Upload model from Colab
Browse files- checkpoints/checkpoint-486/config.json +40 -0
- checkpoints/checkpoint-486/model.safetensors +3 -0
- checkpoints/checkpoint-486/optimizer.pt +3 -0
- checkpoints/checkpoint-486/rng_state.pth +3 -0
- checkpoints/checkpoint-486/scheduler.pt +3 -0
- checkpoints/checkpoint-486/trainer_state.json +450 -0
- checkpoints/checkpoint-486/training_args.bin +3 -0
- checkpoints/checkpoint-540/config.json +40 -0
- checkpoints/checkpoint-540/model.safetensors +3 -0
- checkpoints/checkpoint-540/optimizer.pt +3 -0
- checkpoints/checkpoint-540/rng_state.pth +3 -0
- checkpoints/checkpoint-540/scheduler.pt +3 -0
- checkpoints/checkpoint-540/trainer_state.json +500 -0
- checkpoints/checkpoint-540/training_args.bin +3 -0
- config.json +40 -0
- figures/confusion_matrix.png +0 -0
- figures/test_confusion_matrix.png +0 -0
- label_mapping.json +1 -0
- logs/events.out.tfevents.1745145387.bc305b05a4f3.295.0 +3 -0
- logs/events.out.tfevents.1745145409.bc305b05a4f3.295.1 +3 -0
- logs/events.out.tfevents.1745146535.bc305b05a4f3.295.2 +3 -0
- logs/events.out.tfevents.1745146542.bc305b05a4f3.295.3 +3 -0
- logs/events.out.tfevents.1745147411.bc305b05a4f3.295.4 +3 -0
- logs/events.out.tfevents.1745147418.bc305b05a4f3.295.5 +3 -0
- logs/events.out.tfevents.1745148318.bc305b05a4f3.295.6 +3 -0
- logs/events.out.tfevents.1745148325.bc305b05a4f3.295.7 +3 -0
- logs/events.out.tfevents.1745149227.bc305b05a4f3.295.8 +3 -0
- logs/events.out.tfevents.1745149234.bc305b05a4f3.295.9 +3 -0
- logs/events.out.tfevents.1745150147.bc305b05a4f3.295.10 +3 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- special_tokens_map.json +15 -0
- tokenizer.json +0 -0
- tokenizer_config.json +58 -0
- training_results.json +18 -0
- vocab.json +0 -0
checkpoints/checkpoint-486/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": "Change",
|
| 15 |
+
"1": "Incident",
|
| 16 |
+
"2": "Problem",
|
| 17 |
+
"3": "Request"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Change": 0,
|
| 23 |
+
"Incident": 1,
|
| 24 |
+
"Problem": 2,
|
| 25 |
+
"Request": 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": "4.49.0",
|
| 37 |
+
"type_vocab_size": 1,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 50265
|
| 40 |
+
}
|
checkpoints/checkpoint-486/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a387d7f037109d8a6c96ad2684fd30a831ada62059f1befde68359e308f798f3
|
| 3 |
+
size 498618976
|
checkpoints/checkpoint-486/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:88e0b51e183e05907a2b1a4bb8d6a062cbb1591b88366517a68d3578295d3357
|
| 3 |
+
size 997357818
|
checkpoints/checkpoint-486/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dad6a2f20b67d39c3125c0c9c38a29f9cc3ed00ed548c39578373a123e1918f0
|
| 3 |
+
size 14244
|
checkpoints/checkpoint-486/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3fd6092bd5bc983ae99c649df79fb638d9ae5be88e078f8c6f4671d348e7ea1
|
| 3 |
+
size 1064
|
checkpoints/checkpoint-486/trainer_state.json
ADDED
|
@@ -0,0 +1,450 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.00033540153526701033,
|
| 3 |
+
"best_model_checkpoint": "./high_accuracy_model/checkpoints/checkpoint-486",
|
| 4 |
+
"epoch": 9.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 486,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.18518518518518517,
|
| 13 |
+
"grad_norm": 1.84208345413208,
|
| 14 |
+
"learning_rate": 5.555555555555555e-06,
|
| 15 |
+
"loss": 1.3842,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.37037037037037035,
|
| 20 |
+
"grad_norm": 1.194960594177246,
|
| 21 |
+
"learning_rate": 1.111111111111111e-05,
|
| 22 |
+
"loss": 1.3909,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.5555555555555556,
|
| 27 |
+
"grad_norm": 2.837631940841675,
|
| 28 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 29 |
+
"loss": 1.3735,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.7407407407407407,
|
| 34 |
+
"grad_norm": 6.684326171875,
|
| 35 |
+
"learning_rate": 2.222222222222222e-05,
|
| 36 |
+
"loss": 1.2219,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.9259259259259259,
|
| 41 |
+
"grad_norm": 8.828328132629395,
|
| 42 |
+
"learning_rate": 2.777777777777778e-05,
|
| 43 |
+
"loss": 0.607,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_loss": 0.14139007031917572,
|
| 49 |
+
"eval_runtime": 5.3313,
|
| 50 |
+
"eval_samples_per_second": 81.031,
|
| 51 |
+
"eval_steps_per_second": 2.626,
|
| 52 |
+
"step": 54
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.1111111111111112,
|
| 56 |
+
"grad_norm": 5.395774841308594,
|
| 57 |
+
"learning_rate": 2.962962962962963e-05,
|
