upload ipc_level0 model
Browse files- config.json +48 -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 +704 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "ipc0",
|
| 10 |
+
"gradient_checkpointing": false,
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 1024,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "A",
|
| 16 |
+
"1": "B",
|
| 17 |
+
"2": "C",
|
| 18 |
+
"3": "D",
|
| 19 |
+
"4": "E",
|
| 20 |
+
"5": "F",
|
| 21 |
+
"6": "G",
|
| 22 |
+
"7": "H"
|
| 23 |
+
},
|
| 24 |
+
"initializer_range": 0.02,
|
| 25 |
+
"intermediate_size": 4096,
|
| 26 |
+
"label2id": {
|
| 27 |
+
"A": 0,
|
| 28 |
+
"B": 1,
|
| 29 |
+
"C": 2,
|
| 30 |
+
"D": 3,
|
| 31 |
+
"E": 4,
|
| 32 |
+
"F": 5,
|
| 33 |
+
"G": 6,
|
| 34 |
+
"H": 7
|
| 35 |
+
},
|
| 36 |
+
"layer_norm_eps": 1e-05,
|
| 37 |
+
"max_position_embeddings": 514,
|
| 38 |
+
"model_type": "roberta",
|
| 39 |
+
"num_attention_heads": 16,
|
| 40 |
+
"num_hidden_layers": 24,
|
| 41 |
+
"pad_token_id": 1,
|
| 42 |
+
"position_embedding_type": "absolute",
|
| 43 |
+
"problem_type": "multi_label_classification",
|
| 44 |
+
"transformers_version": "4.6.1",
|
| 45 |
+
"type_vocab_size": 1,
|
| 46 |
+
"use_cache": true,
|
| 47 |
+
"vocab_size": 50265
|
| 48 |
+
}
|
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:e0f179b15fc1ed7e8b57544150935f52c02d380a1ab401567979987615bd3524
|
| 3 |
+
size 1421635885
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:79c6c475f7f9e1eedf88fa4fee6a35cdb392d2f8258ac19db5995b78fd175097
|
| 3 |
+
size 17563
|
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/"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,704 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.8422989695943094,
|
| 3 |
+
"best_model_checkpoint": "./output//roberta-large_ipc0_5__5e-5_0.01_0.06_07-20-22_16-12/checkpoint-78000",
|
| 4 |
+
"epoch": 0.14747043196404466,
|
| 5 |
+
"global_step": 86000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.0,
|
| 12 |
+
"learning_rate": 5.71588616241119e-07,
|
| 13 |
+
"loss": 0.3883,
|
| 14 |
+
"step": 2000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.0,
|
| 18 |
+
"eval_accuracy": 0.5407561450712831,
|
| 19 |
+
"eval_f1": 0.6846357008233311,
|
| 20 |
+
"eval_loss": 0.2273142784833908,
|
| 21 |
+
"eval_roc_auc": 0.7884579701932871,
|
| 22 |
+
"eval_runtime": 4707.9267,
|
| 23 |
+
"eval_samples_per_second": 62.918,
|
| 24 |
+
"step": 2000
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.01,
|
| 28 |
+
"learning_rate": 1.143177232482238e-06,
|
| 29 |
+
"loss": 0.2054,
|
| 30 |
+
"step": 4000
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.01,
|
| 34 |
+
"eval_accuracy": 0.6222245478760217,
|
| 35 |
+
"eval_f1": 0.7599527299062029,
|
| 36 |
+
"eval_loss": 0.18135647475719452,
|
| 37 |
+
"eval_roc_auc": 0.8430138570362599,
|
| 38 |
+
"eval_runtime": 4704.9968,
|
| 39 |
+
"eval_samples_per_second": 62.957,
|
| 40 |
+
"step": 4000
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.01,
|
| 44 |
+
"learning_rate": 1.7147658487233569e-06,
|
| 45 |
+
"loss": 0.1754,
|
| 46 |
+
"step": 6000
