ZhangYunchenY
commited on
Commit
·
9cd308b
1
Parent(s):
6380dd0
[Model] bart-base-qnli
Browse files- config.json +74 -0
- merges.txt +0 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +1 -0
- tokenizer.json +0 -0
- tokenizer_config.json +1 -0
- trainer_state.json +601 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/mnt/lustre/zhangyunchen/transformers/bart-base",
|
| 3 |
+
"activation_dropout": 0.1,
|
| 4 |
+
"activation_function": "gelu",
|
| 5 |
+
"add_bias_logits": false,
|
| 6 |
+
"add_final_layer_norm": false,
|
| 7 |
+
"architectures": [
|
| 8 |
+
"BartForSequenceClassification"
|
| 9 |
+
],
|
| 10 |
+
"attention_dropout": 0.1,
|
| 11 |
+
"bos_token_id": 0,
|
| 12 |
+
"classif_dropout": 0.1,
|
| 13 |
+
"classifier_dropout": 0.0,
|
| 14 |
+
"d_model": 768,
|
| 15 |
+
"decoder_attention_heads": 12,
|
| 16 |
+
"decoder_ffn_dim": 3072,
|
| 17 |
+
"decoder_layerdrop": 0.0,
|
| 18 |
+
"decoder_layers": 6,
|
| 19 |
+
"decoder_start_token_id": 2,
|
| 20 |
+
"dropout": 0.1,
|
| 21 |
+
"early_stopping": true,
|
| 22 |
+
"encoder_attention_heads": 12,
|
| 23 |
+
"encoder_ffn_dim": 3072,
|
| 24 |
+
"encoder_layerdrop": 0.0,
|
| 25 |
+
"encoder_layers": 6,
|
| 26 |
+
"eos_token_id": 2,
|
| 27 |
+
"finetuning_task": "qnli",
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "entailment",
|
| 32 |
+
"1": "not_entailment"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"entailment": 0,
|
| 38 |
+
"not_entailment": 1
|
| 39 |
+
},
|
| 40 |
+
"max_position_embeddings": 1024,
|
| 41 |
+
"model_type": "bart",
|
| 42 |
+
"no_repeat_ngram_size": 3,
|
| 43 |
+
"normalize_before": false,
|
| 44 |
+
"normalize_embedding": true,
|
| 45 |
+
"num_beams": 4,
|
| 46 |
+
"num_hidden_layers": 6,
|
| 47 |
+
"pad_token_id": 1,
|
| 48 |
+
"problem_type": "single_label_classification",
|
| 49 |
+
"scale_embedding": false,
|
| 50 |
+
"task_specific_params": {
|
| 51 |
+
"summarization": {
|
| 52 |
+
"length_penalty": 1.0,
|
| 53 |
+
"max_length": 128,
|
| 54 |
+
"min_length": 12,
|
| 55 |
+
"num_beams": 4
|
| 56 |
+
},
|
| 57 |
+
"summarization_cnn": {
|
| 58 |
+
"length_penalty": 2.0,
|
| 59 |
+
"max_length": 142,
|
| 60 |
+
"min_length": 56,
|
| 61 |
+
"num_beams": 4
|
| 62 |
+
},
|
| 63 |
+
"summarization_xsum": {
|
| 64 |
+
"length_penalty": 1.0,
|
| 65 |
+
"max_length": 62,
|
| 66 |
+
"min_length": 11,
|
| 67 |
+
"num_beams": 6
|
| 68 |
+
}
|
| 69 |
+
},
|
| 70 |
+
"torch_dtype": "float32",
|
| 71 |
+
"transformers_version": "4.16.2",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"vocab_size": 50265
|
| 74 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d8711fb50d167d06006e992e2f08394b31b9787c73fc05c1b953e984baad415
|
| 3 |
+
size 1120266491
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d32b5abb6d59ef0ac4a4726a20e361baa18ba3257f94194fbf6ddb625bd6ea5
|
| 3 |
+
size 560154805
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:184fdebcde055140ebcc99c3798c96bcd5c876ca4cd21d92ab155dbc72b36e8e
|
| 3 |
+
size 14595
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a715bef82c9849fb1445364fdcd20c1aa2893f2335f1467b95ed69501c00cdf3
|
| 3 |
+
size 623
|