| 58 |
+
"loss": 0.1888,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.2962962962962963,
|
| 63 |
+
"grad_norm": 0.4055171012878418,
|
| 64 |
+
"learning_rate": 2.9012345679012347e-05,
|
| 65 |
+
"loss": 0.0843,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.4814814814814814,
|
| 70 |
+
"grad_norm": 0.1396542340517044,
|
| 71 |
+
"learning_rate": 2.839506172839506e-05,
|
| 72 |
+
"loss": 0.0149,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.6666666666666665,
|
| 77 |
+
"grad_norm": 0.10366827249526978,
|
| 78 |
+
"learning_rate": 2.777777777777778e-05,
|
| 79 |
+
"loss": 0.0149,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.8518518518518519,
|
| 84 |
+
"grad_norm": 0.04384304955601692,
|
| 85 |
+
"learning_rate": 2.7160493827160493e-05,
|
| 86 |
+
"loss": 0.0068,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.0,
|
| 91 |
+
"eval_loss": 0.0060031237080693245,
|
| 92 |
+
"eval_runtime": 5.3271,
|
| 93 |
+
"eval_samples_per_second": 81.094,
|
| 94 |
+
"eval_steps_per_second": 2.628,
|
| 95 |
+
"step": 108
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.037037037037037,
|
| 99 |
+
"grad_norm": 58.33610916137695,
|
| 100 |
+
"learning_rate": 2.654320987654321e-05,
|
| 101 |
+
"loss": 0.0282,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.2222222222222223,
|
| 106 |
+
"grad_norm": 0.025968477129936218,
|
| 107 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 108 |
+
"loss": 0.0028,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.4074074074074074,
|
| 113 |
+
"grad_norm": 0.02779112197458744,
|
| 114 |
+
"learning_rate": 2.5308641975308642e-05,
|
| 115 |
+
"loss": 0.0023,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.5925925925925926,
|
| 120 |
+
"grad_norm": 0.02369321882724762,
|
| 121 |
+
"learning_rate": 2.469135802469136e-05,
|
| 122 |
+
"loss": 0.0021,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.7777777777777777,
|
| 127 |
+
"grad_norm": 0.019034041091799736,
|
| 128 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 129 |
+
"loss": 0.0018,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.962962962962963,
|
| 134 |
+
"grad_norm": 0.017112266272306442,
|
| 135 |
+
"learning_rate": 2.345679012345679e-05,
|
| 136 |
+
"loss": 0.0016,
|
| 137 |
+
"step": 160
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 3.0,
|
| 141 |
+
"eval_loss": 0.0009095199056901038,
|
| 142 |
+
"eval_runtime": 5.3498,
|
| 143 |
+
"eval_samples_per_second": 80.75,
|
| 144 |
+
"eval_steps_per_second": 2.617,
|
| 145 |
+
"step": 162
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 3.148148148148148,
|
| 149 |
+
"grad_norm": 0.0168638713657856,
|
| 150 |
+
"learning_rate": 2.2839506172839506e-05,
|
| 151 |
+
"loss": 0.0015,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.3333333333333335,
|
| 156 |
+
"grad_norm": 0.01457894779741764,
|
| 157 |
+
"learning_rate": 2.222222222222222e-05,
|
| 158 |
+
"loss": 0.0014,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.5185185185185186,
|
| 163 |
+
"grad_norm": 0.015107030980288982,
|
| 164 |
+
"learning_rate": 2.160493827160494e-05,
|
| 165 |
+
"loss": 0.0013,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 3.7037037037037037,
|
| 170 |
+
"grad_norm": 0.014471936039626598,
|
| 171 |
+
"learning_rate": 2.0987654320987655e-05,
|
| 172 |
+
"loss": 0.0012,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.888888888888889,
|
| 177 |
+
"grad_norm": 0.015352337621152401,
|
| 178 |
+
"learning_rate": 2.0370370370370372e-05,
|
| 179 |
+
"loss": 0.0011,
|
| 180 |
+
"step": 210
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 4.0,
|
| 184 |
+
"eval_loss": 0.000643909617792815,
|
| 185 |
+
"eval_runtime": 5.3279,
|
| 186 |
+
"eval_samples_per_second": 81.082,
|
| 187 |
+
"eval_steps_per_second": 2.628,
|
| 188 |
+
"step": 216
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.074074074074074,
|
| 192 |
+
"grad_norm": 0.012968766503036022,
|
| 193 |
+
"learning_rate": 1.9753086419753087e-05,
|
| 194 |
+
"loss": 0.0011,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.2592592592592595,
|
| 199 |
+
"grad_norm": 0.010898980312049389,
|
| 200 |
+
"learning_rate": 1.9135802469135804e-05,
|
| 201 |
+
"loss": 0.0011,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 4.444444444444445,
|
| 206 |
+
"grad_norm": 0.010916095227003098,
|
| 207 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 208 |
+
"loss": 0.001,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.62962962962963,
|
| 213 |
+
"grad_norm": 0.0120779974386096,
|
| 214 |
+
"learning_rate": 1.7901234567901232e-05,
|
| 215 |
+
