upload ipc_level1_C model
Browse files- config.json +75 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +339 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "../models/roberta-large/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"eos_token_id": 2,
|
| 9 |
+
"finetuning_task": "ipc1",
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "01",
|
| 16 |
+
"1": "02",
|
| 17 |
+
"2": "03",
|
| 18 |
+
"3": "04",
|
| 19 |
+
"4": "05",
|
| 20 |
+
"5": "06",
|
| 21 |
+
"6": "07",
|
| 22 |
+
"7": "08",
|
| 23 |
+
"8": "09",
|
| 24 |
+
"9": "10",
|
| 25 |
+
"10": "11",
|
| 26 |
+
"11": "12",
|
| 27 |
+
"12": "13",
|
| 28 |
+
"13": "14",
|
| 29 |
+
"14": "21",
|
| 30 |
+
"15": "22",
|
| 31 |
+
"16": "23",
|
| 32 |
+
"17": "25",
|
| 33 |
+
"18": "30",
|
| 34 |
+
"19": "40",
|
| 35 |
+
"20": "99"
|
| 36 |
+
},
|
| 37 |
+
"initializer_range": 0.02,
|
| 38 |
+
"intermediate_size": 4096,
|
| 39 |
+
"label2id": {
|
| 40 |
+
"01": 0,
|
| 41 |
+
"02": 1,
|
| 42 |
+
"03": 2,
|
| 43 |
+
"04": 3,
|
| 44 |
+
"05": 4,
|
| 45 |
+
"06": 5,
|
| 46 |
+
"07": 6,
|
| 47 |
+
"08": 7,
|
| 48 |
+
"09": 8,
|
| 49 |
+
"10": 9,
|
| 50 |
+
"11": 10,
|
| 51 |
+
"12": 11,
|
| 52 |
+
"13": 12,
|
| 53 |
+
"14": 13,
|
| 54 |
+
"21": 14,
|
| 55 |
+
"22": 15,
|
| 56 |
+
"23": 16,
|
| 57 |
+
"25": 17,
|
| 58 |
+
"30": 18,
|
| 59 |
+
"40": 19,
|
| 60 |
+
"99": 20
|
| 61 |
+
},
|
| 62 |
+
"layer_norm_eps": 1e-05,
|
| 63 |
+
"max_position_embeddings": 514,
|
| 64 |
+
"model_type": "roberta",
|
| 65 |
+
"num_attention_heads": 16,
|
| 66 |
+
"num_hidden_layers": 24,
|
| 67 |
+
"pad_token_id": 1,
|
| 68 |
+
"position_embedding_type": "absolute",
|
| 69 |
+
"problem_type": "multi_label_classification",
|
| 70 |
+
"torch_dtype": "float32",
|
| 71 |
+
"transformers_version": "4.9.2",
|
| 72 |
+
"type_vocab_size": 1,
|
| 73 |
+
"use_cache": true,
|
| 74 |
+
"vocab_size": 50265
|
| 75 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3eb0f3601af13bca7e3d72cae8ef25b775502b0155e89746e28ee95c940ef299
|
| 3 |
+
size 1421689197
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b7ca6830334bf18495fe6f0e4691cd2803d7aef8e7fded5e9158474c3d9f84ab
|
| 3 |
+
size 15523
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "../models/roberta-large/", "tokenizer_class": "RobertaTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,339 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8934987662530843,
|
| 3 |
+
"best_model_checkpoint": "./output//roberta-large_ipc1_C_5_32_5e-6_0.01_0.06_07-07-22_23-17/checkpoint-38000",
|
| 4 |
+
"epoch": 0.4979296608836941,
|
| 5 |
+
"global_step": 38000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.03,
|
| 12 |
+
"learning_rate": 4.3677658877484174e-07,
|
| 13 |
+
"loss": 0.3698,
|
| 14 |
+
"step": 2000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"eval_accuracy": 0.0003641602938615241,
|
| 19 |
+
"eval_f1": 0.0007814160080609232,
|
| 20 |
+
"eval_loss": 0.1831192523241043,
|
| 21 |
+
"eval_roc_auc": 0.5001946379048023,
|
| 22 |
+
"eval_runtime": 3712.996,
|
| 23 |
+
"eval_samples_per_second": 34.021,
|
| 24 |
+
"eval_steps_per_second": 2.126,
|
| 25 |
+
"step": 2000
|
| 26 |
+
},
|
| 27 |
+
{
|
| 28 |
+
"epoch": 0.05,
|
| 29 |
+
"learning_rate": 8.735531775496835e-07,
|
| 30 |
+
"loss": 0.1415,
|
| 31 |
+
"step": 4000
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.05,
|
| 35 |
+
"eval_accuracy": 0.6030652796909387,
|
| 36 |
+
