3829,
|
| 20 |
+
"step": 16
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.22,
|
| 24 |
+
"learning_rate": 1.2e-05,
|
| 25 |
+
"loss": 1.3398,
|
| 26 |
+
"step": 24
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.29,
|
| 30 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 31 |
+
"loss": 1.0594,
|
| 32 |
+
"step": 32
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.29,
|
| 36 |
+
"eval_accuracy": 0.8646052631578948,
|
| 37 |
+
"eval_f1": 0.8637236213946768,
|
| 38 |
+
"eval_loss": 0.6905946731567383,
|
| 39 |
+
"eval_precision": 0.8650720213650118,
|
| 40 |
+
"eval_recall": 0.8646052631578948,
|
| 41 |
+
"eval_runtime": 27.1686,
|
| 42 |
+
"eval_samples_per_second": 279.735,
|
| 43 |
+
"eval_steps_per_second": 4.122,
|
| 44 |
+
"step": 32
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.36,
|
| 48 |
+
"learning_rate": 2e-05,
|
| 49 |
+
"loss": 0.5565,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.44,
|
| 54 |
+
"learning_rate": 2.4e-05,
|
| 55 |
+
"loss": 0.3452,
|
| 56 |
+
"step": 48
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.51,
|
| 60 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 61 |
+
"loss": 0.2851,
|
| 62 |
+
"step": 56
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.58,
|
| 66 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 67 |
+
"loss": 0.2791,
|
| 68 |
+
"step": 64
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.58,
|
| 72 |
+
"eval_accuracy": 0.9181578947368421,
|
| 73 |
+
"eval_f1": 0.9178446745855575,
|
| 74 |
+
"eval_loss": 0.2583260238170624,
|
| 75 |
+
"eval_precision": 0.9178522458398034,
|
| 76 |
+
"eval_recall": 0.9181578947368422,
|
| 77 |
+
"eval_runtime": 27.1489,
|
| 78 |
+
"eval_samples_per_second": 279.938,
|
| 79 |
+
"eval_steps_per_second": 4.125,
|
| 80 |
+
"step": 64
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.65,
|
| 84 |
+
"learning_rate": 3.6e-05,
|
| 85 |
+
"loss": 0.2591,
|
| 86 |
+
"step": 72
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.73,
|
| 90 |
+
"learning_rate": 4e-05,
|
| 91 |
+
"loss": 0.2432,
|
| 92 |
+
"step": 80
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.8,
|
| 96 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 97 |
+
"loss": 0.2259,
|
| 98 |
+
"step": 88
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.87,
|
| 102 |
+
"learning_rate": 4.8e-05,
|
| 103 |
+
"loss": 0.2263,
|
| 104 |
+
"step": 96
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.87,
|
| 108 |
+
"eval_accuracy": 0.9243421052631579,
|
| 109 |
+
"eval_f1": 0.9244165095066339,
|
| 110 |
+
"eval_loss": 0.21840104460716248,
|
| 111 |
+
"eval_precision": 0.9274635904725687,
|
| 112 |
+
"eval_recall": 0.924342105263158,
|
| 113 |
+
"eval_runtime": 27.1511,
|
| 114 |
+
"eval_samples_per_second": 279.915,
|
| 115 |
+
"eval_steps_per_second": 4.125,
|
| 116 |
+
"step": 96
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.94,
|
| 120 |
+
"learning_rate": 4.955555555555556e-05,
|
| 121 |
+
"loss": 0.2172,
|
| 122 |
+
"step": 104
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.02,
|
| 126 |
+
"learning_rate": 4.866666666666667e-05,
|
| 127 |
+
"loss": 0.1923,
|
| 128 |
+
"step": 112
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 1.09,
|
| 132 |
+
"learning_rate": 4.7777777777777784e-05,
|
| 133 |
+
"loss": 0.1875,
|
| 134 |
+
"step": 120
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 1.16,
|
| 138 |
+
"learning_rate": 4.6888888888888895e-05,
|
| 139 |
+
"loss": 0.1826,
|
| 140 |
+
"step": 128