"loss": 0.001,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 4.814814814814815,
|
| 220 |
+
"grad_norm": 0.010523187927901745,
|
| 221 |
+
"learning_rate": 1.7283950617283953e-05,
|
| 222 |
+
"loss": 0.0009,
|
| 223 |
+
"step": 260
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 5.0,
|
| 227 |
+
"grad_norm": 0.011234262958168983,
|
| 228 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 229 |
+
"loss": 0.0009,
|
| 230 |
+
"step": 270
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.0,
|
| 234 |
+
"eval_loss": 0.0005087139434181154,
|
| 235 |
+
"eval_runtime": 5.2996,
|
| 236 |
+
"eval_samples_per_second": 81.516,
|
| 237 |
+
"eval_steps_per_second": 2.642,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 5.185185185185185,
|
| 242 |
+
"grad_norm": 0.009681645780801773,
|
| 243 |
+
"learning_rate": 1.6049382716049385e-05,
|
| 244 |
+
"loss": 0.0009,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 5.37037037037037,
|
| 249 |
+
"grad_norm": 0.009395086206495762,
|
| 250 |
+
"learning_rate": 1.54320987654321e-05,
|
| 251 |
+
"loss": 0.0008,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.555555555555555,
|
| 256 |
+
"grad_norm": 0.009616800583899021,
|
| 257 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 258 |
+
"loss": 0.0008,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 5.7407407407407405,
|
| 263 |
+
"grad_norm": 0.008898408152163029,
|
| 264 |
+
"learning_rate": 1.419753086419753e-05,
|
| 265 |
+
"loss": 0.0008,
|
| 266 |
+
"step": 310
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.925925925925926,
|
| 270 |
+
"grad_norm": 0.008080519735813141,
|
| 271 |
+
"learning_rate": 1.3580246913580247e-05,
|
| 272 |
+
"loss": 0.0007,
|
| 273 |
+
"step": 320
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 6.0,
|
| 277 |
+
"eval_loss": 0.00043077277950942516,
|
| 278 |
+
"eval_runtime": 5.3388,
|
| 279 |
+
"eval_samples_per_second": 80.917,
|
| 280 |
+
"eval_steps_per_second": 2.622,
|
| 281 |
+
"step": 324
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 6.111111111111111,
|
| 285 |
+
"grad_norm": 0.008911211043596268,
|
| 286 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 287 |
+
"loss": 0.0007,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 6.296296296296296,
|
| 292 |
+
"grad_norm": 0.00797555223107338,
|
| 293 |
+
"learning_rate": 1.234567901234568e-05,
|
| 294 |
+
"loss": 0.0007,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 6.481481481481482,
|
| 299 |
+
"grad_norm": 0.0076234182342886925,
|
| 300 |
+
"learning_rate": 1.1728395061728396e-05,
|
| 301 |
+
"loss": 0.0007,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.666666666666667,
|
| 306 |
+
"grad_norm": 0.007601814344525337,
|
| 307 |
+
"learning_rate": 1.111111111111111e-05,
|
| 308 |
+
"loss": 0.0007,
|
| 309 |
+
"step": 360
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.851851851851852,
|
| 313 |
+
"grad_norm": 0.007262354716658592,
|
| 314 |
+
"learning_rate": 1.0493827160493827e-05,
|
| 315 |
+
"loss": 0.0006,
|
| 316 |
+
"step": 370
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 7.0,
|
| 320 |
+
"eval_loss": 0.0003821477002929896,
|
| 321 |
+
"eval_runtime": 5.3454,
|
| 322 |
+
"eval_samples_per_second": 80.817,
|
| 323 |
+
"eval_steps_per_second": 2.619,
|
| 324 |
+
"step": 378
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.037037037037037,
|
| 328 |
+
"grad_norm": 0.007605003193020821,
|
| 329 |
+
"learning_rate": 9.876543209876543e-06,
|
| 330 |
+
"loss": 0.0006,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 7.222222222222222,
|
| 335 |
+
"grad_norm": 0.007823699153959751,
|
| 336 |
+
"learning_rate": 9.259259259259259e-06,
|
| 337 |
+
"loss": 0.0006,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.407407407407407,
|
| 342 |
+
"grad_norm": 0.006984628736972809,
|
| 343 |
+
"learning_rate": 8.641975308641977e-06,
|
| 344 |
+
"loss": 0.0006,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.592592592592593,
|
| 349 |
+
"grad_norm": 0.0069269961677491665,
|
| 350 |
+
"learning_rate": 8.024691358024692e-06,
|
| 351 |
+
"loss": 0.0006,
|
| 352 |
+
"step": 410
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.777777777777778,
|
| 356 |
+
"grad_norm": 0.00705177616328001,
|
| 357 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 358 |
+
"loss": 0.0006,
|
| 359 |
+
"step": 420
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.962962962962963,
|
| 363 |
+
"grad_norm": 0.006812036037445068,
|
| 364 |
+
"learning_rate": 6.790123456790123e-06,
|
| 365 |
+
"loss": 0.0006,
|
| 366 |
+
"step": 430
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 8.0,