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.01,
|
| 50 |
+
"eval_accuracy": 0.6469635026146725,
|
| 51 |
+
"eval_f1": 0.7830456416949749,
|
| 52 |
+
"eval_loss": 0.16404622793197632,
|
| 53 |
+
"eval_roc_auc": 0.858923618616464,
|
| 54 |
+
"eval_runtime": 4707.9088,
|
| 55 |
+
"eval_samples_per_second": 62.918,
|
| 56 |
+
"step": 6000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.01,
|
| 60 |
+
"learning_rate": 2.286354464964476e-06,
|
| 61 |
+
"loss": 0.1619,
|
| 62 |
+
"step": 8000
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.01,
|
| 66 |
+
"eval_accuracy": 0.6548936069652581,
|
| 67 |
+
"eval_f1": 0.7882942239180966,
|
| 68 |
+
"eval_loss": 0.15830162167549133,
|
| 69 |
+
"eval_roc_auc": 0.8607893437318509,
|
| 70 |
+
"eval_runtime": 4704.8509,
|
| 71 |
+
"eval_samples_per_second": 62.959,
|
| 72 |
+
"step": 8000
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.02,
|
| 76 |
+
"learning_rate": 2.857943081205595e-06,
|
| 77 |
+
"loss": 0.1536,
|
| 78 |
+
"step": 10000
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.02,
|
| 82 |
+
"eval_accuracy": 0.6733600483435906,
|
| 83 |
+
"eval_f1": 0.8012577006532831,
|
| 84 |
+
"eval_loss": 0.14840050041675568,
|
| 85 |
+
"eval_roc_auc": 0.8665618320388239,
|
| 86 |
+
"eval_runtime": 4704.9917,
|
| 87 |
+
"eval_samples_per_second": 62.957,
|
| 88 |
+
"step": 10000
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.02,
|
| 92 |
+
"learning_rate": 3.4295316974467138e-06,
|
| 93 |
+
"loss": 0.1479,
|
| 94 |
+
"step": 12000
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.02,
|
| 98 |
+
"eval_accuracy": 0.6778433087001583,
|
| 99 |
+
"eval_f1": 0.8084837754895617,
|
| 100 |
+
"eval_loss": 0.14521972835063934,
|
| 101 |
+
"eval_roc_auc": 0.8744209349192423,
|
| 102 |
+
"eval_runtime": 4700.2006,
|
| 103 |
+
"eval_samples_per_second": 63.021,
|
| 104 |
+
"step": 12000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.02,
|
| 108 |
+
"learning_rate": 4.001120313687832e-06,
|
| 109 |
+
"loss": 0.1433,
|
| 110 |
+
"step": 14000
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.02,
|
| 114 |
+
"eval_accuracy": 0.6842576119211513,
|
| 115 |
+
"eval_f1": 0.8146811536296887,
|
| 116 |
+
"eval_loss": 0.13989576697349548,
|
| 117 |
+
"eval_roc_auc": 0.8784560258941168,
|
| 118 |
+
"eval_runtime": 4713.9153,
|
| 119 |
+
"eval_samples_per_second": 62.838,
|
| 120 |
+
"step": 14000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.03,
|
| 124 |
+
"learning_rate": 4.572708929928952e-06,
|
| 125 |
+
"loss": 0.1398,
|
| 126 |
+
"step": 16000
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.03,
|
| 130 |
+
"eval_accuracy": 0.6886058343151719,
|
| 131 |
+
"eval_f1": 0.8160765004171728,
|
| 132 |
+
"eval_loss": 0.13773857057094574,
|
| 133 |
+
"eval_roc_auc": 0.877459307877016,
|
| 134 |
+
"eval_runtime": 4705.5648,
|
| 135 |
+
"eval_samples_per_second": 62.95,
|
| 136 |
+
"step": 16000
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.03,
|
| 140 |
+
"learning_rate": 5.144297546170071e-06,
|
| 141 |
+
"loss": 0.1371,
|
| 142 |
+