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"epoch": 1.16,
|
| 144 |
+
"eval_accuracy": 0.9380263157894737,
|
| 145 |
+
"eval_f1": 0.9380307153953753,
|
| 146 |
+
"eval_loss": 0.18940293788909912,
|
| 147 |
+
"eval_precision": 0.9385987876450141,
|
| 148 |
+
"eval_recall": 0.9380263157894737,
|
| 149 |
+
"eval_runtime": 27.4492,
|
| 150 |
+
"eval_samples_per_second": 276.876,
|
| 151 |
+
"eval_steps_per_second": 4.08,
|
| 152 |
+
"step": 128
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.23,
|
| 156 |
+
"learning_rate": 4.600000000000001e-05,
|
| 157 |
+
"loss": 0.1835,
|
| 158 |
+
"step": 136
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.31,
|
| 162 |
+
"learning_rate": 4.511111111111112e-05,
|
| 163 |
+
"loss": 0.1637,
|
| 164 |
+
"step": 144
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.38,
|
| 168 |
+
"learning_rate": 4.422222222222222e-05,
|
| 169 |
+
"loss": 0.1598,
|
| 170 |
+
"step": 152
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.45,
|
| 174 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 175 |
+
"loss": 0.1828,
|
| 176 |
+
"step": 160
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.45,
|
| 180 |
+
"eval_accuracy": 0.9384210526315789,
|
| 181 |
+
"eval_f1": 0.9381955707045027,
|
| 182 |
+
"eval_loss": 0.18510125577449799,
|
| 183 |
+
"eval_precision": 0.9406898302033526,
|
| 184 |
+
"eval_recall": 0.9384210526315789,
|
| 185 |
+
"eval_runtime": 27.1424,
|
| 186 |
+
"eval_samples_per_second": 280.004,
|
| 187 |
+
"eval_steps_per_second": 4.126,
|
| 188 |
+
"step": 160
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.52,
|
| 192 |
+
"learning_rate": 4.2444444444444445e-05,
|
| 193 |
+
"loss": 0.1722,
|
| 194 |
+
"step": 168
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.6,
|
| 198 |
+
"learning_rate": 4.155555555555556e-05,
|
| 199 |
+
"loss": 0.1674,
|
| 200 |
+
"step": 176
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.67,
|
| 204 |
+
"learning_rate": 4.066666666666667e-05,
|
| 205 |
+
"loss": 0.1678,
|
| 206 |
+
"step": 184
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 1.74,
|
| 210 |
+
"learning_rate": 3.977777777777778e-05,
|
| 211 |
+
"loss": 0.1608,
|
| 212 |
+
"step": 192
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 1.74,
|
| 216 |
+
"eval_accuracy": 0.9396052631578947,
|
| 217 |
+
"eval_f1": 0.939515727059736,
|
| 218 |
+
"eval_loss": 0.17982347309589386,
|
| 219 |
+
"eval_precision": 0.9416077079782574,
|
| 220 |
+
"eval_recall": 0.9396052631578948,
|
| 221 |
+
"eval_runtime": 27.1356,
|
| 222 |
+
"eval_samples_per_second": 280.075,
|
| 223 |
+
"eval_steps_per_second": 4.127,
|
| 224 |
+
"step": 192
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.81,
|
| 228 |
+
"learning_rate": 3.888888888888889e-05,
|
| 229 |
+
"loss": 0.1697,
|
| 230 |
+
"step": 200
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 1.89,
|
| 234 |
+
"learning_rate": 3.8e-05,
|
| 235 |
+
"loss": 0.1728,
|
| 236 |
+
"step": 208
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 1.96,
|
| 240 |
+
"learning_rate": 3.7111111111111113e-05,
|
| 241 |
+
"loss": 0.1718,
|
| 242 |
+
"step": 216
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 2.03,
|
| 246 |
+
"learning_rate": 3.6222222222222225e-05,
|
| 247 |
+
"loss": 0.1502,
|
| 248 |
+
"step": 224
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.03,
|
| 252 |
+
"eval_accuracy": 0.9496052631578947,
|
| 253 |
+
"eval_f1": 0.9496119126383771,
|
| 254 |
+
"eval_loss": 0.15795519948005676,
|
| 255 |
+