|
| 370 |
+
"eval_loss": 0.00035223510349169374,
|
| 371 |
+
"eval_runtime": 5.3231,
|
| 372 |
+
"eval_samples_per_second": 81.156,
|
| 373 |
+
"eval_steps_per_second": 2.63,
|
| 374 |
+
"step": 432
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 8.148148148148149,
|
| 378 |
+
"grad_norm": 0.01267582643777132,
|
| 379 |
+
"learning_rate": 6.17283950617284e-06,
|
| 380 |
+
"loss": 0.0006,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 8.333333333333334,
|
| 385 |
+
"grad_norm": 0.0074326274916529655,
|
| 386 |
+
"learning_rate": 5.555555555555555e-06,
|
| 387 |
+
"loss": 0.0006,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 8.518518518518519,
|
| 392 |
+
"grad_norm": 0.006270403973758221,
|
| 393 |
+
"learning_rate": 4.938271604938272e-06,
|
| 394 |
+
"loss": 0.0006,
|
| 395 |
+
"step": 460
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 8.703703703703704,
|
| 399 |
+
"grad_norm": 0.006308271083980799,
|
| 400 |
+
"learning_rate": 4.320987654320988e-06,
|
| 401 |
+
"loss": 0.0006,
|
| 402 |
+
"step": 470
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 8.88888888888889,
|
| 406 |
+
"grad_norm": 0.006707304157316685,
|
| 407 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 408 |
+
"loss": 0.0006,
|
| 409 |
+
"step": 480
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 9.0,
|
| 413 |
+
"eval_loss": 0.00033540153526701033,
|
| 414 |
+
"eval_runtime": 5.3591,
|
| 415 |
+
"eval_samples_per_second": 80.611,
|
| 416 |
+
"eval_steps_per_second": 2.612,
|
| 417 |
+
"step": 486
|
| 418 |
+
}
|
| 419 |
+
],
|
| 420 |
+
"logging_steps": 10,
|
| 421 |
+
"max_steps": 540,
|
| 422 |
+
"num_input_tokens_seen": 0,
|
| 423 |
+
"num_train_epochs": 10,
|
| 424 |
+
"save_steps": 500,
|
| 425 |
+
"stateful_callbacks": {
|
| 426 |
+
"EarlyStoppingCallback": {
|
| 427 |
+
"args": {
|
| 428 |
+
"early_stopping_patience": 3,
|
| 429 |
+
"early_stopping_threshold": 0.0
|
| 430 |
+
},
|
| 431 |
+
"attributes": {
|
| 432 |
+
"early_stopping_patience_counter": 0
|
| 433 |
+
}
|
| 434 |
+
},
|
| 435 |
+
"TrainerControl": {
|
| 436 |
+
"args": {
|
| 437 |
+
"should_epoch_stop": false,
|
| 438 |
+
"should_evaluate": false,
|
| 439 |
+
"should_log": false,
|
| 440 |
+
"should_save": true,
|
| 441 |
+
"should_training_stop": false
|
| 442 |
+
},
|
| 443 |
+
"attributes": {}
|
| 444 |
+
}
|
| 445 |
+
},
|
| 446 |
+
"total_flos": 2045988306026496.0,
|
| 447 |
+
"train_batch_size": 32,
|
| 448 |
+
"trial_name": null,
|
| 449 |
+
"trial_params": null
|
| 450 |
+
}
|
checkpoints/checkpoint-486/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3c350a25f8a44897bcf6ffd215af0db661426eb2919e743b6277779709685d1
|
| 3 |
+
size 5368
|
checkpoints/checkpoint-540/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": "Change",
|
| 15 |
+
"1": "Incident",
|
| 16 |
+
"2": "Problem",
|
| 17 |
+
"3": "Request"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Change": 0,
|
| 23 |
+
"Incident": 1,
|
| 24 |
+
"Problem": 2,
|
| 25 |
+
"Request": 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": "4.49.0",
|
| 37 |
+
"type_vocab_size": 1,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 50265
|
| 40 |
+
}
|
checkpoints/checkpoint-540/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c072bf9ad7c1452fb7bdaa8f05662332fa4bb22de10a33d3d07c270e967d86b8
|
| 3 |
+
size 498618976
|
checkpoints/checkpoint-540/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f7f3d9004d32886678f3d8f96d0a6211cfb8f86d4f1f51d4ffd3e9add1f0e35
|
| 3 |
+
size 997357818
|
checkpoints/checkpoint-540/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43e2436386da9ccb9bb9025deda5591302f3d2fbc0df8411db63f806536b9ea2
|
| 3 |
+
size 14244
|
checkpoints/checkpoint-540/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ad48e9d65b2d9c9b96d2e5633a4abc1fd86d36f82f5afa6ed3089a33d0bad26
|
| 3 |
+
size 1064
|
checkpoints/checkpoint-540/trainer_state.json
ADDED
|
@@ -0,0 +1,500 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.00032986211590468884,
|
| 3 |
+
"best_model_checkpoint": "./high_accuracy_model/checkpoints/checkpoint-540",
|
| 4 |
+
"epoch": 10.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 540,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.18518518518518517,
|
| 13 |
+
"grad_norm": 1.84208345413208,
|
| 14 |
+
"learning_rate": 5.555555555555555e-06,
|
| 15 |
+
"loss": 1.3842,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.37037037037037035,
|
| 20 |
+
"grad_norm": 1.194960594177246,
|
| 21 |
+
"learning_rate": 1.111111111111111e-05,
|
| 22 |
+
"loss": 1.3909,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.5555555555555556,
