Upload 7 files
Browse files- config.json +44 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +570 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "klue/bert-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"hidden_act": "gelu",
|
| 9 |
+
"hidden_dropout_prob": 0.1,
|
| 10 |
+
"hidden_size": 768,
|
| 11 |
+
"id2label": {
|
| 12 |
+
"0": "LABEL_0",
|
| 13 |
+
"1": "LABEL_1",
|
| 14 |
+
"2": "LABEL_2",
|
| 15 |
+
"3": "LABEL_3",
|
| 16 |
+
"4": "LABEL_4",
|
| 17 |
+
"5": "LABEL_5",
|
| 18 |
+
"6": "LABEL_6"
|
| 19 |
+
},
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 3072,
|
| 22 |
+
"label2id": {
|
| 23 |
+
"LABEL_0": 0,
|
| 24 |
+
"LABEL_1": 1,
|
| 25 |
+
"LABEL_2": 2,
|
| 26 |
+
"LABEL_3": 3,
|
| 27 |
+
"LABEL_4": 4,
|
| 28 |
+
"LABEL_5": 5,
|
| 29 |
+
"LABEL_6": 6
|
| 30 |
+
},
|
| 31 |
+
"layer_norm_eps": 1e-12,
|
| 32 |
+
"max_position_embeddings": 512,
|
| 33 |
+
"model_type": "bert",
|
| 34 |
+
"num_attention_heads": 12,
|
| 35 |
+
"num_hidden_layers": 12,
|
| 36 |
+
"pad_token_id": 0,
|
| 37 |
+
"position_embedding_type": "absolute",
|
| 38 |
+
"problem_type": "single_label_classification",
|
| 39 |
+
"torch_dtype": "float32",
|
| 40 |
+
"transformers_version": "4.46.1",
|
| 41 |
+
"type_vocab_size": 2,
|
| 42 |
+
"use_cache": true,
|
| 43 |
+
"vocab_size": 32000
|
| 44 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6d69fd3b07839a370f696636a37793b8baade9734b03e9841ad7b96da88c3dd
|
| 3 |
+
size 442514444
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9095c169227d79339439d844811a97cfaa2e12577be53f46f05cca7e41e4b8b
|
| 3 |
+
size 885149946
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbccc70bd33155ac584a271ef918f2788d349e8731ac943c0a3e0a7534674813
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54c7bfe41b244ff7fac493dc230b65609829d3986f8020d396a6f4190d3e5594
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,570 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.840443960959029,
|
| 3 |
+
"best_model_checkpoint": "/data/ephemeral/home/level2-nlp-datacentric-nlp-15/models/train_new_8564_7000fconcat+deepl_15000.csv_20241107_163124/checkpoint-600",
|
| 4 |
+
"epoch": 2.0,
|
| 5 |
+
"eval_steps": 100,
|
| 6 |
+
"global_step": 692,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.028901734104046242,
|
| 13 |
+
"grad_norm": 5.670835018157959,
|
| 14 |
+
"learning_rate": 1.971098265895954e-05,
|
| 15 |
+
"loss": 1.8852,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.057803468208092484,
|
| 20 |
+
"grad_norm": 5.40836763381958,
|
| 21 |
+
"learning_rate": 1.9421965317919077e-05,
|
| 22 |
+
"loss": 1.6768,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08670520231213873,
|
| 27 |
+
"grad_norm": 6.977480888366699,
|
| 28 |
+
"learning_rate": 1.9132947976878615e-05,
|
| 29 |
+
"loss": 1.4293,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.11560693641618497,
|
| 34 |
+
"grad_norm": 6.8324995040893555,
|
| 35 |
+
"learning_rate": 1.8843930635838153e-05,
|
| 36 |
+
"loss": 1.2372,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.14450867052023122,
|
| 41 |
+
"grad_norm": 4.969491481781006,
|
| 42 |
+
"learning_rate": 1.855491329479769e-05,
|
| 43 |
+
"loss": 1.0231,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.17341040462427745,
|
| 48 |
+
"grad_norm": 7.948673725128174,
|