"eval_precision": 0.9496711091764023,
|
| 256 |
+
"eval_recall": 0.9496052631578947,
|
| 257 |
+
"eval_runtime": 27.1505,
|
| 258 |
+
"eval_samples_per_second": 279.921,
|
| 259 |
+
"eval_steps_per_second": 4.125,
|
| 260 |
+
"step": 224
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.1,
|
| 264 |
+
"learning_rate": 3.5333333333333336e-05,
|
| 265 |
+
"loss": 0.1359,
|
| 266 |
+
"step": 232
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.18,
|
| 270 |
+
"learning_rate": 3.444444444444445e-05,
|
| 271 |
+
"loss": 0.1343,
|
| 272 |
+
"step": 240
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.25,
|
| 276 |
+
"learning_rate": 3.355555555555556e-05,
|
| 277 |
+
"loss": 0.1199,
|
| 278 |
+
"step": 248
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 2.32,
|
| 282 |
+
"learning_rate": 3.266666666666667e-05,
|
| 283 |
+
"loss": 0.1424,
|
| 284 |
+
"step": 256
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 2.32,
|
| 288 |
+
"eval_accuracy": 0.9465789473684211,
|
| 289 |
+
"eval_f1": 0.9465467539090038,
|
| 290 |
+
"eval_loss": 0.15993377566337585,
|
| 291 |
+
"eval_precision": 0.9471187943151717,
|
| 292 |
+
"eval_recall": 0.9465789473684211,
|
| 293 |
+
"eval_runtime": 27.1331,
|
| 294 |
+
"eval_samples_per_second": 280.1,
|
| 295 |
+
"eval_steps_per_second": 4.128,
|
| 296 |
+
"step": 256
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.39,
|
| 300 |
+
"learning_rate": 3.177777777777778e-05,
|
| 301 |
+
"loss": 0.1245,
|
| 302 |
+
"step": 264
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 2.47,
|
| 306 |
+
"learning_rate": 3.088888888888889e-05,
|
| 307 |
+
"loss": 0.1314,
|
| 308 |
+
"step": 272
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 2.54,
|
| 312 |
+
"learning_rate": 3e-05,
|
| 313 |
+
"loss": 0.1301,
|
| 314 |
+
"step": 280
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 2.61,
|
| 318 |
+
"learning_rate": 2.9111111111111112e-05,
|
| 319 |
+
"loss": 0.1383,
|
| 320 |
+
"step": 288
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.61,
|
| 324 |
+
"eval_accuracy": 0.9456578947368421,
|
| 325 |
+
"eval_f1": 0.94558793989311,
|
| 326 |
+
"eval_loss": 0.16593697667121887,
|
| 327 |
+
"eval_precision": 0.9469255477230607,
|
| 328 |
+
"eval_recall": 0.9456578947368421,
|
| 329 |
+
"eval_runtime": 27.1781,
|
| 330 |
+
"eval_samples_per_second": 279.637,
|
| 331 |
+
"eval_steps_per_second": 4.121,
|
| 332 |
+
"step": 288
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.68,
|
| 336 |
+
"learning_rate": 2.8222222222222223e-05,
|
| 337 |
+
"loss": 0.143,
|
| 338 |
+
"step": 296
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.76,
|
| 342 |
+
"learning_rate": 2.733333333333333e-05,
|
| 343 |
+
"loss": 0.1273,
|
| 344 |
+
"step": 304
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.83,
|
| 348 |
+
"learning_rate": 2.6444444444444443e-05,
|
| 349 |
+
"loss": 0.1208,
|
| 350 |
+
"step": 312
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.9,
|
| 354 |
+
"learning_rate": 2.5555555555555554e-05,
|
| 355 |
+
"loss": 0.1235,
|
| 356 |
+
"step": 320
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 2.9,
|
| 360 |
+
"eval_accuracy": 0.9478947368421052,
|
| 361 |
+
"eval_f1": 0.947742882839795,
|
| 362 |
+
"eval_loss": 0.16203150153160095,
|
| 363 |
+
"eval_precision": 0.9479819938629999,
|
| 364 |
+
"eval_recall": 0.9478947368421052,
|
| 365 |
+
"eval_runtime": 27.1639,
|
| 366 |
+
"eval_samples_per_second": 279.783,
|
| 367 |
+
"eval_steps_per_second": 4.123,
|
| 368 |