"eval_f1": 0.7397382281617269,
|
| 37 |
+
"eval_loss": 0.09564058482646942,
|
| 38 |
+
"eval_roc_auc": 0.8112905369107336,
|
| 39 |
+
"eval_runtime": 3711.74,
|
| 40 |
+
"eval_samples_per_second": 34.032,
|
| 41 |
+
"eval_steps_per_second": 2.127,
|
| 42 |
+
"step": 4000
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.08,
|
| 46 |
+
"learning_rate": 1.3103297663245252e-06,
|
| 47 |
+
"loss": 0.0855,
|
| 48 |
+
"step": 6000
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.08,
|
| 52 |
+
"eval_accuracy": 0.7227869345619785,
|
| 53 |
+
"eval_f1": 0.8181041339128826,
|
| 54 |
+
"eval_loss": 0.06705362349748611,
|
| 55 |
+
"eval_roc_auc": 0.8763586156819746,
|
| 56 |
+
"eval_runtime": 3713.5565,
|
| 57 |
+
"eval_samples_per_second": 34.015,
|
| 58 |
+
"eval_steps_per_second": 2.126,
|
| 59 |
+
"step": 6000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.1,
|
| 63 |
+
"learning_rate": 1.747106355099367e-06,
|
| 64 |
+
"loss": 0.0643,
|
| 65 |
+
"step": 8000
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.1,
|
| 69 |
+
"eval_accuracy": 0.7567884228692665,
|
| 70 |
+
"eval_f1": 0.841935061915005,
|
| 71 |
+
"eval_loss": 0.05476009473204613,
|
| 72 |
+
"eval_roc_auc": 0.8945397223068867,
|
| 73 |
+
"eval_runtime": 3712.7654,
|
| 74 |
+
"eval_samples_per_second": 34.023,
|
| 75 |
+
"eval_steps_per_second": 2.126,
|
| 76 |
+
"step": 8000
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.13,
|
| 80 |
+
"learning_rate": 2.1838829438742083e-06,
|
| 81 |
+
"loss": 0.055,
|
| 82 |
+
"step": 10000
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.13,
|
| 86 |
+
"eval_accuracy": 0.7719169081207745,
|
| 87 |
+
"eval_f1": 0.8556000272324324,
|
| 88 |
+
"eval_loss": 0.0483216755092144,
|
| 89 |
+
"eval_roc_auc": 0.9065874885210222,
|
| 90 |
+
"eval_runtime": 3715.8841,
|
| 91 |
+
"eval_samples_per_second": 33.994,
|
| 92 |
+
"eval_steps_per_second": 2.125,
|
| 93 |
+
"step": 10000
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.16,
|
| 97 |
+
"learning_rate": 2.6206595326490503e-06,
|
| 98 |
+
"loss": 0.0493,
|
| 99 |
+
"step": 12000
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.16,
|
| 103 |
+
"eval_accuracy": 0.779200113998005,
|
| 104 |
+
"eval_f1": 0.8616441123005455,
|
| 105 |
+
"eval_loss": 0.045345865190029144,
|
| 106 |
+
"eval_roc_auc": 0.9139128753285614,
|
| 107 |
+
"eval_runtime": 3715.5277,
|
| 108 |
+
"eval_samples_per_second": 33.997,
|
| 109 |
+
"eval_steps_per_second": 2.125,
|
| 110 |
+
"step": 12000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.18,
|
| 114 |
+
"learning_rate": 3.057436121423892e-06,
|
| 115 |
+
"loss": 0.0462,
|
| 116 |
+
"step": 14000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.18,
|
| 120 |
+
"eval_accuracy": 0.7865545686283824,
|
| 121 |
+
"eval_f1": 0.8685937966212471,
|
| 122 |
+
"eval_loss": 0.04221072793006897,
|
| 123 |
+
"eval_roc_auc": 0.9165307568850345,
|
| 124 |
+
"eval_runtime": 3716.006,
|
| 125 |
+
"eval_samples_per_second": 33.993,
|
| 126 |
+
"eval_steps_per_second": 2.125,
|
| 127 |
+
"step": 14000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.21,
|
| 131 |
+
"learning_rate": 3.494212710198734e-06,
|
| 132 |
+
"loss": 0.0437,
|
| 133 |
+
"step": 16000
|
| 134 |
+
},
|
| 135 |
+
{
|
| 136 |
+
"epoch": 0.21,
|
| 137 |
+
"eval_accuracy": 0.7878212131287703,
|
| 138 |
+
"eval_f1": 0.8674021275833662,
|
| 139 |
+
"eval_loss": 0.04178840294480324,
|
| 140 |