| 49 |
+
"learning_rate": 1.8265895953757225e-05,
|
| 50 |
+
"loss": 0.9941,
|
| 51 |
+
"step": 60
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.2023121387283237,
|
| 55 |
+
"grad_norm": 7.314361572265625,
|
| 56 |
+
"learning_rate": 1.7976878612716763e-05,
|
| 57 |
+
"loss": 0.8929,
|
| 58 |
+
"step": 70
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.23121387283236994,
|
| 62 |
+
"grad_norm": 7.860761642456055,
|
| 63 |
+
"learning_rate": 1.76878612716763e-05,
|
| 64 |
+
"loss": 0.7236,
|
| 65 |
+
"step": 80
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.26011560693641617,
|
| 69 |
+
"grad_norm": 8.400164604187012,
|
| 70 |
+
"learning_rate": 1.739884393063584e-05,
|
| 71 |
+
"loss": 0.7342,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.28901734104046245,
|
| 76 |
+
"grad_norm": 5.281578063964844,
|
| 77 |
+
"learning_rate": 1.7109826589595377e-05,
|
| 78 |
+
"loss": 0.7285,
|
| 79 |
+
"step": 100
|
| 80 |
+
},
|
| 81 |
+
{
|
| 82 |
+
"epoch": 0.28901734104046245,
|
| 83 |
+
"eval_f1": 0.7855931775121717,
|
| 84 |
+
"eval_loss": 0.6838143467903137,
|
| 85 |
+
"eval_runtime": 43.4732,
|
| 86 |
+
"eval_samples_per_second": 108.895,
|
| 87 |
+
"eval_steps_per_second": 3.404,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.3179190751445087,
|
| 92 |
+
"grad_norm": 6.559142589569092,
|
| 93 |
+
"learning_rate": 1.6820809248554915e-05,
|
| 94 |
+
"loss": 0.767,
|
| 95 |
+
"step": 110
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.3468208092485549,
|
| 99 |
+
"grad_norm": 6.961650371551514,
|
| 100 |
+
"learning_rate": 1.6531791907514452e-05,
|
| 101 |
+
"loss": 0.72,
|
| 102 |
+
"step": 120
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.37572254335260113,
|
| 106 |
+
"grad_norm": 7.83851432800293,
|
| 107 |
+
"learning_rate": 1.624277456647399e-05,
|
| 108 |
+
"loss": 0.6204,
|
| 109 |
+
"step": 130
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.4046242774566474,
|
| 113 |
+
"grad_norm": 5.967935562133789,
|
| 114 |
+
"learning_rate": 1.5953757225433528e-05,
|
| 115 |
+
"loss": 0.6811,
|
| 116 |
+
"step": 140
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.43352601156069365,
|
| 120 |
+
"grad_norm": 7.195727348327637,
|
| 121 |
+
"learning_rate": 1.5664739884393066e-05,
|
| 122 |
+
"loss": 0.7254,
|
| 123 |
+
"step": 150
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.4624277456647399,
|
| 127 |
+
"grad_norm": 6.0163750648498535,
|
| 128 |
+
"learning_rate": 1.5375722543352604e-05,
|
| 129 |
+
"loss": 0.5248,
|
| 130 |
+
"step": 160
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.4913294797687861,
|
| 134 |
+
"grad_norm": 7.599509239196777,
|
| 135 |
+
"learning_rate": 1.508670520231214e-05,
|
| 136 |
+
"loss": 0.6095,
|
| 137 |
+
"step": 170
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 0.5202312138728323,
|
| 141 |
+
"grad_norm": 11.452792167663574,
|
| 142 |
+
"learning_rate": 1.4797687861271676e-05,
|
| 143 |
+
"loss": 0.6339,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.5491329479768786,
|
| 148 |
+
"grad_norm": 9.863639831542969,
|
| 149 |
+
"learning_rate": 1.4508670520231216e-05,
|
| 150 |
+
"loss": 0.5901,
|
| 151 |
+
"step": 190
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 0.5780346820809249,
|
| 155 |
+
"grad_norm": 6.931671619415283,
|
| 156 |
+