|
| 27 |
+
"grad_norm": 2.837631940841675,
|
| 28 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 29 |
+
"loss": 1.3735,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.7407407407407407,
|
| 34 |
+
"grad_norm": 6.684326171875,
|
| 35 |
+
"learning_rate": 2.222222222222222e-05,
|
| 36 |
+
"loss": 1.2219,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.9259259259259259,
|
| 41 |
+
"grad_norm": 8.828328132629395,
|
| 42 |
+
"learning_rate": 2.777777777777778e-05,
|
| 43 |
+
"loss": 0.607,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 1.0,
|
| 48 |
+
"eval_loss": 0.14139007031917572,
|
| 49 |
+
"eval_runtime": 5.3313,
|
| 50 |
+
"eval_samples_per_second": 81.031,
|
| 51 |
+
"eval_steps_per_second": 2.626,
|
| 52 |
+
"step": 54
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 1.1111111111111112,
|
| 56 |
+
"grad_norm": 5.395774841308594,
|
| 57 |
+
"learning_rate": 2.962962962962963e-05,
|
| 58 |
+
"loss": 0.1888,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 1.2962962962962963,
|
| 63 |
+
"grad_norm": 0.4055171012878418,
|
| 64 |
+
"learning_rate": 2.9012345679012347e-05,
|
| 65 |
+
"loss": 0.0843,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 1.4814814814814814,
|
| 70 |
+
"grad_norm": 0.1396542340517044,
|
| 71 |
+
"learning_rate": 2.839506172839506e-05,
|
| 72 |
+
"loss": 0.0149,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 1.6666666666666665,
|
| 77 |
+
"grad_norm": 0.10366827249526978,
|
| 78 |
+
"learning_rate": 2.777777777777778e-05,
|
| 79 |
+
"loss": 0.0149,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 1.8518518518518519,
|
| 84 |
+
"grad_norm": 0.04384304955601692,
|
| 85 |
+
"learning_rate": 2.7160493827160493e-05,
|
| 86 |
+
"loss": 0.0068,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.0,
|
| 91 |
+
"eval_loss": 0.0060031237080693245,
|
| 92 |
+
"eval_runtime": 5.3271,
|
| 93 |
+
"eval_samples_per_second": 81.094,
|
| 94 |
+
"eval_steps_per_second": 2.628,
|
| 95 |
+
"step": 108
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 2.037037037037037,
|
| 99 |
+
"grad_norm": 58.33610916137695,
|
| 100 |
+
"learning_rate": 2.654320987654321e-05,
|
| 101 |
+
"loss": 0.0282,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 2.2222222222222223,
|
| 106 |
+
"grad_norm": 0.025968477129936218,
|
| 107 |
+
"learning_rate": 2.5925925925925925e-05,
|
| 108 |
+
"loss": 0.0028,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 2.4074074074074074,
|
| 113 |
+
"grad_norm": 0.02779112197458744,
|
| 114 |
+
"learning_rate": 2.5308641975308642e-05,
|
| 115 |
+
"loss": 0.0023,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 2.5925925925925926,
|
| 120 |
+
"grad_norm": 0.02369321882724762,
|
| 121 |
+
"learning_rate": 2.469135802469136e-05,
|
| 122 |
+
"loss": 0.0021,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 2.7777777777777777,
|
| 127 |
+
"grad_norm": 0.019034041091799736,
|
| 128 |
+
"learning_rate": 2.4074074074074074e-05,
|
| 129 |
+
"loss": 0.0018,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 2.962962962962963,
|
| 134 |
+
"grad_norm": 0.017112266272306442,
|
| 135 |
+
"learning_rate": 2.345679012345679e-05,
|
| 136 |
+
"loss": 0.0016,
|
| 137 |
+
"step": 160
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 3.0,
|
| 141 |
+
"eval_loss": 0.0009095199056901038,
|
| 142 |
+
"eval_runtime": 5.3498,
|
| 143 |
+
"eval_samples_per_second": 80.75,
|
| 144 |
+
"eval_steps_per_second": 2.617,
|
| 145 |
+
"step": 162
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 3.148148148148148,
|
| 149 |
+
"grad_norm": 0.0168638713657856,
|
| 150 |
+
"learning_rate": 2.2839506172839506e-05,
|
| 151 |
+
"loss": 0.0015,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 3.3333333333333335,
|
| 156 |
+
"grad_norm": 0.01457894779741764,
|
| 157 |
+
"learning_rate": 2.222222222222222e-05,
|
| 158 |
+
"loss": 0.0014,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.5185185185185186,
|
| 163 |
+
"grad_norm": 0.015107030980288982,
|
| 164 |
+
"learning_rate": 2.160493827160494e-05,
|
| 165 |
+
"loss": 0.0013,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 3.7037037037037037,
|
| 170 |
+
"grad_norm": 0.014471936039626598,
|
| 171 |
+
"learning_rate": 2.0987654320987655e-05,
|
| 172 |
+
"loss": 0.0012,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.888888888888889,
|
| 177 |
+
"grad_norm": 0.015352337621152401,
|
| 178 |
+
"learning_rate": 2.0370370370370372e-05,
|
| 179 |
+
"loss": 0.0011,
|
| 180 |
+
"step": 210
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 4.0,
|
| 184 |