+
"step": 320
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.97,
|
| 372 |
+
"learning_rate": 2.466666666666667e-05,
|
| 373 |
+
"loss": 0.1358,
|
| 374 |
+
"step": 328
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 3.05,
|
| 378 |
+
"learning_rate": 2.377777777777778e-05,
|
| 379 |
+
"loss": 0.1202,
|
| 380 |
+
"step": 336
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"epoch": 3.12,
|
| 384 |
+
"learning_rate": 2.288888888888889e-05,
|
| 385 |
+
"loss": 0.1095,
|
| 386 |
+
"step": 344
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"epoch": 3.19,
|
| 390 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 391 |
+
"loss": 0.0992,
|
| 392 |
+
"step": 352
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 3.19,
|
| 396 |
+
"eval_accuracy": 0.9488157894736842,
|
| 397 |
+
"eval_f1": 0.9486994674641721,
|
| 398 |
+
"eval_loss": 0.1663181036710739,
|
| 399 |
+
"eval_precision": 0.9488005469862106,
|
| 400 |
+
"eval_recall": 0.9488157894736843,
|
| 401 |
+
"eval_runtime": 27.1653,
|
| 402 |
+
"eval_samples_per_second": 279.768,
|
| 403 |
+
"eval_steps_per_second": 4.123,
|
| 404 |
+
"step": 352
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.26,
|
| 408 |
+
"learning_rate": 2.111111111111111e-05,
|
| 409 |
+
"loss": 0.1007,
|
| 410 |
+
"step": 360
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 3.34,
|
| 414 |
+
"learning_rate": 2.0222222222222222e-05,
|
| 415 |
+
"loss": 0.0977,
|
| 416 |
+
"step": 368
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 3.41,
|
| 420 |
+
"learning_rate": 1.9333333333333333e-05,
|
| 421 |
+
"loss": 0.1016,
|
| 422 |
+
"step": 376
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.48,
|
| 426 |
+
"learning_rate": 1.8444444444444445e-05,
|
| 427 |
+
"loss": 0.1066,
|
| 428 |
+
"step": 384
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.48,
|
| 432 |
+
"eval_accuracy": 0.9498684210526316,
|
| 433 |
+
"eval_f1": 0.949775085232258,
|
| 434 |
+
"eval_loss": 0.16165488958358765,
|
| 435 |
+
"eval_precision": 0.9500336429691177,
|
| 436 |
+
"eval_recall": 0.9498684210526316,
|
| 437 |
+
"eval_runtime": 27.1538,
|
| 438 |
+
"eval_samples_per_second": 279.887,
|
| 439 |
+
"eval_steps_per_second": 4.125,
|
| 440 |
+
"step": 384
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 3.55,
|
| 444 |
+
"learning_rate": 1.7555555555555556e-05,
|
| 445 |
+
"loss": 0.1096,
|
| 446 |
+
"step": 392
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 3.63,
|
| 450 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 451 |
+
"loss": 0.1028,
|
| 452 |
+
"step": 400
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 3.7,
|
| 456 |
+
"learning_rate": 1.577777777777778e-05,
|
| 457 |
+
"loss": 0.1054,
|
| 458 |
+
"step": 408
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 3.77,
|
| 462 |
+
"learning_rate": 1.4888888888888888e-05,
|
| 463 |
+
"loss": 0.0982,
|
| 464 |
+
"step": 416
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 3.77,
|
| 468 |
+
"eval_accuracy": 0.9485526315789473,
|
| 469 |
+
"eval_f1": 0.9484327367127127,
|
| 470 |
+
"eval_loss": 0.161124125123024,
|
| 471 |
+
"eval_precision": 0.9491280462351354,
|
| 472 |
+
"eval_recall": 0.9485526315789473,
|
| 473 |
+
"eval_runtime": 27.1519,
|
| 474 |
+
"eval_samples_per_second": 279.907,
|
| 475 |
+
"eval_steps_per_second": 4.125,
|
| 476 |
+
"step": 416
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 3.84,
|
| 480 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 481 |
+
"loss": 0.1051,
|