"learning_rate": 1.4219653179190754e-05,
|
| 157 |
+
"loss": 0.5106,
|
| 158 |
+
"step": 200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.5780346820809249,
|
| 162 |
+
"eval_f1": 0.8163391427279263,
|
| 163 |
+
"eval_loss": 0.604805588722229,
|
| 164 |
+
"eval_runtime": 43.5017,
|
| 165 |
+
"eval_samples_per_second": 108.823,
|
| 166 |
+
"eval_steps_per_second": 3.402,
|
| 167 |
+
"step": 200
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.6069364161849711,
|
| 171 |
+
"grad_norm": 7.751237869262695,
|
| 172 |
+
"learning_rate": 1.393063583815029e-05,
|
| 173 |
+
"loss": 0.6615,
|
| 174 |
+
"step": 210
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.6358381502890174,
|
| 178 |
+
"grad_norm": 7.981545925140381,
|
| 179 |
+
"learning_rate": 1.3641618497109828e-05,
|
| 180 |
+
"loss": 0.6194,
|
| 181 |
+
"step": 220
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.6647398843930635,
|
| 185 |
+
"grad_norm": 8.75810432434082,
|
| 186 |
+
"learning_rate": 1.3352601156069365e-05,
|
| 187 |
+
"loss": 0.6756,
|
| 188 |
+
"step": 230
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.6936416184971098,
|
| 192 |
+
"grad_norm": 7.4759521484375,
|
| 193 |
+
"learning_rate": 1.3063583815028902e-05,
|
| 194 |
+
"loss": 0.6079,
|
| 195 |
+
"step": 240
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.7225433526011561,
|
| 199 |
+
"grad_norm": 9.445594787597656,
|
| 200 |
+
"learning_rate": 1.2774566473988441e-05,
|
| 201 |
+
"loss": 0.5329,
|
| 202 |
+
"step": 250
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.7514450867052023,
|
| 206 |
+
"grad_norm": 7.227514266967773,
|
| 207 |
+
"learning_rate": 1.2485549132947979e-05,
|
| 208 |
+
"loss": 0.5342,
|
| 209 |
+
"step": 260
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.7803468208092486,
|
| 213 |
+
"grad_norm": 6.781445503234863,
|
| 214 |
+
"learning_rate": 1.2196531791907515e-05,
|
| 215 |
+
"loss": 0.5455,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.8092485549132948,
|
| 220 |
+
"grad_norm": 7.4944353103637695,
|
| 221 |
+
"learning_rate": 1.1907514450867053e-05,
|
| 222 |
+
"loss": 0.5171,
|
| 223 |
+
"step": 280
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 0.838150289017341,
|
| 227 |
+
"grad_norm": 12.261595726013184,
|
| 228 |
+
"learning_rate": 1.161849710982659e-05,
|
| 229 |
+
"loss": 0.5793,
|
| 230 |
+
"step": 290
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.8670520231213873,
|
| 234 |
+
"grad_norm": 7.033445835113525,
|
| 235 |
+
"learning_rate": 1.1329479768786129e-05,
|
| 236 |
+
"loss": 0.6664,
|
| 237 |
+
"step": 300
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.8670520231213873,
|
| 241 |
+
"eval_f1": 0.8202014204332396,
|
| 242 |
+
"eval_loss": 0.5958309769630432,
|
| 243 |
+
"eval_runtime": 43.4645,
|
| 244 |
+
"eval_samples_per_second": 108.916,
|
| 245 |
+
"eval_steps_per_second": 3.405,
|
| 246 |
+
"step": 300
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.8959537572254336,
|
| 250 |
+
"grad_norm": 16.04691505432129,
|
| 251 |
+
"learning_rate": 1.1040462427745667e-05,
|
| 252 |
+
"loss": 0.5736,
|
| 253 |
+
"step": 310
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.9248554913294798,
|
| 257 |
+
"grad_norm": 6.906232833862305,
|
| 258 |
+
"learning_rate": 1.0751445086705203e-05,
|
| 259 |
+