+
"eval_loss": 0.000643909617792815,
|
| 185 |
+
"eval_runtime": 5.3279,
|
| 186 |
+
"eval_samples_per_second": 81.082,
|
| 187 |
+
"eval_steps_per_second": 2.628,
|
| 188 |
+
"step": 216
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 4.074074074074074,
|
| 192 |
+
"grad_norm": 0.012968766503036022,
|
| 193 |
+
"learning_rate": 1.9753086419753087e-05,
|
| 194 |
+
"loss": 0.0011,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 4.2592592592592595,
|
| 199 |
+
"grad_norm": 0.010898980312049389,
|
| 200 |
+
"learning_rate": 1.9135802469135804e-05,
|
| 201 |
+
"loss": 0.0011,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 4.444444444444445,
|
| 206 |
+
"grad_norm": 0.010916095227003098,
|
| 207 |
+
"learning_rate": 1.8518518518518518e-05,
|
| 208 |
+
"loss": 0.001,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 4.62962962962963,
|
| 213 |
+
"grad_norm": 0.0120779974386096,
|
| 214 |
+
"learning_rate": 1.7901234567901232e-05,
|
| 215 |
+
"loss": 0.001,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 4.814814814814815,
|
| 220 |
+
"grad_norm": 0.010523187927901745,
|
| 221 |
+
"learning_rate": 1.7283950617283953e-05,
|
| 222 |
+
"loss": 0.0009,
|
| 223 |
+
"step": 260
|
| 224 |
+
},
|
| 225 |
+
{
|
| 226 |
+
"epoch": 5.0,
|
| 227 |
+
"grad_norm": 0.011234262958168983,
|
| 228 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 229 |
+
"loss": 0.0009,
|
| 230 |
+
"step": 270
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 5.0,
|
| 234 |
+
"eval_loss": 0.0005087139434181154,
|
| 235 |
+
"eval_runtime": 5.2996,
|
| 236 |
+
"eval_samples_per_second": 81.516,
|
| 237 |
+
"eval_steps_per_second": 2.642,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 5.185185185185185,
|
| 242 |
+
"grad_norm": 0.009681645780801773,
|
| 243 |
+
"learning_rate": 1.6049382716049385e-05,
|
| 244 |
+
"loss": 0.0009,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 5.37037037037037,
|
| 249 |
+
"grad_norm": 0.009395086206495762,
|
| 250 |
+
"learning_rate": 1.54320987654321e-05,
|
| 251 |
+
"loss": 0.0008,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 5.555555555555555,
|
| 256 |
+
"grad_norm": 0.009616800583899021,
|
| 257 |
+
"learning_rate": 1.4814814814814815e-05,
|
| 258 |
+
"loss": 0.0008,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 5.7407407407407405,
|
| 263 |
+
"grad_norm": 0.008898408152163029,
|
| 264 |
+
"learning_rate": 1.419753086419753e-05,
|
| 265 |
+
"loss": 0.0008,
|
| 266 |
+
"step": 310
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 5.925925925925926,
|
| 270 |
+
"grad_norm": 0.008080519735813141,
|
| 271 |
+
"learning_rate": 1.3580246913580247e-05,
|
| 272 |
+
"loss": 0.0007,
|
| 273 |
+
"step": 320
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 6.0,
|
| 277 |
+
"eval_loss": 0.00043077277950942516,
|
| 278 |
+
"eval_runtime": 5.3388,
|
| 279 |
+
"eval_samples_per_second": 80.917,
|
| 280 |
+
"eval_steps_per_second": 2.622,
|
| 281 |
+
"step": 324
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 6.111111111111111,
|
| 285 |
+
"grad_norm": 0.008911211043596268,
|
| 286 |
+
"learning_rate": 1.2962962962962962e-05,
|
| 287 |
+
"loss": 0.0007,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 6.296296296296296,
|
| 292 |
+
"grad_norm": 0.00797555223107338,
|
| 293 |
+
"learning_rate": 1.234567901234568e-05,
|
| 294 |
+
"loss": 0.0007,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 6.481481481481482,
|
| 299 |
+
"grad_norm": 0.0076234182342886925,
|
| 300 |
+
"learning_rate": 1.1728395061728396e-05,
|
| 301 |
+
"loss": 0.0007,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 6.666666666666667,
|
| 306 |
+
"grad_norm": 0.007601814344525337,
|
| 307 |
+
"learning_rate": 1.111111111111111e-05,
|
| 308 |
+
"loss": 0.0007,
|
| 309 |
+
"step": 360
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 6.851851851851852,
|
| 313 |
+
"grad_norm": 0.007262354716658592,
|
| 314 |
+
"learning_rate": 1.0493827160493827e-05,
|
| 315 |
+
"loss": 0.0006,
|
| 316 |
+
"step": 370
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 7.0,
|
| 320 |
+
"eval_loss": 0.0003821477002929896,
|
| 321 |
+
"eval_runtime": 5.3454,
|
| 322 |
+
"eval_samples_per_second": 80.817,
|
| 323 |
+
"eval_steps_per_second": 2.619,
|
| 324 |
+
"step": 378
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.037037037037037,
|
| 328 |
+
"grad_norm": 0.007605003193020821,
|
| 329 |
+
"learning_rate": 9.876543209876543e-06,
|
| 330 |
+
"loss": 0.0006,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 7.222222222222222,
|
| 335 |
+
"grad_norm": 0.007823699153959751,
|
| 336 |