| 482 |
+
"step": 424
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.92,
|
| 486 |
+
"learning_rate": 1.3111111111111113e-05,
|
| 487 |
+
"loss": 0.1051,
|
| 488 |
+
"step": 432
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.99,
|
| 492 |
+
"learning_rate": 1.2222222222222222e-05,
|
| 493 |
+
"loss": 0.1041,
|
| 494 |
+
"step": 440
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.06,
|
| 498 |
+
"learning_rate": 1.1333333333333334e-05,
|
| 499 |
+
"loss": 0.0887,
|
| 500 |
+
"step": 448
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.06,
|
| 504 |
+
"eval_accuracy": 0.9506578947368421,
|
| 505 |
+
"eval_f1": 0.9505658100077847,
|
| 506 |
+
"eval_loss": 0.15977711975574493,
|
| 507 |
+
"eval_precision": 0.9508508453699076,
|
| 508 |
+
"eval_recall": 0.9506578947368421,
|
| 509 |
+
"eval_runtime": 27.1343,
|
| 510 |
+
"eval_samples_per_second": 280.089,
|
| 511 |
+
"eval_steps_per_second": 4.128,
|
| 512 |
+
"step": 448
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 4.13,
|
| 516 |
+
"learning_rate": 1.0444444444444445e-05,
|
| 517 |
+
"loss": 0.0778,
|
| 518 |
+
"step": 456
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 4.21,
|
| 522 |
+
"learning_rate": 9.555555555555556e-06,
|
| 523 |
+
"loss": 0.0858,
|
| 524 |
+
"step": 464
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 4.28,
|
| 528 |
+
"learning_rate": 8.666666666666668e-06,
|
| 529 |
+
"loss": 0.0872,
|
| 530 |
+
"step": 472
|
| 531 |
+
},
|
| 532 |
+
{
|
| 533 |
+
"epoch": 4.35,
|
| 534 |
+
"learning_rate": 7.777777777777777e-06,
|
| 535 |
+
"loss": 0.0891,
|
| 536 |
+
"step": 480
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 4.35,
|
| 540 |
+
"eval_accuracy": 0.9511842105263157,
|
| 541 |
+
"eval_f1": 0.9511326895081746,
|
| 542 |
+
"eval_loss": 0.16269291937351227,
|
| 543 |
+
"eval_precision": 0.9510882932907387,
|
| 544 |
+
"eval_recall": 0.9511842105263157,
|
| 545 |
+
"eval_runtime": 27.0255,
|
| 546 |
+
"eval_samples_per_second": 281.216,
|
| 547 |
+
"eval_steps_per_second": 4.144,
|
| 548 |
+
"step": 480
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 4.42,
|
| 552 |
+
"learning_rate": 6.888888888888889e-06,
|
| 553 |
+
"loss": 0.0887,
|
| 554 |
+
"step": 488
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 4.5,
|
| 558 |
+
"learning_rate": 6e-06,
|
| 559 |
+
"loss": 0.0867,
|
| 560 |
+
"step": 496
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.57,
|
| 564 |
+
"learning_rate": 5.1111111111111115e-06,
|
| 565 |
+
"loss": 0.091,
|
| 566 |
+
"step": 504
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 4.64,
|
| 570 |
+
"learning_rate": 4.222222222222223e-06,
|
| 571 |
+
"loss": 0.0802,
|
| 572 |
+
"step": 512
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 4.64,
|
| 576 |
+
"eval_accuracy": 0.950921052631579,
|
| 577 |
+
"eval_f1": 0.9509254806694175,
|
| 578 |
+
"eval_loss": 0.15928590297698975,
|
| 579 |
+
"eval_precision": 0.9511139611391479,
|
| 580 |
+
"eval_recall": 0.9509210526315789,
|
| 581 |
+
"eval_runtime": 27.0214,
|
| 582 |
+
"eval_samples_per_second": 281.259,
|
| 583 |
+
"eval_steps_per_second": 4.145,
|
| 584 |
+
"step": 512
|
| 585 |
+
}
|
| 586 |
+
],
|
| 587 |
+
"max_steps": 550,
|
| 588 |
+
"num_train_epochs": 5,
|
| 589 |
+
"total_flos": 1.465491747347497e+17,
|
| 590 |
+
"trial_name": null,
|
| 591 |
+
"trial_params": null
|
| 592 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1397788e80a5f1db87ce028af93845ff143df8ce8662472ad3a90dafe8ea2f95
|
| 3 |
+
size 3515
|