Upload model files to root directory
Browse files- config.json +28 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +56 -0
- trainer_state.json +375 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 3072,
|
| 15 |
+
"layer_norm_eps": 1e-05,
|
| 16 |
+
"max_position_embeddings": 514,
|
| 17 |
+
"model_type": "roberta",
|
| 18 |
+
"num_attention_heads": 12,
|
| 19 |
+
"num_hidden_layers": 12,
|
| 20 |
+
"pad_token_id": 1,
|
| 21 |
+
"position_embedding_type": "absolute",
|
| 22 |
+
"problem_type": "single_label_classification",
|
| 23 |
+
"torch_dtype": "float32",
|
| 24 |
+
"transformers_version": "4.43.1",
|
| 25 |
+
"type_vocab_size": 1,
|
| 26 |
+
"use_cache": true,
|
| 27 |
+
"vocab_size": 50265
|
| 28 |
+
}
|
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:c094612cea9dcaf5905c0da642fcaf038dc423743738e31f22e0c94afa2581ca
|
| 3 |
+
size 498612824
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3bac9d1e000bf018f003b16b3d68528d793d5e9edc5d44f9706910afcffc234
|
| 3 |
+
size 997345530
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71e46d01902a6e5e86b53d78c5c1fb888a4d7a73e0132f7b3c5608010601324c
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4271b529ffd68ad25597aaede6f8cfc879e800716a6412047ca47388f094caff
|
| 3 |
+
size 1064
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"unk_token": "<unk>"
|
| 56 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,375 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.05933361500501633,
|
| 3 |
+
"best_model_checkpoint": "runs/roberta-base-500000-samples-512-max-len-64-train-batch-size-8-test-batch-size-3-epochs-1e-05-lr-0.1-warmup-ratio/checkpoint-12000",
|
| 4 |
+
"epoch": 2.1331058020477816,
|
| 5 |
+
"eval_steps": 1500,
|
| 6 |
+
"global_step": 15000,
|
| 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,
|
| 13 |
+
"eval_accuracy": 0.4971,
|
| 14 |
+
"eval_f1": 0.6639222657346396,
|
| 15 |
+
"eval_loss": 0.6927798390388489,
|
| 16 |
+
"eval_precision": 0.4973866025833584,
|
| 17 |
+
"eval_recall": 0.9981112361356695,
|
| 18 |
+
"eval_runtime": 372.4207,
|
| 19 |
+
"eval_samples_per_second": 134.257,
|
| 20 |
+
"eval_steps_per_second": 16.782,
|
| 21 |
+
"step": 0
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.07110352673492605,
|
| 25 |
+
"grad_norm": 11.443495750427246,
|
| 26 |
+
"learning_rate": 2.369668246445498e-06,
|
| 27 |
+
"loss": 0.4665,
|
| 28 |
+
"step": 500
|
| 29 |
+
},
|
| 30 |
+
{
|
| 31 |
+
"epoch": 0.1422070534698521,
|
| 32 |
+
"grad_norm": 5.395324230194092,
|
| 33 |
+
"learning_rate": 4.739336492890996e-06,
|
| 34 |
+
"loss": 0.1226,
|
| 35 |
+
"step": 1000
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.21331058020477817,
|
| 39 |
+
"grad_norm": 3.713897705078125,
|
| 40 |
+
"learning_rate": 7.1090047393364935e-06,
|
| 41 |
+
"loss": 0.1013,
|
| 42 |
+
"step": 1500
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"epoch": 0.21331058020477817,
|
| 46 |
+
"eval_accuracy": 0.96946,
|
| 47 |
+
"eval_f1": 0.9694067677759302,
|
| 48 |
+
"eval_loss": 0.08184666186571121,
|
| 49 |
+
"eval_precision": 0.9665987454552719,
|
| 50 |
+
"eval_recall": 0.9722311525478219,
|
| 51 |
+
"eval_runtime": 369.1947,
|
| 52 |
+
"eval_samples_per_second": 135.43,
|
| 53 |
+
"eval_steps_per_second": 16.929,
|
| 54 |
+
"step": 1500
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.2844141069397042,
|
| 58 |
+
"grad_norm": 22.85436248779297,
|
| 59 |
+
"learning_rate": 9.478672985781992e-06,
|
| 60 |
+
"loss": 0.0911,
|
| 61 |
+
"step": 2000
|
| 62 |
+
},
|
| 63 |
+
{
|
| 64 |
+
"epoch": 0.35551763367463024,