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>", "trim_offsets": true, "special_tokens_map_file": null, "name_or_path": "/mnt/lustre/zhangyunchen/transformers/bart-base", "tokenizer_class": "BartTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,601 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 4.581551618814905,
|
| 5 |
+
"global_step": 15000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.06,
|
| 12 |
+
"learning_rate": 1.0070493454179256e-06,
|
| 13 |
+
"loss": 0.7017,
|
| 14 |
+
"step": 200
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.12,
|
| 18 |
+
"learning_rate": 2.0140986908358513e-06,
|
| 19 |
+
"loss": 0.6899,
|
| 20 |
+
"step": 400
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.18,
|
| 24 |
+
"learning_rate": 3.0211480362537765e-06,
|
| 25 |
+
"loss": 0.5926,
|
| 26 |
+
"step": 600
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.24,
|
| 30 |
+
"learning_rate": 4.028197381671703e-06,
|
| 31 |
+
"loss": 0.4967,
|
| 32 |
+
"step": 800
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.31,
|
| 36 |
+
"learning_rate": 5.035246727089627e-06,
|
| 37 |
+
"loss": 0.4748,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.31,
|
| 42 |
+
"eval_accuracy": 0.8350723045945451,
|
| 43 |
+
"eval_loss": 0.3857437074184418,
|
| 44 |
+
"eval_runtime": 24.3432,
|
| 45 |
+
"eval_samples_per_second": 224.416,
|
| 46 |
+
"eval_steps_per_second": 7.025,
|
| 47 |
+
"step": 1000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.37,
|
| 51 |
+
"learning_rate": 6.042296072507553e-06,
|
| 52 |
+
"loss": 0.4313,
|
| 53 |
+
"step": 1200
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.43,
|
| 57 |
+
"learning_rate": 7.0493454179254795e-06,
|
| 58 |
+
"loss": 0.4277,
|
| 59 |
+
"step": 1400
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.49,
|
| 63 |
+
"learning_rate": 8.056394763343405e-06,
|
| 64 |
+
"loss": 0.4182,
|
| 65 |
+
"step": 1600
|
| 66 |
+
},
|
| 67 |
+
{
|
| 68 |
+
"epoch": 0.55,
|
| 69 |
+
"learning_rate": 9.06344410876133e-06,
|
| 70 |
+
"loss": 0.3942,
|
| 71 |
+
"step": 1800
|
| 72 |
+
},
|
| 73 |
+
{
|
| 74 |
+
"epoch": 0.61,
|
| 75 |
+
"learning_rate": 9.995447746634584e-06,
|
| 76 |
+
"loss": 0.3548,
|
| 77 |
+
"step": 2000
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.61,
|
| 81 |
+
"eval_accuracy": 0.8813838550247117,
|
| 82 |
+
"eval_loss": 0.3002248704433441,
|
| 83 |
+
"eval_runtime": 23.5094,
|
| 84 |
+
"eval_samples_per_second": 232.375,
|
| 85 |
+
"eval_steps_per_second": 7.274,
|
| 86 |
+
"step": 2000
|
| 87 |
+
},
|
| 88 |
+
{
|
| 89 |
+
"epoch": 0.67,
|
| 90 |
+
"learning_rate": 9.930415555700073e-06,
|
| 91 |
+
"loss": 0.3842,
|
| 92 |
+
"step": 2200
|
| 93 |
+
},
|
| 94 |
+
{
|
| 95 |
+
"epoch": 0.73,
|
| 96 |
+
"learning_rate": 9.86538336476556e-06,
|
| 97 |
+
"loss": 0.3613,
|
| 98 |
+
"step": 2400
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.79,
|
| 102 |
+
"learning_rate": 9.800351173831047e-06,
|
| 103 |
+
"loss": 0.357,
|
| 104 |
+
"step": 2600
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.86,
|
| 108 |
+
"learning_rate": 9.735318982896535e-06,
|
| 109 |
+
"loss": 0.3459,
|
| 110 |
+
"step": 2800
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.92,
|
| 114 |
+
