Upload folder using huggingface_hub
Browse files- config.json +36 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- scheduler.pt +3 -0
- trainer_state.json +402 -0
- training_args.bin +3 -0
config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "AI-Sweden-Models/roberta-large-1160k",
|
| 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": 1024,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "incorrect",
|
| 15 |
+
"1": "correct"
|
| 16 |
+
},
|
| 17 |
+
"initializer_range": 0.02,
|
| 18 |
+
"intermediate_size": 4096,
|
| 19 |
+
"label2id": {
|
| 20 |
+
"correct": 1,
|
| 21 |
+
"incorrect": 0
|
| 22 |
+
},
|
| 23 |
+
"layer_norm_eps": 1e-05,
|
| 24 |
+
"max_position_embeddings": 514,
|
| 25 |
+
"model_type": "roberta",
|
| 26 |
+
"num_attention_heads": 16,
|
| 27 |
+
"num_hidden_layers": 24,
|
| 28 |
+
"pad_token_id": 1,
|
| 29 |
+
"position_embedding_type": "absolute",
|
| 30 |
+
"problem_type": "single_label_classification",
|
| 31 |
+
"torch_dtype": "float32",
|
| 32 |
+
"transformers_version": "4.47.0",
|
| 33 |
+
"type_vocab_size": 1,
|
| 34 |
+
"use_cache": true,
|
| 35 |
+
"vocab_size": 50265
|
| 36 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c49f6e060df6810f3b91880527af078de63d239d1fc6960413004323440b6325
|
| 3 |
+
size 1421495416
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e9b35295a7ac37f48cd97ccda43ae9386204ce4b83f320b81a195618797937f6
|
| 3 |
+
size 2843223277
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97a5fc467aebdd5947e6fdbc15e65b0948e3cb5874fefd70a99a6ce05ba3c20a
|
| 3 |
+
size 14704
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1dd9275dfbf0a38b644d4a59eea3fb4e6b9f93ebfee6b921866c5316ac20cce4
|
| 3 |
+
size 14704
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6e295970091b09d252fe330ced255eba3cc49d47701531bfd028f7eaa8e1783
|
| 3 |
+
size 14704
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e965798c4e2d47a637b156503287771f09488f07dc245312937d45f728b9bbac
|
| 3 |
+
size 1064
|
trainer_state.json
ADDED
|
@@ -0,0 +1,402 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8716280849435623,
|
| 3 |
+
"best_model_checkpoint": "best_model_big/checkpoint-2968",
|
| 4 |
+
"epoch": 5.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3710,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.1347708894878706,
|
| 13 |
+
"grad_norm": 18.93534278869629,
|
| 14 |
+
"learning_rate": 1.946091644204852e-05,
|
| 15 |
+
"loss": 0.5038,
|
| 16 |
+
"step": 100
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2695417789757412,
|
| 20 |
+
"grad_norm": 7.889501571655273,
|
| 21 |
+
"learning_rate": 1.8921832884097035e-05,
|
| 22 |
+
"loss": 0.4015,
|
| 23 |
+
"step": 200
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.40431266846361186,
|
| 27 |
+
"grad_norm": 17.194637298583984,
|
| 28 |
+
"learning_rate": 1.8382749326145554e-05,
|
| 29 |
+
"loss": 0.359,
|
| 30 |
+
"step": 300
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5390835579514824,
|
| 34 |
+
"grad_norm": 10.652689933776855,
|
| 35 |
+
"learning_rate": 1.7843665768194072e-05,
|
| 36 |
+
"loss": 0.3494,
|
| 37 |
+
"step": 400
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.6738544474393531,
|
| 41 |
+
"grad_norm": 12.343999862670898,
|
| 42 |
+
"learning_rate": 1.7304582210242588e-05,
|
| 43 |
+
"loss": 0.357,
|
| 44 |
+
"step": 500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.8086253369272237,
|
| 48 |
+
"grad_norm": 5.575014114379883,
|
| 49 |
+
"learning_rate": 1.6765498652291106e-05,
|
| 50 |
+
"loss": 0.3446,
|
| 51 |
+
"step": 600
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.9433962264150944,