"step": 18000
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.03,
|
| 146 |
+
"eval_accuracy": 0.6879238926043084,
|
| 147 |
+
"eval_f1": 0.8203506019576413,
|
| 148 |
+
"eval_loss": 0.13596272468566895,
|
| 149 |
+
"eval_roc_auc": 0.8839289957852754,
|
| 150 |
+
"eval_runtime": 4711.3568,
|
| 151 |
+
"eval_samples_per_second": 62.872,
|
| 152 |
+
"step": 18000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.03,
|
| 156 |
+
"learning_rate": 5.71588616241119e-06,
|
| 157 |
+
"loss": 0.1348,
|
| 158 |
+
"step": 20000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.03,
|
| 162 |
+
"eval_accuracy": 0.6958573729039577,
|
| 163 |
+
"eval_f1": 0.824050131286724,
|
| 164 |
+
"eval_loss": 0.13410066068172455,
|
| 165 |
+
"eval_roc_auc": 0.8851249727718851,
|
| 166 |
+
"eval_runtime": 4700.4765,
|
| 167 |
+
"eval_samples_per_second": 63.018,
|
| 168 |
+
"step": 20000
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.04,
|
| 172 |
+
"learning_rate": 6.287474778652308e-06,
|
| 173 |
+
"loss": 0.1337,
|
| 174 |
+
"step": 22000
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.04,
|
| 178 |
+
"eval_accuracy": 0.6954286273728701,
|
| 179 |
+
"eval_f1": 0.8228504902698741,
|
| 180 |
+
"eval_loss": 0.13327716290950775,
|
| 181 |
+
"eval_roc_auc": 0.8827479207014749,
|
| 182 |
+
"eval_runtime": 4730.8966,
|
| 183 |
+
"eval_samples_per_second": 62.612,
|
| 184 |
+
"step": 22000
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"epoch": 0.04,
|
| 188 |
+
"learning_rate": 6.8590633948934276e-06,
|
| 189 |
+
"loss": 0.1331,
|
| 190 |
+
"step": 24000
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.04,
|
| 194 |
+
"eval_accuracy": 0.6971469854462836,
|
| 195 |
+
"eval_f1": 0.8237129350972603,
|
| 196 |
+
"eval_loss": 0.13190585374832153,
|
| 197 |
+
"eval_roc_auc": 0.883230389109756,
|
| 198 |
+
"eval_runtime": 4692.6605,
|
| 199 |
+
"eval_samples_per_second": 63.123,
|
| 200 |
+
"step": 24000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.04,
|
| 204 |
+
"learning_rate": 7.4306520111345465e-06,
|
| 205 |
+
"loss": 0.1309,
|
| 206 |
+
"step": 26000
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.04,
|
| 210 |
+
"eval_accuracy": 0.7027004216560381,
|
| 211 |
+
"eval_f1": 0.8271447851497717,
|
| 212 |
+
"eval_loss": 0.13012564182281494,
|
| 213 |
+
"eval_roc_auc": 0.8860201435878601,
|
| 214 |
+
"eval_runtime": 4762.2583,
|
| 215 |
+
"eval_samples_per_second": 62.2,
|
| 216 |
+
"step": 26000
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.05,
|
| 220 |
+
"learning_rate": 8.002240627375665e-06,
|
| 221 |
+
"loss": 0.1298,
|
| 222 |
+
"step": 28000
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.05,
|
| 226 |
+
"eval_accuracy": 0.7013432901324385,
|
| 227 |
+
"eval_f1": 0.8245749680737388,
|
| 228 |
+
"eval_loss": 0.12999016046524048,
|
| 229 |
+
"eval_roc_auc": 0.8808593693278481,
|
| 230 |
+
"eval_runtime": 4730.1652,
|
| 231 |
+
"eval_samples_per_second": 62.622,
|
| 232 |
+
"step": 28000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.05,
|
| 236 |
+
"learning_rate": 8.573829243616784e-06,