"learning_rate": 9.670286791962022e-06,
|
| 115 |
+
"loss": 0.3244,
|
| 116 |
+
"step": 3000
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.92,
|
| 120 |
+
"eval_accuracy": 0.8949295259015193,
|
| 121 |
+
"eval_loss": 0.2588460445404053,
|
| 122 |
+
"eval_runtime": 29.4325,
|
| 123 |
+
"eval_samples_per_second": 185.611,
|
| 124 |
+
"eval_steps_per_second": 5.81,
|
| 125 |
+
"step": 3000
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 0.98,
|
| 129 |
+
"learning_rate": 9.60525460102751e-06,
|
| 130 |
+
"loss": 0.3215,
|
| 131 |
+
"step": 3200
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.04,
|
| 135 |
+
"learning_rate": 9.540222410092996e-06,
|
| 136 |
+
"loss": 0.3189,
|
| 137 |
+
"step": 3400
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.1,
|
| 141 |
+
"learning_rate": 9.475190219158484e-06,
|
| 142 |
+
"loss": 0.3007,
|
| 143 |
+
"step": 3600
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.16,
|
| 147 |
+
"learning_rate": 9.410158028223972e-06,
|
| 148 |
+
"loss": 0.3032,
|
| 149 |
+
"step": 3800
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 1.22,
|
| 153 |
+
"learning_rate": 9.34512583728946e-06,
|
| 154 |
+
"loss": 0.2853,
|
| 155 |
+
"step": 4000
|
| 156 |
+
},
|
| 157 |
+
{
|
| 158 |
+
"epoch": 1.22,
|
| 159 |
+
"eval_accuracy": 0.8989566172432729,
|
| 160 |
+
"eval_loss": 0.2614916265010834,
|
| 161 |
+
"eval_runtime": 26.1105,
|
| 162 |
+
"eval_samples_per_second": 209.226,
|
| 163 |
+
"eval_steps_per_second": 6.549,
|
| 164 |
+
"step": 4000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.28,
|
| 168 |
+
"learning_rate": 9.280093646354947e-06,
|
| 169 |
+
"loss": 0.2773,
|
| 170 |
+
"step": 4200
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"epoch": 1.34,
|
| 174 |
+
"learning_rate": 9.215061455420435e-06,
|
| 175 |
+
"loss": 0.277,
|
| 176 |
+
"step": 4400
|
| 177 |
+
},
|
| 178 |
+
{
|
| 179 |
+
"epoch": 1.41,
|
| 180 |
+
"learning_rate": 9.15002926448592e-06,
|
| 181 |
+
"loss": 0.2913,
|
| 182 |
+
"step": 4600
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 1.47,
|
| 186 |
+
"learning_rate": 9.084997073551408e-06,
|
| 187 |
+
"loss": 0.2767,
|
| 188 |
+
"step": 4800
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.53,
|
| 192 |
+
"learning_rate": 9.019964882616896e-06,
|
| 193 |
+
"loss": 0.277,
|
| 194 |
+
"step": 5000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.53,
|
| 198 |
+
"eval_accuracy": 0.9011532125205931,
|
| 199 |
+
"eval_loss": 0.24724067747592926,
|
| 200 |
+
"eval_runtime": 24.2716,
|
| 201 |
+
"eval_samples_per_second": 225.078,
|
| 202 |
+
"eval_steps_per_second": 7.045,
|
| 203 |
+
"step": 5000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.59,
|
| 207 |
+
"learning_rate": 8.954932691682384e-06,
|
| 208 |
+
"loss": 0.2723,
|
| 209 |
+
"step": 5200
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.65,
|
| 213 |
+
"learning_rate": 8.889900500747872e-06,
|
| 214 |
+
"loss": 0.2767,
|
| 215 |
+
"step": 5400
|
| 216 |
+
},
|
| 217 |
+
{
|
| 218 |
+
"epoch": 1.71,
|
| 219 |
+
"learning_rate": 8.824868309813358e-06,
|
| 220 |
+
"loss": 0.2747,
|
| 221 |
+
"step": 5600
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 1.77,