+
"eval_roc_auc": 0.9127150639723773,
|
| 141 |
+
"eval_runtime": 3717.2766,
|
| 142 |
+
"eval_samples_per_second": 33.981,
|
| 143 |
+
"eval_steps_per_second": 2.124,
|
| 144 |
+
"step": 16000
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.24,
|
| 148 |
+
"learning_rate": 3.9309892989735755e-06,
|
| 149 |
+
"loss": 0.0416,
|
| 150 |
+
"step": 18000
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.24,
|
| 154 |
+
"eval_accuracy": 0.7823746417771023,
|
| 155 |
+
"eval_f1": 0.8717482944145543,
|
| 156 |
+
"eval_loss": 0.04093621298670769,
|
| 157 |
+
"eval_roc_auc": 0.9277326030672447,
|
| 158 |
+
"eval_runtime": 3718.3054,
|
| 159 |
+
"eval_samples_per_second": 33.972,
|
| 160 |
+
"eval_steps_per_second": 2.123,
|
| 161 |
+
"step": 18000
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"epoch": 0.26,
|
| 165 |
+
"learning_rate": 4.367765887748417e-06,
|
| 166 |
+
"loss": 0.0401,
|
| 167 |
+
"step": 20000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.26,
|
| 171 |
+
"eval_accuracy": 0.7977643724568153,
|
| 172 |
+
"eval_f1": 0.8785716806040718,
|
| 173 |
+
"eval_loss": 0.03799275681376457,
|
| 174 |
+
"eval_roc_auc": 0.9242562472497354,
|
| 175 |
+
"eval_runtime": 3718.544,
|
| 176 |
+
"eval_samples_per_second": 33.97,
|
| 177 |
+
"eval_steps_per_second": 2.123,
|
| 178 |
+
"step": 20000
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.29,
|
| 182 |
+
"learning_rate": 4.804542476523259e-06,
|
| 183 |
+
"loss": 0.0396,
|
| 184 |
+
"step": 22000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.29,
|
| 188 |
+
"eval_accuracy": 0.8008518184265109,
|
| 189 |
+
"eval_f1": 0.8802290810342459,
|
| 190 |
+
"eval_loss": 0.0379040502011776,
|
| 191 |
+
"eval_roc_auc": 0.9258168171723399,
|
| 192 |
+
"eval_runtime": 3718.4418,
|
| 193 |
+
"eval_samples_per_second": 33.971,
|
| 194 |
+
"eval_steps_per_second": 2.123,
|
| 195 |
+
"step": 22000
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.31,
|
| 199 |
+
"learning_rate": 4.984596512260062e-06,
|
| 200 |
+
"loss": 0.0387,
|
| 201 |
+
"step": 24000
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.31,
|
| 205 |
+
"eval_accuracy": 0.802775534761475,
|
| 206 |
+
"eval_f1": 0.882195878143154,
|
| 207 |
+
"eval_loss": 0.036688029766082764,
|
| 208 |
+
"eval_roc_auc": 0.9262638395674476,
|
| 209 |
+
"eval_runtime": 3717.6016,
|
| 210 |
+
"eval_samples_per_second": 33.978,
|
| 211 |
+
"eval_steps_per_second": 2.124,
|
| 212 |
+
"step": 24000
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.34,
|
| 216 |
+
"learning_rate": 4.956716896441168e-06,
|
| 217 |
+
"loss": 0.0377,
|
| 218 |
+
"step": 26000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.34,
|
| 222 |
+
"eval_accuracy": 0.8030446967178074,
|
| 223 |
+
"eval_f1": 0.8856592114236406,
|
| 224 |
+
"eval_loss": 0.03543846309185028,
|
| 225 |
+
"eval_roc_auc": 0.9335204908137789,
|
| 226 |
+
"eval_runtime": 3718.4609,
|
| 227 |
+
"eval_samples_per_second": 33.971,
|
| 228 |
+
"eval_steps_per_second": 2.123,
|
| 229 |
+
"step": 26000
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"epoch": 0.37,
|
| 233 |
+
"learning_rate": 4.9288372806222735e-06,
|
| 234 |
+
"loss": 0.0366,
|
| 235 |
+
"step": 28000
|
| 236 |
+
},
|
| 237 |
+
{
|
| 238 |
+
"epoch": 0.37,
|
| 239 |
+
"eval_accuracy": 0.8094650010291486,
|
| 240 |
+
"eval_f1": 0.8885554494611922,
|
| 241 |
+
"eval_loss": 0.03468663617968559,
|
| 242 |
+