|
| 237 |
+
"loss": 0.1284,
|
| 238 |
+
"step": 30000
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.05,
|
| 242 |
+
"eval_accuracy": 0.7064072137279592,
|
| 243 |
+
"eval_f1": 0.8300594309848033,
|
| 244 |
+
"eval_loss": 0.12789227068424225,
|
| 245 |
+
"eval_roc_auc": 0.887462059567475,
|
| 246 |
+
"eval_runtime": 4709.67,
|
| 247 |
+
"eval_samples_per_second": 62.895,
|
| 248 |
+
"step": 30000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.05,
|
| 252 |
+
"learning_rate": 9.145417859857904e-06,
|
| 253 |
+
"loss": 0.1294,
|
| 254 |
+
"step": 32000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.05,
|
| 258 |
+
"eval_accuracy": 0.7096987640650478,
|
| 259 |
+
"eval_f1": 0.8326160218501911,
|
| 260 |
+
"eval_loss": 0.12640197575092316,
|
| 261 |
+
"eval_roc_auc": 0.8885914760719662,
|
| 262 |
+
"eval_runtime": 4696.3704,
|
| 263 |
+
"eval_samples_per_second": 63.073,
|
| 264 |
+
"step": 32000
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.06,
|
| 268 |
+
"learning_rate": 9.717006476099022e-06,
|
| 269 |
+
"loss": 0.1281,
|
| 270 |
+
"step": 34000
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.06,
|
| 274 |
+
"eval_accuracy": 0.7070351402538039,
|
| 275 |
+
"eval_f1": 0.8319073213351634,
|
| 276 |
+
"eval_loss": 0.12621602416038513,
|
| 277 |
+
"eval_roc_auc": 0.8896376613488131,
|
| 278 |
+
"eval_runtime": 4698.8191,
|
| 279 |
+
"eval_samples_per_second": 63.04,
|
| 280 |
+
"step": 34000
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.06,
|
| 284 |
+
"learning_rate": 1.0288595092340142e-05,
|
| 285 |
+
"loss": 0.1266,
|
| 286 |
+
"step": 36000
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.06,
|
| 290 |
+
"eval_accuracy": 0.7081255718013727,
|
| 291 |
+
"eval_f1": 0.8335308031653823,
|
| 292 |
+
"eval_loss": 0.12684929370880127,
|
| 293 |
+
"eval_roc_auc": 0.8919053253578205,
|
| 294 |
+
"eval_runtime": 4698.6474,
|
| 295 |
+
"eval_samples_per_second": 63.042,
|
| 296 |
+
"step": 36000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.07,
|
| 300 |
+
"learning_rate": 1.086018370858126e-05,
|
| 301 |
+
"loss": 0.1264,
|
| 302 |
+
"step": 38000
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.07,
|
| 306 |
+
"eval_accuracy": 0.7080074135841439,
|
| 307 |
+
"eval_f1": 0.8339326805263629,
|
| 308 |
+
"eval_loss": 0.12483926117420197,
|
| 309 |
+
"eval_roc_auc": 0.8912626509356554,
|
| 310 |
+
"eval_runtime": 4703.9737,
|
| 311 |
+
"eval_samples_per_second": 62.971,
|
| 312 |
+
"step": 38000
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.07,
|
| 316 |
+
"learning_rate": 1.143177232482238e-05,
|
| 317 |
+
"loss": 0.1252,
|
| 318 |
+
"step": 40000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.07,
|
| 322 |
+
"eval_accuracy": 0.7134258118313511,
|
| 323 |
+
"eval_f1": 0.8343130408901507,
|
| 324 |
+
"eval_loss": 0.12493231147527695,
|
| 325 |
+
"eval_roc_auc": 0.8898269175762451,
|
| 326 |
+
"eval_runtime": 4715.1654,
|
| 327 |
+
"eval_samples_per_second": 62.821,
|
| 328 |
+
"step": 40000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.07,
|
| 332 |