|
| 55 |
+
"grad_norm": 10.024672508239746,
|
| 56 |
+
"learning_rate": 1.6226415094339625e-05,
|
| 57 |
+
"loss": 0.3307,
|
| 58 |
+
"step": 700
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.0,
|
| 62 |
+
"eval_accuracy": 0.8470863462356444,
|
| 63 |
+
"eval_confusion_matrix": [
|
| 64 |
+
[
|
| 65 |
+
1759,
|
| 66 |
+
519
|
| 67 |
+
],
|
| 68 |
+
[
|
| 69 |
+
200,
|
| 70 |
+
2224
|
| 71 |
+
]
|
| 72 |
+
],
|
| 73 |
+
"eval_f1": 0.8608476872459842,
|
| 74 |
+
"eval_loss": 0.3607315421104431,
|
| 75 |
+
"eval_precision": 0.8107911046299672,
|
| 76 |
+
"eval_recall": 0.9174917491749175,
|
| 77 |
+
"eval_runtime": 22.8032,
|
| 78 |
+
"eval_samples_per_second": 206.199,
|
| 79 |
+
"eval_steps_per_second": 4.298,
|
| 80 |
+
"step": 742
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.0781671159029649,
|
| 84 |
+
"grad_norm": 8.227458000183105,
|
| 85 |
+
"learning_rate": 1.5687331536388143e-05,
|
| 86 |
+
"loss": 0.301,
|
| 87 |
+
"step": 800
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 1.2129380053908356,
|
| 91 |
+
"grad_norm": 13.138360023498535,
|
| 92 |
+
"learning_rate": 1.5148247978436658e-05,
|
| 93 |
+
"loss": 0.261,
|
| 94 |
+
"step": 900
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 1.3477088948787062,
|
| 98 |
+
"grad_norm": 21.908050537109375,
|
| 99 |
+
"learning_rate": 1.4609164420485175e-05,
|
| 100 |
+
"loss": 0.2568,
|
| 101 |
+
"step": 1000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 1.482479784366577,
|
| 105 |
+
"grad_norm": 65.63346862792969,
|
| 106 |
+
"learning_rate": 1.4070080862533696e-05,
|
| 107 |
+
"loss": 0.2525,
|
| 108 |
+
"step": 1100
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 1.6172506738544474,
|
| 112 |
+
"grad_norm": 10.492274284362793,
|
| 113 |
+
"learning_rate": 1.3530997304582212e-05,
|
| 114 |
+
"loss": 0.2738,
|
| 115 |
+
"step": 1200
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 1.7520215633423182,
|
| 119 |
+
"grad_norm": 4.424431800842285,
|
| 120 |
+
"learning_rate": 1.299191374663073e-05,
|
| 121 |
+
"loss": 0.2612,
|
| 122 |
+
"step": 1300
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 1.8867924528301887,
|
| 126 |
+
"grad_norm": 5.688779830932617,
|
| 127 |
+
"learning_rate": 1.2452830188679246e-05,
|
| 128 |
+
"loss": 0.2821,
|
| 129 |
+
"step": 1400
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 2.0,
|
| 133 |
+
"eval_accuracy": 0.8517652062951936,
|
| 134 |
+
"eval_confusion_matrix": [
|
| 135 |
+
[
|
| 136 |
+
1750,
|
| 137 |
+
528
|
| 138 |
+
],
|
| 139 |
+
[
|
| 140 |
+
169,
|
| 141 |
+
2255
|
| 142 |
+
]
|
| 143 |
+
],
|
| 144 |
+
"eval_f1": 0.8661417322834646,
|
| 145 |
+
"eval_loss": 0.3994266390800476,
|
| 146 |
+
"eval_precision": 0.8102766798418972,
|
| 147 |
+
"eval_recall": 0.9302805280528053,
|
| 148 |
+
"eval_runtime": 22.8205,
|
| 149 |
+
"eval_samples_per_second": 206.043,
|
| 150 |
+
"eval_steps_per_second": 4.294,
|
| 151 |
+
"step": 1484
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"epoch": 2.0215633423180592,
|
| 155 |
+
"grad_norm": 17.876014709472656,
|
| 156 |
+
"learning_rate": 1.1913746630727763e-05,
|
| 157 |
+
"loss": 0.2494,
|
| 158 |
+
"step": 1500
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 2.1563342318059298,
|
| 162 |
+
"grad_norm": 30.222442626953125,
|
| 163 |
+
"learning_rate": 1.1374663072776282e-05,
|
| 164 |
+
"loss": 0.2105,
|
| 165 |
+
"step": 1600
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 2.2911051212938007,
|
| 169 |
+
"grad_norm": 8.314850807189941,
|
| 170 |
+
"learning_rate": 1.0835579514824798e-05,
|
| 171 |
+
"loss": 0.2062,