|
| 225 |
+
"learning_rate": 8.759836118878845e-06,
|
| 226 |
+
"loss": 0.264,
|
| 227 |
+
"step": 5800
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 1.83,
|
| 231 |
+
"learning_rate": 8.694803927944333e-06,
|
| 232 |
+
"loss": 0.2604,
|
| 233 |
+
"step": 6000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.83,
|
| 237 |
+
"eval_accuracy": 0.9104887424492037,
|
| 238 |
+
"eval_loss": 0.22219303250312805,
|
| 239 |
+
"eval_runtime": 23.7933,
|
| 240 |
+
"eval_samples_per_second": 229.602,
|
| 241 |
+
"eval_steps_per_second": 7.187,
|
| 242 |
+
"step": 6000
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 1.89,
|
| 246 |
+
"learning_rate": 8.62977173700982e-06,
|
| 247 |
+
"loss": 0.2717,
|
| 248 |
+
"step": 6200
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.95,
|
| 252 |
+
"learning_rate": 8.564739546075308e-06,
|
| 253 |
+
"loss": 0.2733,
|
| 254 |
+
"step": 6400
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.02,
|
| 258 |
+
"learning_rate": 8.499707355140794e-06,
|
| 259 |
+
"loss": 0.245,
|
| 260 |
+
"step": 6600
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.08,
|
| 264 |
+
"learning_rate": 8.434675164206282e-06,
|
| 265 |
+
"loss": 0.2251,
|
| 266 |
+
"step": 6800
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 2.14,
|
| 270 |
+
"learning_rate": 8.36964297327177e-06,
|
| 271 |
+
"loss": 0.229,
|
| 272 |
+
"step": 7000
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 2.14,
|
| 276 |
+
"eval_accuracy": 0.9139666849716274,
|
| 277 |
+
"eval_loss": 0.21798129379749298,
|
| 278 |
+
"eval_runtime": 24.6881,
|
| 279 |
+
"eval_samples_per_second": 221.28,
|
| 280 |
+
"eval_steps_per_second": 6.926,
|
| 281 |
+
"step": 7000
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.2,
|
| 285 |
+
"learning_rate": 8.304610782337258e-06,
|
| 286 |
+
"loss": 0.2268,
|
| 287 |
+
"step": 7200
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.26,
|
| 291 |
+
"learning_rate": 8.239578591402745e-06,
|
| 292 |
+
"loss": 0.2317,
|
| 293 |
+
"step": 7400
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 2.32,
|
| 297 |
+
"learning_rate": 8.174546400468233e-06,
|
| 298 |
+
"loss": 0.2306,
|
| 299 |
+
"step": 7600
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 2.38,
|
| 303 |
+
"learning_rate": 8.109514209533719e-06,
|
| 304 |
+
"loss": 0.236,
|
| 305 |
+
"step": 7800
|
| 306 |
+
},
|
| 307 |
+
{
|
| 308 |
+
"epoch": 2.44,
|
| 309 |
+
"learning_rate": 8.044482018599207e-06,
|
| 310 |
+
"loss": 0.2257,
|
| 311 |
+
"step": 8000
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 2.44,
|
| 315 |
+
"eval_accuracy": 0.918542925132711,
|
| 316 |
+
"eval_loss": 0.2288324385881424,
|
| 317 |
+
"eval_runtime": 24.6216,
|
| 318 |
+
"eval_samples_per_second": 221.878,
|
| 319 |
+
"eval_steps_per_second": 6.945,
|
| 320 |
+
"step": 8000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 2.5,
|
| 324 |
+
"learning_rate": 7.979449827664695e-06,
|
| 325 |
+
"loss": 0.2265,
|
| 326 |
+
"step": 8200
|
| 327 |
+
},
|
| 328 |
+
{
|
| 329 |
+
"epoch": 2.57,
|
| 330 |
+
"learning_rate": 7.914417636730182e-06,
|
| 331 |
+
"loss": 0.2137,
|
| 332 |
+
"step": 8400
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 2.63,