+
"learning_rate": 1.20033609410635e-05,
|
| 333 |
+
"loss": 0.1253,
|
| 334 |
+
"step": 42000
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.07,
|
| 338 |
+
"eval_accuracy": 0.7114036183422064,
|
| 339 |
+
"eval_f1": 0.8363716860622692,
|
| 340 |
+
"eval_loss": 0.12403804063796997,
|
| 341 |
+
"eval_roc_auc": 0.8935152243226613,
|
| 342 |
+
"eval_runtime": 4721.8512,
|
| 343 |
+
"eval_samples_per_second": 62.732,
|
| 344 |
+
"step": 42000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.08,
|
| 348 |
+
"learning_rate": 1.2574949557304616e-05,
|
| 349 |
+
"loss": 0.1241,
|
| 350 |
+
"step": 44000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 0.08,
|
| 354 |
+
"eval_accuracy": 0.7098405539257223,
|
| 355 |
+
"eval_f1": 0.8373545897529787,
|
| 356 |
+
"eval_loss": 0.12371223419904709,
|
| 357 |
+
"eval_roc_auc": 0.8963795632569544,
|
| 358 |
+
"eval_runtime": 4728.9925,
|
| 359 |
+
"eval_samples_per_second": 62.638,
|
| 360 |
+
"step": 44000
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.08,
|
| 364 |
+
"learning_rate": 1.3146538173545735e-05,
|
| 365 |
+
"loss": 0.1238,
|
| 366 |
+
"step": 46000
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.08,
|
| 370 |
+
"eval_accuracy": 0.7124602903991385,
|
| 371 |
+
"eval_f1": 0.8370424197096473,
|
| 372 |
+
"eval_loss": 0.12373730540275574,
|
| 373 |
+
"eval_roc_auc": 0.8944393753665816,
|
| 374 |
+
"eval_runtime": 4701.3381,
|
| 375 |
+
"eval_samples_per_second": 63.006,
|
| 376 |
+
"step": 46000
|
| 377 |
+
},
|
| 378 |
+
{
|
| 379 |
+
"epoch": 0.08,
|
| 380 |
+
"learning_rate": 1.3718126789786855e-05,
|
| 381 |
+
"loss": 0.1238,
|
| 382 |
+
"step": 48000
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.08,
|
| 386 |
+
"eval_accuracy": 0.7092024995526868,
|
| 387 |
+
"eval_f1": 0.8358656658561511,
|
| 388 |
+
"eval_loss": 0.125064879655838,
|
| 389 |
+
"eval_roc_auc": 0.895248662380464,
|
| 390 |
+
"eval_runtime": 4691.6911,
|
| 391 |
+
"eval_samples_per_second": 63.136,
|
| 392 |
+
"step": 48000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.09,
|
| 396 |
+
"learning_rate": 1.4289715406027973e-05,
|
| 397 |
+
"loss": 0.1228,
|
| 398 |
+
"step": 50000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.09,
|
| 402 |
+
"eval_accuracy": 0.7139119484965211,
|
| 403 |
+
"eval_f1": 0.8380575940983299,
|
| 404 |
+
"eval_loss": 0.12305936962366104,
|
| 405 |
+
"eval_roc_auc": 0.8943202372027479,
|
| 406 |
+
"eval_runtime": 4708.5133,
|
| 407 |
+
"eval_samples_per_second": 62.91,
|
| 408 |
+
"step": 50000
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.09,
|
| 412 |
+
"learning_rate": 1.4861304022269093e-05,
|
| 413 |
+
"loss": 0.123,
|
| 414 |
+
"step": 52000
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 0.09,
|
| 418 |
+
"eval_accuracy": 0.7159408938837931,
|
| 419 |
+
"eval_f1": 0.8405024216747294,
|
| 420 |
+
"eval_loss": 0.12146713584661484,
|
| 421 |
+
"eval_roc_auc": 0.8976514718844044,
|
| 422 |
+
"eval_runtime": 4705.5754,
|
| 423 |
+
"eval_samples_per_second": 62.949,
|
| 424 |
+
"step": 52000