|
| 172 |
+
"step": 1700
|
| 173 |
+
},
|
| 174 |
+
{
|
| 175 |
+
"epoch": 2.4258760107816713,
|
| 176 |
+
"grad_norm": 14.823955535888672,
|
| 177 |
+
"learning_rate": 1.0296495956873315e-05,
|
| 178 |
+
"loss": 0.1949,
|
| 179 |
+
"step": 1800
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 2.560646900269542,
|
| 183 |
+
"grad_norm": 15.158774375915527,
|
| 184 |
+
"learning_rate": 9.757412398921834e-06,
|
| 185 |
+
"loss": 0.2077,
|
| 186 |
+
"step": 1900
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 2.6954177897574123,
|
| 190 |
+
"grad_norm": 3.280972719192505,
|
| 191 |
+
"learning_rate": 9.21832884097035e-06,
|
| 192 |
+
"loss": 0.2029,
|
| 193 |
+
"step": 2000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 2.830188679245283,
|
| 197 |
+
"grad_norm": 23.08829116821289,
|
| 198 |
+
"learning_rate": 8.67924528301887e-06,
|
| 199 |
+
"loss": 0.2147,
|
| 200 |
+
"step": 2100
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.964959568733154,
|
| 204 |
+
"grad_norm": 6.822205543518066,
|
| 205 |
+
"learning_rate": 8.140161725067386e-06,
|
| 206 |
+
"loss": 0.2226,
|
| 207 |
+
"step": 2200
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 3.0,
|
| 211 |
+
"eval_accuracy": 0.8555933645257338,
|
| 212 |
+
"eval_confusion_matrix": [
|
| 213 |
+
[
|
| 214 |
+
1752,
|
| 215 |
+
526
|
| 216 |
+
],
|
| 217 |
+
[
|
| 218 |
+
153,
|
| 219 |
+
2271
|
| 220 |
+
]
|
| 221 |
+
],
|
| 222 |
+
"eval_f1": 0.8699482857690097,
|
| 223 |
+
"eval_loss": 0.482412725687027,
|
| 224 |
+
"eval_precision": 0.8119413657490168,
|
| 225 |
+
"eval_recall": 0.9368811881188119,
|
| 226 |
+
"eval_runtime": 22.8014,
|
| 227 |
+
"eval_samples_per_second": 206.215,
|
| 228 |
+
"eval_steps_per_second": 4.298,
|
| 229 |
+
"step": 2226
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 3.0997304582210243,
|
| 233 |
+
"grad_norm": 21.149120330810547,
|
| 234 |
+
"learning_rate": 7.601078167115904e-06,
|
| 235 |
+
"loss": 0.1726,
|
| 236 |
+
"step": 2300
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 3.234501347708895,
|
| 240 |
+
"grad_norm": 6.035734176635742,
|
| 241 |
+
"learning_rate": 7.061994609164421e-06,
|
| 242 |
+
"loss": 0.1614,
|
| 243 |
+
"step": 2400
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 3.3692722371967654,
|
| 247 |
+
"grad_norm": 9.38839340209961,
|
| 248 |
+
"learning_rate": 6.522911051212939e-06,
|
| 249 |
+
"loss": 0.1648,
|
| 250 |
+
"step": 2500
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 3.5040431266846364,
|
| 254 |
+
"grad_norm": 7.1731486320495605,
|
| 255 |
+
"learning_rate": 5.983827493261456e-06,
|
| 256 |
+
"loss": 0.1678,
|
| 257 |
+
"step": 2600
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"epoch": 3.638814016172507,
|
| 261 |
+
"grad_norm": 29.55657958984375,
|
| 262 |
+
"learning_rate": 5.444743935309974e-06,
|
| 263 |
+
"loss": 0.1492,
|
| 264 |
+
"step": 2700
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 3.7735849056603774,
|
| 268 |
+
"grad_norm": 15.47530746459961,
|
| 269 |
+
"learning_rate": 4.905660377358491e-06,
|
| 270 |
+
"loss": 0.1707,
|
| 271 |
+
"step": 2800
|
| 272 |
+
},
|
| 273 |
+
{
|
| 274 |
+
"epoch": 3.908355795148248,
|
| 275 |
+
"grad_norm": 8.083237648010254,
|
| 276 |
+
"learning_rate": 4.366576819407008e-06,
|
| 277 |
+
"loss": 0.1727,
|
| 278 |
+
"step": 2900
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 4.0,
|
| 282 |
+
"eval_accuracy": 0.8572947681837516,
|
| 283 |
+
"eval_confusion_matrix": [
|
| 284 |
+
[
|
| 285 |
+
1753,
|
| 286 |
+
525
|
| 287 |
+
],
|
| 288 |
+
[
|
| 289 |
+
146,
|
| 290 |
+
2278
|
| 291 |
+
]
|