"eval_roc_auc": 0.9329188925134719,
|
| 243 |
+
"eval_runtime": 3718.3781,
|
| 244 |
+
"eval_samples_per_second": 33.971,
|
| 245 |
+
"eval_steps_per_second": 2.123,
|
| 246 |
+
"step": 28000
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.39,
|
| 250 |
+
"learning_rate": 4.900957664803379e-06,
|
| 251 |
+
"loss": 0.0359,
|
| 252 |
+
"step": 30000
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.39,
|
| 256 |
+
"eval_accuracy": 0.8062508906094144,
|
| 257 |
+
"eval_f1": 0.8869252133833476,
|
| 258 |
+
"eval_loss": 0.03476712107658386,
|
| 259 |
+
"eval_roc_auc": 0.9315236503482228,
|
| 260 |
+
"eval_runtime": 3719.6636,
|
| 261 |
+
"eval_samples_per_second": 33.96,
|
| 262 |
+
"eval_steps_per_second": 2.123,
|
| 263 |
+
"step": 30000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.42,
|
| 267 |
+
"learning_rate": 4.873078048984485e-06,
|
| 268 |
+
"loss": 0.0356,
|
| 269 |
+
"step": 32000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.42,
|
| 273 |
+
"eval_accuracy": 0.8126395288082459,
|
| 274 |
+
"eval_f1": 0.8891505277035555,
|
| 275 |
+
"eval_loss": 0.03411931172013283,
|
| 276 |
+
"eval_roc_auc": 0.9300795994141317,
|
| 277 |
+
"eval_runtime": 3718.944,
|
| 278 |
+
"eval_samples_per_second": 33.966,
|
| 279 |
+
"eval_steps_per_second": 2.123,
|
| 280 |
+
"step": 32000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.45,
|
| 284 |
+
"learning_rate": 4.845198433165592e-06,
|
| 285 |
+
"loss": 0.035,
|
| 286 |
+
"step": 34000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.45,
|
| 290 |
+
"eval_accuracy": 0.8100587406387055,
|
| 291 |
+
"eval_f1": 0.8897779847957649,
|
| 292 |
+
"eval_loss": 0.033911969512701035,
|
| 293 |
+
"eval_roc_auc": 0.9360625989159235,
|
| 294 |
+
"eval_runtime": 3718.5781,
|
| 295 |
+
"eval_samples_per_second": 33.969,
|
| 296 |
+
"eval_steps_per_second": 2.123,
|
| 297 |
+
"step": 34000
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.47,
|
| 301 |
+
"learning_rate": 4.817318817346697e-06,
|
| 302 |
+
"loss": 0.0353,
|
| 303 |
+
"step": 36000
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.47,
|
| 307 |
+
"eval_accuracy": 0.8157190582498139,
|
| 308 |
+
"eval_f1": 0.8927496417045404,
|
| 309 |
+
"eval_loss": 0.03287062793970108,
|
| 310 |
+
"eval_roc_auc": 0.9343416214326565,
|
| 311 |
+
"eval_runtime": 3719.9265,
|
| 312 |
+
"eval_samples_per_second": 33.957,
|
| 313 |
+
"eval_steps_per_second": 2.122,
|
| 314 |
+
"step": 36000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.5,
|
| 318 |
+
"learning_rate": 4.789439201527804e-06,
|
| 319 |
+
"loss": 0.0345,
|
| 320 |
+
"step": 38000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.5,
|
| 324 |
+
"eval_accuracy": 0.8162652986906063,
|
| 325 |
+
"eval_f1": 0.8934987662530843,
|
| 326 |
+
"eval_loss": 0.0325697623193264,
|
| 327 |
+
"eval_roc_auc": 0.935207039689335,
|
| 328 |
+
"eval_runtime": 3719.4103,
|
| 329 |
+
"eval_samples_per_second": 33.962,
|
| 330 |
+
"eval_steps_per_second": 2.123,
|
| 331 |
+
"step": 38000
|
| 332 |
+
}
|
| 333 |
+
],
|
| 334 |
+
"max_steps": 381580,
|
| 335 |
+
"num_train_epochs": 5,
|
| 336 |
+
"total_flos": 1.133301287682048e+18,
|
| 337 |
+
"trial_name": null,
|
| 338 |
+
"trial_params": null
|
| 339 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:52e4517a5c70ca759fe24cd776a9e49e3eb0ab855f7c9fa246d74280481a275f
|
| 3 |
+
size 2735
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|