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.09,
|
| 428 |
+
"learning_rate": 1.5432892638510214e-05,
|
| 429 |
+
"loss": 0.123,
|
| 430 |
+
"step": 54000
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.09,
|
| 434 |
+
"eval_accuracy": 0.7114069942912701,
|
| 435 |
+
"eval_f1": 0.8382327921361191,
|
| 436 |
+
"eval_loss": 0.12516580522060394,
|
| 437 |
+
"eval_roc_auc": 0.8973778420243191,
|
| 438 |
+
"eval_runtime": 4690.4939,
|
| 439 |
+
"eval_samples_per_second": 63.152,
|
| 440 |
+
"step": 54000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 0.1,
|
| 444 |
+
"learning_rate": 1.600448125475133e-05,
|
| 445 |
+
"loss": 0.1222,
|
| 446 |
+
"step": 56000
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.1,
|
| 450 |
+
"eval_accuracy": 0.7157248331437175,
|
| 451 |
+
"eval_f1": 0.8389102808480002,
|
| 452 |
+
"eval_loss": 0.1224837601184845,
|
| 453 |
+
"eval_roc_auc": 0.8953561781764309,
|
| 454 |
+
"eval_runtime": 4699.8836,
|
| 455 |
+
"eval_samples_per_second": 63.026,
|
| 456 |
+
"step": 56000
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.1,
|
| 460 |
+
"learning_rate": 1.657606987099245e-05,
|
| 461 |
+
"loss": 0.1222,
|
| 462 |
+
"step": 58000
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.1,
|
| 466 |
+
"eval_accuracy": 0.7158564951572011,
|
| 467 |
+
"eval_f1": 0.8399927583173271,
|
| 468 |
+
"eval_loss": 0.12127628922462463,
|
| 469 |
+
"eval_roc_auc": 0.8965841568131228,
|
| 470 |
+
"eval_runtime": 4698.6002,
|
| 471 |
+
"eval_samples_per_second": 63.043,
|
| 472 |
+
"step": 58000
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.1,
|
| 476 |
+
"learning_rate": 1.714765848723357e-05,
|
| 477 |
+
"loss": 0.1219,
|
| 478 |
+
"step": 60000
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.1,
|
| 482 |
+
"eval_accuracy": 0.7170279494822982,
|
| 483 |
+
"eval_f1": 0.8398695690490878,
|
| 484 |
+
"eval_loss": 0.12054365128278732,
|
| 485 |
+
"eval_roc_auc": 0.8949977373242076,
|
| 486 |
+
"eval_runtime": 4766.0245,
|
| 487 |
+
"eval_samples_per_second": 62.151,
|
| 488 |
+
"step": 60000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.11,
|
| 492 |
+
"learning_rate": 1.7719247103474687e-05,
|
| 493 |
+
"loss": 0.1217,
|
| 494 |
+
"step": 62000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.11,
|
| 498 |
+
"eval_accuracy": 0.7173587924905389,
|
| 499 |
+
"eval_f1": 0.8384044315001998,
|
| 500 |
+
"eval_loss": 0.12145062536001205,
|
| 501 |
+
"eval_roc_auc": 0.8928348976264423,
|
| 502 |
+
"eval_runtime": 4726.8677,
|
| 503 |
+
"eval_samples_per_second": 62.666,
|
| 504 |
+
"step": 62000
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 0.11,
|
| 508 |
+
"learning_rate": 1.8290835719715808e-05,
|
| 509 |
+
"loss": 0.1212,
|
| 510 |
+
"step": 64000
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.11,
|
| 514 |
+
"eval_accuracy": 0.7183074341774331,
|
| 515 |
+
"eval_f1": 0.8391874180865005,
|
| 516 |
+
"eval_loss": 0.12094008922576904,
|
| 517 |
+
"eval_roc_auc": 0.8939367915265275,
|
| 518 |
+
"eval_runtime": 4721.7671,
|
| 519 |
+
"eval_samples_per_second": 62.734,
|