"loss": 0.5677,
|
| 260 |
+
"step": 320
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.953757225433526,
|
| 264 |
+
"grad_norm": 7.995438098907471,
|
| 265 |
+
"learning_rate": 1.046242774566474e-05,
|
| 266 |
+
"loss": 0.5872,
|
| 267 |
+
"step": 330
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.9826589595375722,
|
| 271 |
+
"grad_norm": 7.967160701751709,
|
| 272 |
+
"learning_rate": 1.0173410404624278e-05,
|
| 273 |
+
"loss": 0.5363,
|
| 274 |
+
"step": 340
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 1.0115606936416186,
|
| 278 |
+
"grad_norm": 7.901902198791504,
|
| 279 |
+
"learning_rate": 9.884393063583816e-06,
|
| 280 |
+
"loss": 0.4558,
|
| 281 |
+
"step": 350
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 1.0404624277456647,
|
| 285 |
+
"grad_norm": 3.8353588581085205,
|
| 286 |
+
"learning_rate": 9.595375722543352e-06,
|
| 287 |
+
"loss": 0.563,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 1.069364161849711,
|
| 292 |
+
"grad_norm": 10.367301940917969,
|
| 293 |
+
"learning_rate": 9.306358381502892e-06,
|
| 294 |
+
"loss": 0.4669,
|
| 295 |
+
"step": 370
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 1.0982658959537572,
|
| 299 |
+
"grad_norm": 3.960563898086548,
|
| 300 |
+
"learning_rate": 9.017341040462428e-06,
|
| 301 |
+
"loss": 0.4186,
|
| 302 |
+
"step": 380
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 1.1271676300578035,
|
| 306 |
+
"grad_norm": 5.368332862854004,
|
| 307 |
+
"learning_rate": 8.728323699421966e-06,
|
| 308 |
+
"loss": 0.4852,
|
| 309 |
+
"step": 390
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.1560693641618498,
|
| 313 |
+
"grad_norm": 4.498876094818115,
|
| 314 |
+
"learning_rate": 8.439306358381504e-06,
|
| 315 |
+
"loss": 0.5515,
|
| 316 |
+
"step": 400
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 1.1560693641618498,
|
| 320 |
+
"eval_f1": 0.832606512739663,
|
| 321 |
+
"eval_loss": 0.5639938116073608,
|
| 322 |
+
"eval_runtime": 43.4855,
|
| 323 |
+
"eval_samples_per_second": 108.864,
|
| 324 |
+
"eval_steps_per_second": 3.403,
|
| 325 |
+
"step": 400
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 1.1849710982658959,
|
| 329 |
+
"grad_norm": 6.101068496704102,
|
| 330 |
+
"learning_rate": 8.150289017341042e-06,
|
| 331 |
+
"loss": 0.5084,
|
| 332 |
+
"step": 410
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 1.2138728323699421,
|
| 336 |
+
"grad_norm": 8.67908000946045,
|
| 337 |
+
"learning_rate": 7.86127167630058e-06,
|
| 338 |
+
"loss": 0.4328,
|
| 339 |
+
"step": 420
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.2427745664739884,
|
| 343 |
+
"grad_norm": 6.932382106781006,
|
| 344 |
+
"learning_rate": 7.5722543352601166e-06,
|
| 345 |
+
"loss": 0.3798,
|
| 346 |
+
"step": 430
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 1.2716763005780347,
|
| 350 |
+
"grad_norm": 6.64376163482666,
|
| 351 |
+
"learning_rate": 7.283236994219654e-06,
|
| 352 |
+
"loss": 0.4763,
|
| 353 |
+
"step": 440
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.300578034682081,
|
| 357 |
+
"grad_norm": 5.648944854736328,
|
| 358 |
+
"learning_rate": 6.9942196531791914e-06,
|
| 359 |
+
"loss": 0.4008,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 1.3294797687861273,
|
| 364 |
+
"grad_norm": 8.3818998336792,
|
| 365 |
+