|
| 65 |
+
"grad_norm": 2.183819532394409,
|
| 66 |
+
"learning_rate": 9.794585484040872e-06,
|
| 67 |
+
"loss": 0.0904,
|
| 68 |
+
"step": 2500
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.42662116040955633,
|
| 72 |
+
"grad_norm": 3.5085792541503906,
|
| 73 |
+
"learning_rate": 9.53123354050353e-06,
|
| 74 |
+
"loss": 0.0853,
|
| 75 |
+
"step": 3000
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.42662116040955633,
|
| 79 |
+
"eval_accuracy": 0.97452,
|
| 80 |
+
"eval_f1": 0.97444332998997,
|
| 81 |
+
"eval_loss": 0.06914982199668884,
|
| 82 |
+
"eval_precision": 0.9728430665705359,
|
| 83 |
+
"eval_recall": 0.9760488667416815,
|
| 84 |
+
"eval_runtime": 369.1227,
|
| 85 |
+
"eval_samples_per_second": 135.456,
|
| 86 |
+
"eval_steps_per_second": 16.932,
|
| 87 |
+
"step": 3000
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.49772468714448237,
|
| 91 |
+
"grad_norm": 6.5320234298706055,
|
| 92 |
+
"learning_rate": 9.267881596966186e-06,
|
| 93 |
+
"loss": 0.0799,
|
| 94 |
+
"step": 3500
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.5688282138794084,
|
| 98 |
+
"grad_norm": 1.3349543809890747,
|
| 99 |
+
"learning_rate": 9.004529653428843e-06,
|
| 100 |
+
"loss": 0.0751,
|
| 101 |
+
"step": 4000
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.6399317406143344,
|
| 105 |
+
"grad_norm": 1.4865925312042236,
|
| 106 |
+
"learning_rate": 8.7411777098915e-06,
|
| 107 |
+
"loss": 0.0742,
|
| 108 |
+
"step": 4500
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.6399317406143344,
|
| 112 |
+
"eval_accuracy": 0.97572,
|
| 113 |
+
"eval_f1": 0.9756136756257282,
|
| 114 |
+
"eval_loss": 0.06528624147176743,
|
| 115 |
+
"eval_precision": 0.9753393846895333,
|
| 116 |
+
"eval_recall": 0.9758881208808873,
|
| 117 |
+
"eval_runtime": 369.1379,
|
| 118 |
+
"eval_samples_per_second": 135.451,
|
| 119 |
+
"eval_steps_per_second": 16.931,
|
| 120 |
+
"step": 4500
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"epoch": 0.7110352673492605,
|
| 124 |
+
"grad_norm": 1.9182387590408325,
|
| 125 |
+
"learning_rate": 8.477825766354156e-06,
|
| 126 |
+
"loss": 0.0761,
|
| 127 |
+
"step": 5000
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"epoch": 0.7821387940841866,
|
| 131 |
+
"grad_norm": 4.340898036956787,
|
| 132 |
+
"learning_rate": 8.214473822816812e-06,
|
| 133 |
+
"loss": 0.0742,
|
| 134 |
+
"step": 5500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.8532423208191127,
|
| 138 |
+
"grad_norm": 4.503939151763916,
|
| 139 |
+
"learning_rate": 7.95112187927947e-06,
|
| 140 |
+
"loss": 0.0722,
|
| 141 |
+
"step": 6000
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.8532423208191127,
|
| 145 |
+
"eval_accuracy": 0.97488,
|
| 146 |
+
"eval_f1": 0.9744964262508122,
|
| 147 |
+
"eval_loss": 0.06521258503198624,
|
| 148 |
+
"eval_precision": 0.9848957478246594,
|
| 149 |
+
"eval_recall": 0.9643144189037133,
|
| 150 |
+
"eval_runtime": 369.1106,
|
| 151 |
+
"eval_samples_per_second": 135.461,
|
| 152 |
+
"eval_steps_per_second": 16.933,
|
| 153 |
+
"step": 6000
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.9243458475540387,
|
| 157 |
+
"grad_norm": 5.767714977264404,
|
| 158 |
+
"learning_rate": 7.687769935742126e-06,
|
| 159 |
+
"loss": 0.0664,
|
| 160 |
+
"step": 6500
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.9954493742889647,
|
| 164 |
+
"grad_norm": 1.0236719846725464,
|
| 165 |
+
"learning_rate": 7.424417992204783e-06,
|
| 166 |
+
"loss": 0.0687,
|
| 167 |
+
"step": 7000
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 1.0665529010238908,
|