| 520 |
+
"step": 64000
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.11,
|
| 524 |
+
"learning_rate": 1.8862424335956926e-05,
|
| 525 |
+
"loss": 0.1217,
|
| 526 |
+
"step": 66000
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.11,
|
| 530 |
+
"eval_accuracy": 0.7173655443886663,
|
| 531 |
+
"eval_f1": 0.8390122732329008,
|
| 532 |
+
"eval_loss": 0.12199072539806366,
|
| 533 |
+
"eval_roc_auc": 0.8938961477593685,
|
| 534 |
+
"eval_runtime": 4689.9026,
|
| 535 |
+
"eval_samples_per_second": 63.16,
|
| 536 |
+
"step": 66000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.12,
|
| 540 |
+
"learning_rate": 1.9434012952198044e-05,
|
| 541 |
+
"loss": 0.1211,
|
| 542 |
+
"step": 68000
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.12,
|
| 546 |
+
"eval_accuracy": 0.7192932113040278,
|
| 547 |
+
"eval_f1": 0.8406356467928897,
|
| 548 |
+
"eval_loss": 0.12074108421802521,
|
| 549 |
+
"eval_roc_auc": 0.8959624591328685,
|
| 550 |
+
"eval_runtime": 4689.6506,
|
| 551 |
+
"eval_samples_per_second": 63.163,
|
| 552 |
+
"step": 68000
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.12,
|
| 556 |
+
"learning_rate": 2.0005601568439166e-05,
|
| 557 |
+
"loss": 0.1218,
|
| 558 |
+
"step": 70000
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.12,
|
| 562 |
+
"eval_accuracy": 0.718013726608893,
|
| 563 |
+
"eval_f1": 0.8394379496338936,
|
| 564 |
+
"eval_loss": 0.1212056577205658,
|
| 565 |
+
"eval_roc_auc": 0.8946202640469076,
|
| 566 |
+
"eval_runtime": 4729.1038,
|
| 567 |
+
"eval_samples_per_second": 62.636,
|
| 568 |
+
"step": 70000
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.12,
|
| 572 |
+
"learning_rate": 2.0577190184680284e-05,
|
| 573 |
+
"loss": 0.1214,
|
| 574 |
+
"step": 72000
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 0.12,
|
| 578 |
+
"eval_accuracy": 0.7165721963587013,
|
| 579 |
+
"eval_f1": 0.8417356069559346,
|
| 580 |
+
"eval_loss": 0.12099753320217133,
|
| 581 |
+
"eval_roc_auc": 0.8992088434208416,
|
| 582 |
+
"eval_runtime": 4735.2667,
|
| 583 |
+
"eval_samples_per_second": 62.555,
|
| 584 |
+
"step": 72000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.13,
|
| 588 |
+
"learning_rate": 2.11487788009214e-05,
|
| 589 |
+
"loss": 0.1208,
|
| 590 |
+
"step": 74000
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.13,
|
| 594 |
+
"eval_accuracy": 0.7096379969819016,
|
| 595 |
+
"eval_f1": 0.8359202990403864,
|
| 596 |
+
"eval_loss": 0.12574784457683563,
|
| 597 |
+
"eval_roc_auc": 0.8958735028365457,
|
| 598 |
+
"eval_runtime": 4708.3575,
|
| 599 |
+
"eval_samples_per_second": 62.912,
|
| 600 |
+
"step": 74000
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.13,
|
| 604 |
+
"learning_rate": 2.172036741716252e-05,
|
| 605 |
+
"loss": 0.1202,
|
| 606 |
+
"step": 76000
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.13,
|
| 610 |
+
"eval_accuracy": 0.7170211975841708,
|
| 611 |
+
"eval_f1": 0.8380538350579405,
|
| 612 |
+
"eval_loss": 0.12220340967178345,
|
| 613 |
+
"eval_roc_auc": 0.8937227496461092,
|
| 614 |
+
"eval_runtime": 4705.5508,
|