"learning_rate": 6.7052023121387284e-06,
|
| 366 |
+
"loss": 0.4959,
|
| 367 |
+
"step": 460
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 1.3583815028901733,
|
| 371 |
+
"grad_norm": 6.271963119506836,
|
| 372 |
+
"learning_rate": 6.416184971098266e-06,
|
| 373 |
+
"loss": 0.4123,
|
| 374 |
+
"step": 470
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.3872832369942196,
|
| 378 |
+
"grad_norm": 10.868525505065918,
|
| 379 |
+
"learning_rate": 6.127167630057804e-06,
|
| 380 |
+
"loss": 0.4478,
|
| 381 |
+
"step": 480
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.416184971098266,
|
| 385 |
+
"grad_norm": 4.8018012046813965,
|
| 386 |
+
"learning_rate": 5.838150289017341e-06,
|
| 387 |
+
"loss": 0.3475,
|
| 388 |
+
"step": 490
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 1.4450867052023122,
|
| 392 |
+
"grad_norm": 7.195227146148682,
|
| 393 |
+
"learning_rate": 5.549132947976878e-06,
|
| 394 |
+
"loss": 0.5246,
|
| 395 |
+
"step": 500
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 1.4450867052023122,
|
| 399 |
+
"eval_f1": 0.8394367921843663,
|
| 400 |
+
"eval_loss": 0.5455829501152039,
|
| 401 |
+
"eval_runtime": 43.4865,
|
| 402 |
+
"eval_samples_per_second": 108.861,
|
| 403 |
+
"eval_steps_per_second": 3.403,
|
| 404 |
+
"step": 500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.4739884393063583,
|
| 408 |
+
"grad_norm": 7.47812557220459,
|
| 409 |
+
"learning_rate": 5.260115606936417e-06,
|
| 410 |
+
"loss": 0.4008,
|
| 411 |
+
"step": 510
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.5028901734104045,
|
| 415 |
+
"grad_norm": 3.8493812084198,
|
| 416 |
+
"learning_rate": 4.971098265895954e-06,
|
| 417 |
+
"loss": 0.4166,
|
| 418 |
+
"step": 520
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.5317919075144508,
|
| 422 |
+
"grad_norm": 6.382811069488525,
|
| 423 |
+
"learning_rate": 4.682080924855492e-06,
|
| 424 |
+
"loss": 0.4287,
|
| 425 |
+
"step": 530
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.560693641618497,
|
| 429 |
+
"grad_norm": 4.259267330169678,
|
| 430 |
+
"learning_rate": 4.3930635838150296e-06,
|
| 431 |
+
"loss": 0.4493,
|
| 432 |
+
"step": 540
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.5895953757225434,
|
| 436 |
+
"grad_norm": 5.338929653167725,
|
| 437 |
+
"learning_rate": 4.1040462427745666e-06,
|
| 438 |
+
"loss": 0.4488,
|
| 439 |
+
"step": 550
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 1.6184971098265897,
|
| 443 |
+
"grad_norm": 4.65845251083374,
|
| 444 |
+
"learning_rate": 3.815028901734104e-06,
|
| 445 |
+
"loss": 0.4649,
|
| 446 |
+
"step": 560
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 1.647398843930636,
|
| 450 |
+
"grad_norm": 8.946381568908691,
|
| 451 |
+
"learning_rate": 3.526011560693642e-06,
|
| 452 |
+
"loss": 0.4826,
|
| 453 |
+
"step": 570
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.6763005780346822,
|
| 457 |
+
"grad_norm": 10.277519226074219,
|
| 458 |
+
"learning_rate": 3.2369942196531797e-06,
|
| 459 |
+
"loss": 0.4061,
|
| 460 |
+
"step": 580
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 1.7052023121387283,
|
| 464 |
+
"grad_norm": 9.004323959350586,
|
| 465 |
+
"learning_rate": 2.947976878612717e-06,
|
| 466 |
+
"loss": 0.463,
|
| 467 |
+
"step": 590
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 1.7341040462427746,