| 171 |
+
"grad_norm": 5.575131416320801,
|
| 172 |
+
"learning_rate": 7.1610660486674395e-06,
|
| 173 |
+
"loss": 0.0594,
|
| 174 |
+
"step": 7500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 1.0665529010238908,
|
| 178 |
+
"eval_accuracy": 0.9734,
|
| 179 |
+
"eval_f1": 0.9729013854930725,
|
| 180 |
+
"eval_loss": 0.07639238238334656,
|
| 181 |
+
"eval_precision": 0.9867333443544387,
|
| 182 |
+
"eval_recall": 0.9594518566146921,
|
| 183 |
+
"eval_runtime": 369.1258,
|
| 184 |
+
"eval_samples_per_second": 135.455,
|
| 185 |
+
"eval_steps_per_second": 16.932,
|
| 186 |
+
"step": 7500
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 1.1376564277588168,
|
| 190 |
+
"grad_norm": 1.4480912685394287,
|
| 191 |
+
"learning_rate": 6.8977141051300965e-06,
|
| 192 |
+
"loss": 0.0613,
|
| 193 |
+
"step": 8000
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"epoch": 1.2087599544937428,
|
| 197 |
+
"grad_norm": 14.01652717590332,
|
| 198 |
+
"learning_rate": 6.6343621615927535e-06,
|
| 199 |
+
"loss": 0.0626,
|
| 200 |
+
"step": 8500
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 1.2798634812286689,
|
| 204 |
+
"grad_norm": 2.645029067993164,
|
| 205 |
+
"learning_rate": 6.3710102180554104e-06,
|
| 206 |
+
"loss": 0.0595,
|
| 207 |
+
"step": 9000
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.2798634812286689,
|
| 211 |
+
"eval_accuracy": 0.97674,
|
| 212 |
+
"eval_f1": 0.9764427069618586,
|
| 213 |
+
"eval_loss": 0.0677267462015152,
|
| 214 |
+
"eval_precision": 0.9843986113947315,
|
| 215 |
+
"eval_recall": 0.968614370679955,
|
| 216 |
+
"eval_runtime": 369.1238,
|
| 217 |
+
"eval_samples_per_second": 135.456,
|
| 218 |
+
"eval_steps_per_second": 16.932,
|
| 219 |
+
"step": 9000
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.350967007963595,
|
| 223 |
+
"grad_norm": 4.5592122077941895,
|
| 224 |
+
"learning_rate": 6.1076582745180666e-06,
|
| 225 |
+
"loss": 0.0618,
|
| 226 |
+
"step": 9500
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 1.4220705346985212,
|
| 230 |
+
"grad_norm": 5.417106628417969,
|
| 231 |
+
"learning_rate": 5.8443063309807235e-06,
|
| 232 |
+
"loss": 0.058,
|
| 233 |
+
"step": 10000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.493174061433447,
|
| 237 |
+
"grad_norm": 1.136661171913147,
|
| 238 |
+
"learning_rate": 5.5809543874433805e-06,
|
| 239 |
+
"loss": 0.0542,
|
| 240 |
+
"step": 10500
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"epoch": 1.493174061433447,
|
| 244 |
+
"eval_accuracy": 0.97848,
|
| 245 |
+
"eval_f1": 0.9783422567529487,
|
| 246 |
+
"eval_loss": 0.06500901281833649,
|
| 247 |
+
"eval_precision": 0.9800387127994193,
|
| 248 |
+
"eval_recall": 0.9766516637196592,
|
| 249 |
+
"eval_runtime": 369.2146,
|
| 250 |
+
"eval_samples_per_second": 135.423,
|
| 251 |
+
"eval_steps_per_second": 16.928,
|
| 252 |
+
"step": 10500
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 1.5642775881683733,
|
| 256 |
+
"grad_norm": 2.5331344604492188,
|
| 257 |
+
"learning_rate": 5.317602443906037e-06,
|
| 258 |
+
"loss": 0.0623,
|
| 259 |
+
"step": 11000
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 1.635381114903299,
|
| 263 |
+
"grad_norm": 2.5099124908447266,
|
| 264 |
+
"learning_rate": 5.054250500368693e-06,
|
| 265 |
+
"loss": 0.0617,
|
| 266 |
+
"step": 11500
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 1.7064846416382253,
|
| 270 |
+
"grad_norm": 0.18802767992019653,
|
| 271 |
+
"learning_rate": 4.79089855683135e-06,
|
| 272 |
+
"loss": 0.0571,
|
| 273 |
+
"step": 12000
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.7064846416382253,