| 615 |
+
"eval_samples_per_second": 62.95,
|
| 616 |
+
"step": 76000
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.13,
|
| 620 |
+
"learning_rate": 2.229195603340364e-05,
|
| 621 |
+
"loss": 0.1211,
|
| 622 |
+
"step": 78000
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.13,
|
| 626 |
+
"eval_accuracy": 0.7159375179347294,
|
| 627 |
+
"eval_f1": 0.8422989695943094,
|
| 628 |
+
"eval_loss": 0.12021646648645401,
|
| 629 |
+
"eval_roc_auc": 0.8995460792466595,
|
| 630 |
+
"eval_runtime": 4706.4093,
|
| 631 |
+
"eval_samples_per_second": 62.938,
|
| 632 |
+
"step": 78000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.14,
|
| 636 |
+
"learning_rate": 2.286354464964476e-05,
|
| 637 |
+
"loss": 0.1212,
|
| 638 |
+
"step": 80000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 0.14,
|
| 642 |
+
"eval_accuracy": 0.7161333229804229,
|
| 643 |
+
"eval_f1": 0.8413767292128633,
|
| 644 |
+
"eval_loss": 0.12168838083744049,
|
| 645 |
+
"eval_roc_auc": 0.8989878842731752,
|
| 646 |
+
"eval_runtime": 4758.053,
|
| 647 |
+
"eval_samples_per_second": 62.255,
|
| 648 |
+
"step": 80000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.14,
|
| 652 |
+
"learning_rate": 2.3435133265885877e-05,
|
| 653 |
+
"loss": 0.1211,
|
| 654 |
+
"step": 82000
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.14,
|
| 658 |
+
"eval_accuracy": 0.7183985848021525,
|
| 659 |
+
"eval_f1": 0.8372888052842701,
|
| 660 |
+
"eval_loss": 0.12127470970153809,
|
| 661 |
+
"eval_roc_auc": 0.891376589798138,
|
| 662 |
+
"eval_runtime": 4718.8962,
|
| 663 |
+
"eval_samples_per_second": 62.772,
|
| 664 |
+
"step": 82000
|
| 665 |
+
},
|
| 666 |
+
{
|
| 667 |
+
"epoch": 0.14,
|
| 668 |
+
"learning_rate": 2.4006721882127e-05,
|
| 669 |
+
"loss": 0.1208,
|
| 670 |
+
"step": 84000
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.14,
|
| 674 |
+
"eval_accuracy": 0.7164675419377272,
|
| 675 |
+
"eval_f1": 0.8410196283399609,
|
| 676 |
+
"eval_loss": 0.12072896212339401,
|
| 677 |
+
"eval_roc_auc": 0.8975580711258158,
|
| 678 |
+
"eval_runtime": 4700.4599,
|
| 679 |
+
"eval_samples_per_second": 63.018,
|
| 680 |
+
"step": 84000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.15,
|
| 684 |
+
"learning_rate": 2.4578310498368117e-05,
|
| 685 |
+
"loss": 0.1207,
|
| 686 |
+
"step": 86000
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.15,
|
| 690 |
+
"eval_accuracy": 0.7182635468396052,
|
| 691 |
+
"eval_f1": 0.8404677971481037,
|
| 692 |
+
"eval_loss": 0.12209167331457138,
|
| 693 |
+
"eval_roc_auc": 0.8963189679938305,
|
| 694 |
+
"eval_runtime": 4690.2466,
|
| 695 |
+
"eval_samples_per_second": 63.155,
|
| 696 |
+
"step": 86000
|
| 697 |
+
}
|
| 698 |
+
],
|
| 699 |
+
"max_steps": 2915835,
|
| 700 |
+
"num_train_epochs": 5,
|
| 701 |
+
"total_flos": 1.39736361467904e+17,
|
| 702 |
+
"trial_name": null,
|
| 703 |
+
"trial_params": null
|
| 704 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ede448aac65db0a1c8da70bed695e971ec99a3b7595b7373bc24bebb8232e59
|
| 3 |
+
size 2479
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|