|
| 471 |
+
"grad_norm": 9.768237113952637,
|
| 472 |
+
"learning_rate": 2.658959537572254e-06,
|
| 473 |
+
"loss": 0.407,
|
| 474 |
+
"step": 600
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 1.7341040462427746,
|
| 478 |
+
"eval_f1": 0.840443960959029,
|
| 479 |
+
"eval_loss": 0.5418282151222229,
|
| 480 |
+
"eval_runtime": 43.4552,
|
| 481 |
+
"eval_samples_per_second": 108.94,
|
| 482 |
+
"eval_steps_per_second": 3.406,
|
| 483 |
+
"step": 600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.7630057803468207,
|
| 487 |
+
"grad_norm": 3.791731119155884,
|
| 488 |
+
"learning_rate": 2.369942196531792e-06,
|
| 489 |
+
"loss": 0.4195,
|
| 490 |
+
"step": 610
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.791907514450867,
|
| 494 |
+
"grad_norm": 9.772268295288086,
|
| 495 |
+
"learning_rate": 2.08092485549133e-06,
|
| 496 |
+
"loss": 0.4644,
|
| 497 |
+
"step": 620
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.8208092485549132,
|
| 501 |
+
"grad_norm": 5.360107421875,
|
| 502 |
+
"learning_rate": 1.791907514450867e-06,
|
| 503 |
+
"loss": 0.4315,
|
| 504 |
+
"step": 630
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.8497109826589595,
|
| 508 |
+
"grad_norm": 9.654316902160645,
|
| 509 |
+
"learning_rate": 1.502890173410405e-06,
|
| 510 |
+
"loss": 0.435,
|
| 511 |
+
"step": 640
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.8786127167630058,
|
| 515 |
+
"grad_norm": 6.9839768409729,
|
| 516 |
+
"learning_rate": 1.2138728323699423e-06,
|
| 517 |
+
"loss": 0.387,
|
| 518 |
+
"step": 650
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.907514450867052,
|
| 522 |
+
"grad_norm": 8.008018493652344,
|
| 523 |
+
"learning_rate": 9.248554913294798e-07,
|
| 524 |
+
"loss": 0.4039,
|
| 525 |
+
"step": 660
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.9364161849710984,
|
| 529 |
+
"grad_norm": 7.851306438446045,
|
| 530 |
+
"learning_rate": 6.358381502890174e-07,
|
| 531 |
+
"loss": 0.4879,
|
| 532 |
+
"step": 670
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 1.9653179190751446,
|
| 536 |
+
"grad_norm": 10.8189115524292,
|
| 537 |
+
"learning_rate": 3.468208092485549e-07,
|
| 538 |
+
"loss": 0.3706,
|
| 539 |
+
"step": 680
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.9942196531791907,
|
| 543 |
+
"grad_norm": 8.877676963806152,
|
| 544 |
+
"learning_rate": 5.7803468208092485e-08,
|
| 545 |
+
"loss": 0.3861,
|
| 546 |
+
"step": 690
|
| 547 |
+
}
|
| 548 |
+
],
|
| 549 |
+
"logging_steps": 10,
|
| 550 |
+
"max_steps": 692,
|
| 551 |
+
"num_input_tokens_seen": 0,
|
| 552 |
+
"num_train_epochs": 2,
|
| 553 |
+
"save_steps": 100,
|
| 554 |
+
"stateful_callbacks": {
|
| 555 |
+
"TrainerControl": {
|
| 556 |
+
"args": {
|
| 557 |
+
"should_epoch_stop": false,
|
| 558 |
+
"should_evaluate": false,
|
| 559 |
+
"should_log": false,
|
| 560 |
+
"should_save": true,
|
| 561 |
+
"should_training_stop": true
|
| 562 |
+
},
|
| 563 |
+
"attributes": {}
|
| 564 |
+
}
|
| 565 |
+
},
|
| 566 |
+
"total_flos": 5812910382182400.0,
|
| 567 |
+
"train_batch_size": 32,
|
| 568 |
+
"trial_name": null,
|
| 569 |
+
"trial_params": null
|
| 570 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7df685089f1fda54845a56c2b08b81de31e89a39f766a00e859a228c00d1693e
|
| 3 |
+
size 5432
|