+
"learning_rate": 9.259259259259259e-06,
|
| 337 |
+
"loss": 0.0006,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 7.407407407407407,
|
| 342 |
+
"grad_norm": 0.006984628736972809,
|
| 343 |
+
"learning_rate": 8.641975308641977e-06,
|
| 344 |
+
"loss": 0.0006,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 7.592592592592593,
|
| 349 |
+
"grad_norm": 0.0069269961677491665,
|
| 350 |
+
"learning_rate": 8.024691358024692e-06,
|
| 351 |
+
"loss": 0.0006,
|
| 352 |
+
"step": 410
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 7.777777777777778,
|
| 356 |
+
"grad_norm": 0.00705177616328001,
|
| 357 |
+
"learning_rate": 7.4074074074074075e-06,
|
| 358 |
+
"loss": 0.0006,
|
| 359 |
+
"step": 420
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 7.962962962962963,
|
| 363 |
+
"grad_norm": 0.006812036037445068,
|
| 364 |
+
"learning_rate": 6.790123456790123e-06,
|
| 365 |
+
"loss": 0.0006,
|
| 366 |
+
"step": 430
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 8.0,
|
| 370 |
+
"eval_loss": 0.00035223510349169374,
|
| 371 |
+
"eval_runtime": 5.3231,
|
| 372 |
+
"eval_samples_per_second": 81.156,
|
| 373 |
+
"eval_steps_per_second": 2.63,
|
| 374 |
+
"step": 432
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 8.148148148148149,
|
| 378 |
+
"grad_norm": 0.01267582643777132,
|
| 379 |
+
"learning_rate": 6.17283950617284e-06,
|
| 380 |
+
"loss": 0.0006,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 8.333333333333334,
|
| 385 |
+
"grad_norm": 0.0074326274916529655,
|
| 386 |
+
"learning_rate": 5.555555555555555e-06,
|
| 387 |
+
"loss": 0.0006,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 8.518518518518519,
|
| 392 |
+
"grad_norm": 0.006270403973758221,
|
| 393 |
+
"learning_rate": 4.938271604938272e-06,
|
| 394 |
+
"loss": 0.0006,
|
| 395 |
+
"step": 460
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 8.703703703703704,
|
| 399 |
+
"grad_norm": 0.006308271083980799,
|
| 400 |
+
"learning_rate": 4.320987654320988e-06,
|
| 401 |
+
"loss": 0.0006,
|
| 402 |
+
"step": 470
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 8.88888888888889,
|
| 406 |
+
"grad_norm": 0.006707304157316685,
|
| 407 |
+
"learning_rate": 3.7037037037037037e-06,
|
| 408 |
+
"loss": 0.0006,
|
| 409 |
+
"step": 480
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 9.0,
|
| 413 |
+
"eval_loss": 0.00033540153526701033,
|
| 414 |
+
"eval_runtime": 5.3591,
|
| 415 |
+
"eval_samples_per_second": 80.611,
|
| 416 |
+
"eval_steps_per_second": 2.612,
|
| 417 |
+
"step": 486
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 9.074074074074074,
|
| 421 |
+
"grad_norm": 0.0068153077736496925,
|
| 422 |
+
"learning_rate": 3.08641975308642e-06,
|
| 423 |
+
"loss": 0.0006,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 9.25925925925926,
|
| 428 |
+
"grad_norm": 0.00644618459045887,
|
| 429 |
+
"learning_rate": 2.469135802469136e-06,
|
| 430 |
+
"loss": 0.0006,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 9.444444444444445,
|
| 435 |
+
"grad_norm": 0.006743066944181919,
|
| 436 |
+
"learning_rate": 1.8518518518518519e-06,
|
| 437 |
+
"loss": 0.0006,
|
| 438 |
+
"step": 510
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 9.62962962962963,
|
| 442 |
+
"grad_norm": 0.006693513132631779,
|
| 443 |
+
"learning_rate": 1.234567901234568e-06,
|
| 444 |
+
"loss": 0.0005,
|
| 445 |
+
"step": 520
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 9.814814814814815,
|
| 449 |
+
"grad_norm": 0.006694548763334751,
|
| 450 |
+
"learning_rate": 6.17283950617284e-07,
|
| 451 |
+
"loss": 0.0006,
|
| 452 |
+
"step": 530
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 10.0,
|
| 456 |
+
"grad_norm": 0.006117587443441153,
|
| 457 |
+
"learning_rate": 0.0,
|
| 458 |
+
"loss": 0.0005,
|
| 459 |
+
"step": 540
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.0,
|
| 463 |
+
"eval_loss": 0.00032986211590468884,
|
| 464 |
+
"eval_runtime": 5.3343,
|
| 465 |
+
"eval_samples_per_second": 80.986,
|
| 466 |
+
"eval_steps_per_second": 2.625,
|
| 467 |
+
"step": 540
|
| 468 |
+
}
|
| 469 |
+
],
|
| 470 |
+
"logging_steps": 10,
|
| 471 |
+
"max_steps": 540,
|
| 472 |
+
"num_input_tokens_seen": 0,
|
| 473 |
+
"num_train_epochs": 10,
|
| 474 |
+
"save_steps": 500,
|
| 475 |
+
"stateful_callbacks": {
|
| 476 |
+
"EarlyStoppingCallback": {
|
| 477 |
+
"args": {
|
| 478 |
+
"early_stopping_patience": 3,
|
| 479 |
+
"early_stopping_threshold": 0.0
|
| 480 |
+
},
|
| 481 |
+
"attributes": {
|
| 482 |
+
"early_stopping_patience_counter": 0
|
| 483 |
+
}
|
| 484 |
+
},
|
| 485 |
+
"TrainerControl": {
|
| 486 |