| 292 |
+
],
|
| 293 |
+
"eval_f1": 0.8716280849435623,
|
| 294 |
+
"eval_loss": 0.5570098161697388,
|
| 295 |
+
"eval_precision": 0.8127006778451659,
|
| 296 |
+
"eval_recall": 0.9397689768976898,
|
| 297 |
+
"eval_runtime": 22.7535,
|
| 298 |
+
"eval_samples_per_second": 206.649,
|
| 299 |
+
"eval_steps_per_second": 4.307,
|
| 300 |
+
"step": 2968
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 4.0431266846361185,
|
| 304 |
+
"grad_norm": 8.28526782989502,
|
| 305 |
+
"learning_rate": 3.827493261455526e-06,
|
| 306 |
+
"loss": 0.155,
|
| 307 |
+
"step": 3000
|
| 308 |
+
},
|
| 309 |
+
{
|
| 310 |
+
"epoch": 4.177897574123989,
|
| 311 |
+
"grad_norm": 8.550823211669922,
|
| 312 |
+
"learning_rate": 3.2884097035040433e-06,
|
| 313 |
+
"loss": 0.1385,
|
| 314 |
+
"step": 3100
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 4.3126684636118595,
|
| 318 |
+
"grad_norm": 7.248845100402832,
|
| 319 |
+
"learning_rate": 2.749326145552561e-06,
|
| 320 |
+
"loss": 0.1245,
|
| 321 |
+
"step": 3200
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 4.44743935309973,
|
| 325 |
+
"grad_norm": 4.223452091217041,
|
| 326 |
+
"learning_rate": 2.2102425876010783e-06,
|
| 327 |
+
"loss": 0.1316,
|
| 328 |
+
"step": 3300
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 4.5822102425876015,
|
| 332 |
+
"grad_norm": 26.39322853088379,
|
| 333 |
+
"learning_rate": 1.6711590296495958e-06,
|
| 334 |
+
"loss": 0.1347,
|
| 335 |
+
"step": 3400
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 4.716981132075472,
|
| 339 |
+
"grad_norm": 9.451475143432617,
|
| 340 |
+
"learning_rate": 1.1320754716981133e-06,
|
| 341 |
+
"loss": 0.1373,
|
| 342 |
+
"step": 3500
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 4.8517520215633425,
|
| 346 |
+
"grad_norm": 7.989397048950195,
|
| 347 |
+
"learning_rate": 5.929919137466308e-07,
|
| 348 |
+
"loss": 0.127,
|
| 349 |
+
"step": 3600
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 4.986522911051213,
|
| 353 |
+
"grad_norm": 8.661871910095215,
|
| 354 |
+
"learning_rate": 5.3908355795148254e-08,
|
| 355 |
+
"loss": 0.1288,
|
| 356 |
+
"step": 3700
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 5.0,
|
| 360 |
+
"eval_accuracy": 0.8538919608677159,
|
| 361 |
+
"eval_confusion_matrix": [
|
| 362 |
+
[
|
| 363 |
+
1721,
|
| 364 |
+
557
|
| 365 |
+
],
|
| 366 |
+
[
|
| 367 |
+
130,
|
| 368 |
+
2294
|
| 369 |
+
]
|
| 370 |
+
],
|
| 371 |
+
"eval_f1": 0.8697630331753554,
|
| 372 |
+
"eval_loss": 0.6569812893867493,
|
| 373 |
+
"eval_precision": 0.8046299544019643,
|
| 374 |
+
"eval_recall": 0.9463696369636964,
|
| 375 |
+
"eval_runtime": 22.4622,
|
| 376 |
+
"eval_samples_per_second": 209.329,
|
| 377 |
+
"eval_steps_per_second": 4.363,
|
| 378 |
+
"step": 3710
|
| 379 |
+
}
|
| 380 |
+
],
|
| 381 |
+
"logging_steps": 100,
|
| 382 |
+
"max_steps": 3710,
|
| 383 |
+
"num_input_tokens_seen": 0,
|
| 384 |
+
"num_train_epochs": 5,
|
| 385 |
+
"save_steps": 500,
|
| 386 |
+
"stateful_callbacks": {
|
| 387 |
+
"TrainerControl": {
|
| 388 |
+
"args": {
|
| 389 |
+
"should_epoch_stop": false,
|
| 390 |
+
"should_evaluate": false,
|
| 391 |
+
"should_log": false,
|
| 392 |
+
"should_save": true,
|
| 393 |
+
"should_training_stop": true
|
| 394 |
+
},
|
| 395 |
+
"attributes": {}
|
| 396 |
+
}
|
| 397 |
+
},
|
| 398 |
+
"total_flos": 2.8848225720991744e+16,
|
| 399 |
+
"train_batch_size": 16,
|
| 400 |
+
"trial_name": null,
|
| 401 |
+
"trial_params": null
|
| 402 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b253821b0f0973394e6517ba7469ff3a686ac6e61c1f5c97ed1946d34a95e34c
|
| 3 |
+
size 5304
|