|
| 277 |
+
"eval_accuracy": 0.97944,
|
| 278 |
+
"eval_f1": 0.9793847511330366,
|
| 279 |
+
"eval_loss": 0.05933361500501633,
|
| 280 |
+
"eval_precision": 0.9774637739172204,
|
| 281 |
+
"eval_recall": 0.9813132936826877,
|
| 282 |
+
"eval_runtime": 369.1545,
|
| 283 |
+
"eval_samples_per_second": 135.445,
|
| 284 |
+
"eval_steps_per_second": 16.931,
|
| 285 |
+
"step": 12000
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.7775881683731511,
|
| 289 |
+
"grad_norm": 0.17306402325630188,
|
| 290 |
+
"learning_rate": 4.527546613294007e-06,
|
| 291 |
+
"loss": 0.0575,
|
| 292 |
+
"step": 12500
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 1.8486916951080774,
|
| 296 |
+
"grad_norm": 2.0170910358428955,
|
| 297 |
+
"learning_rate": 4.264194669756664e-06,
|
| 298 |
+
"loss": 0.0573,
|
| 299 |
+
"step": 13000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.9197952218430034,
|
| 303 |
+
"grad_norm": 1.0754927396774292,
|
| 304 |
+
"learning_rate": 4.00084272621932e-06,
|
| 305 |
+
"loss": 0.0562,
|
| 306 |
+
"step": 13500
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 1.9197952218430034,
|
| 310 |
+
"eval_accuracy": 0.9793,
|
| 311 |
+
"eval_f1": 0.9792272955343703,
|
| 312 |
+
"eval_loss": 0.05992409214377403,
|
| 313 |
+
"eval_precision": 0.9781083356721864,
|
| 314 |
+
"eval_recall": 0.9803488185179232,
|
| 315 |
+
"eval_runtime": 369.2584,
|
| 316 |
+
"eval_samples_per_second": 135.407,
|
| 317 |
+
"eval_steps_per_second": 16.926,
|
| 318 |
+
"step": 13500
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 1.9908987485779295,
|
| 322 |
+
"grad_norm": 0.5176452398300171,
|
| 323 |
+
"learning_rate": 3.7374907826819767e-06,
|
| 324 |
+
"loss": 0.0553,
|
| 325 |
+
"step": 14000
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 2.0620022753128557,
|
| 329 |
+
"grad_norm": 3.9174857139587402,
|
| 330 |
+
"learning_rate": 3.474138839144633e-06,
|
| 331 |
+
"loss": 0.0506,
|
| 332 |
+
"step": 14500
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.1331058020477816,
|
| 336 |
+
"grad_norm": 2.6643998622894287,
|
| 337 |
+
"learning_rate": 3.21078689560729e-06,
|
| 338 |
+
"loss": 0.0463,
|
| 339 |
+
"step": 15000
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 2.1331058020477816,
|
| 343 |
+
"eval_accuracy": 0.97976,
|
| 344 |
+
"eval_f1": 0.9796746334605343,
|
| 345 |
+
"eval_loss": 0.05948900803923607,
|
| 346 |
+
"eval_precision": 0.9792419497309885,
|
| 347 |
+
"eval_recall": 0.9801076997267321,
|
| 348 |
+
"eval_runtime": 369.2026,
|
| 349 |
+
"eval_samples_per_second": 135.427,
|
| 350 |
+
"eval_steps_per_second": 16.928,
|
| 351 |
+
"step": 15000
|
| 352 |
+
}
|
| 353 |
+
],
|
| 354 |
+
"logging_steps": 500,
|
| 355 |
+
"max_steps": 21096,
|
| 356 |
+
"num_input_tokens_seen": 0,
|
| 357 |
+
"num_train_epochs": 3,
|
| 358 |
+
"save_steps": 1500,
|
| 359 |
+
"stateful_callbacks": {
|
| 360 |
+
"TrainerControl": {
|
| 361 |
+
"args": {
|
| 362 |
+
"should_epoch_stop": false,
|
| 363 |
+
"should_evaluate": false,
|
| 364 |
+
"should_log": false,
|
| 365 |
+
"should_save": true,
|
| 366 |
+
"should_training_stop": false
|
| 367 |
+
},
|
| 368 |
+
"attributes": {}
|
| 369 |
+
}
|
| 370 |
+
},
|
| 371 |
+
"total_flos": 2.5256135448428544e+17,
|
| 372 |
+
"train_batch_size": 64,
|
| 373 |
+
"trial_name": null,
|
| 374 |
+
"trial_params": null
|
| 375 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff399c0ee8d946a58ab10a5caf56fcb453cd55ab1150693829b072740be35bca
|
| 3 |
+
size 5496
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|