+
"args": {
|
| 487 |
+
"should_epoch_stop": false,
|
| 488 |
+
"should_evaluate": false,
|
| 489 |
+
"should_log": false,
|
| 490 |
+
"should_save": true,
|
| 491 |
+
"should_training_stop": true
|
| 492 |
+
},
|
| 493 |
+
"attributes": {}
|
| 494 |
+
}
|
| 495 |
+
},
|
| 496 |
+
"total_flos": 2273320340029440.0,
|
| 497 |
+
"train_batch_size": 32,
|
| 498 |
+
"trial_name": null,
|
| 499 |
+
"trial_params": null
|
| 500 |
+
}
|
checkpoints/checkpoint-540/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3c350a25f8a44897bcf6ffd215af0db661426eb2919e743b6277779709685d1
|
| 3 |
+
size 5368
|
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": "Change",
|
| 15 |
+
"1": "Incident",
|
| 16 |
+
"2": "Problem",
|
| 17 |
+
"3": "Request"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"Change": 0,
|
| 23 |
+
"Incident": 1,
|
| 24 |
+
"Problem": 2,
|
| 25 |
+
"Request": 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": "4.49.0",
|
| 37 |
+
"type_vocab_size": 1,
|
| 38 |
+
"use_cache": true,
|
| 39 |
+
"vocab_size": 50265
|
| 40 |
+
}
|
figures/confusion_matrix.png
ADDED
|
figures/test_confusion_matrix.png
ADDED
|
label_mapping.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"0": "Change", "1": "Incident", "2": "Problem", "3": "Request"}
|
logs/events.out.tfevents.1745145387.bc305b05a4f3.295.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20336eb0176d36224b3f4f1b03f1c454576760bf1535be21995bd3dbe972c7b0
|
| 3 |
+
size 5294
|
logs/events.out.tfevents.1745145409.bc305b05a4f3.295.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ede67db03bb91a540b54cb18f6ee4a5c3317798ca01dee80d07457b18f610e99
|
| 3 |
+
size 19694
|
logs/events.out.tfevents.1745146535.bc305b05a4f3.295.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aace489a1eeb42c76847350552b8aaa0ceb0a00b4cc9e22c753a2be148211abc
|
| 3 |
+
size 359
|
logs/events.out.tfevents.1745146542.bc305b05a4f3.295.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:659a65e7948f0cd53208fa5c07e81d904786f400e3a9f9baf645e72ac2373972
|
| 3 |
+
size 19694
|
logs/events.out.tfevents.1745147411.bc305b05a4f3.295.4
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c8b0db1ac5c28a69d73a61bfcdcfb78f0bd6d9c0d49a6089fbdcf5adbd07cba0
|
| 3 |
+
size 359
|
logs/events.out.tfevents.1745147418.bc305b05a4f3.295.5
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bed8088aa66380ebfbd49eb87e0fb08dc5ad4175d8d349a649ae6a997fad7c78
|
| 3 |
+
size 19694
|
logs/events.out.tfevents.1745148318.bc305b05a4f3.295.6
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b277825a17f4d5688347caf301afd98465a4ddc3a459452900c0a15a84db90f2
|
| 3 |
+
size 359
|
logs/events.out.tfevents.1745148325.bc305b05a4f3.295.7
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f7f14ff963a8f39283e118f469293c6bc4e9d6ba82e0ae9ac790d1799cd947e4
|
| 3 |
+
size 19694
|
logs/events.out.tfevents.1745149227.bc305b05a4f3.295.8
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:039fd7deca19af8f35427e6eeae591aa3407f7e31dfca34ecdc05b58542da798
|
| 3 |
+
size 359
|
logs/events.out.tfevents.1745149234.bc305b05a4f3.295.9
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3ae8baf98dc1d66f8cc9dc15cc212837e9190c477bf5e31c904861fa663ae88
|
| 3 |
+
size 19694
|
logs/events.out.tfevents.1745150147.bc305b05a4f3.295.10
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e54d882a9ea26580d3cead3014fb9f32c74cc0a5f94e6e798f565e830f82438
|
| 3 |
+
size 359
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9c83e2fb081e19257d15ff7ee94823bf13c4e110b0dca9fa08cc2babf987020
|
| 3 |
+
size 498618976
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": false,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"extra_special_tokens": {},
|
| 51 |
+
"mask_token": "<mask>",
|
| 52 |
+
"model_max_length": 512,
|
| 53 |
+
"pad_token": "<pad>",
|
| 54 |
+
"sep_token": "</s>",
|
| 55 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 56 |
+
"trim_offsets": true,
|
| 57 |
+
"unk_token": "<unk>"
|
| 58 |
+
}
|
training_results.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cv_accuracy": 1.0,
|
| 3 |
+
"best_fold_accuracy": 1.0,
|
| 4 |
+
"test_accuracy": 1.0,
|
| 5 |
+
"runtime_seconds": 4754.493698596954,
|
| 6 |
+
"config": {
|
| 7 |
+
"model_name": "roberta-base",
|
| 8 |
+
"epochs": 10,
|
| 9 |
+
"batch_size": 32,
|
| 10 |
+
"learning_rate": 3e-05,
|
| 11 |
+
"weight_decay": 0.01,
|
| 12 |
+
"max_length": 256,
|
| 13 |
+
"warmup_ratio": 0.1,
|
| 14 |
+
"k_folds": 5,
|
| 15 |
+
"patience": 3,
|
| 16 |
+
"save_path": "./high_accuracy_model"
|
| 17 |
+
}
|
| 18 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|