|
| 336 |
+
"learning_rate": 7.84938544579567e-06,
|
| 337 |
+
"loss": 0.2331,
|
| 338 |
+
"step": 8600
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 2.69,
|
| 342 |
+
"learning_rate": 7.784353254861156e-06,
|
| 343 |
+
"loss": 0.2212,
|
| 344 |
+
"step": 8800
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 2.75,
|
| 348 |
+
"learning_rate": 7.719321063926645e-06,
|
| 349 |
+
"loss": 0.2292,
|
| 350 |
+
"step": 9000
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 2.75,
|
| 354 |
+
"eval_accuracy": 0.919092073952041,
|
| 355 |
+
"eval_loss": 0.2137669026851654,
|
| 356 |
+
"eval_runtime": 25.2669,
|
| 357 |
+
"eval_samples_per_second": 216.212,
|
| 358 |
+
"eval_steps_per_second": 6.768,
|
| 359 |
+
"step": 9000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 2.81,
|
| 363 |
+
"learning_rate": 7.654288872992131e-06,
|
| 364 |
+
"loss": 0.2285,
|
| 365 |
+
"step": 9200
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 2.87,
|
| 369 |
+
"learning_rate": 7.58925668205762e-06,
|
| 370 |
+
"loss": 0.2292,
|
| 371 |
+
"step": 9400
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 2.93,
|
| 375 |
+
"learning_rate": 7.524224491123107e-06,
|
| 376 |
+
"loss": 0.2153,
|
| 377 |
+
"step": 9600
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 2.99,
|
| 381 |
+
"learning_rate": 7.459192300188594e-06,
|
| 382 |
+
"loss": 0.2208,
|
| 383 |
+
"step": 9800
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.05,
|
| 387 |
+
"learning_rate": 7.394160109254081e-06,
|
| 388 |
+
"loss": 0.1947,
|
| 389 |
+
"step": 10000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 3.05,
|
| 393 |
+
"eval_accuracy": 0.914332784184514,
|
| 394 |
+
"eval_loss": 0.23720914125442505,
|
| 395 |
+
"eval_runtime": 24.8628,
|
| 396 |
+
"eval_samples_per_second": 219.726,
|
| 397 |
+
"eval_steps_per_second": 6.878,
|
| 398 |
+
"step": 10000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.12,
|
| 402 |
+
"learning_rate": 7.329127918319568e-06,
|
| 403 |
+
"loss": 0.1857,
|
| 404 |
+
"step": 10200
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 3.18,
|
| 408 |
+
"learning_rate": 7.264095727385057e-06,
|
| 409 |
+
"loss": 0.202,
|
| 410 |
+
"step": 10400
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 3.24,
|
| 414 |
+
"learning_rate": 7.199063536450544e-06,
|
| 415 |
+
"loss": 0.1804,
|
| 416 |
+
"step": 10600
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 3.3,
|
| 420 |
+
"learning_rate": 7.134031345516031e-06,
|
| 421 |
+
"loss": 0.1893,
|
| 422 |
+
"step": 10800
|
| 423 |
+
},
|
| 424 |
+
{
|
| 425 |
+
"epoch": 3.36,
|
| 426 |
+
"learning_rate": 7.068999154581518e-06,
|
| 427 |
+
"loss": 0.1946,
|
| 428 |
+
"step": 11000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 3.36,
|
| 432 |
+
"eval_accuracy": 0.924400512538898,
|
| 433 |
+
"eval_loss": 0.21092592179775238,
|
| 434 |
+
"eval_runtime": 23.8519,
|
| 435 |
+
"eval_samples_per_second": 229.038,
|
| 436 |
+
"eval_steps_per_second": 7.169,
|
| 437 |
+
"step": 11000
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 3.42,
|
| 441 |
+
"learning_rate": 7.003966963647005e-06,
|
| 442 |
+
"loss": 0.1889,
|
| 443 |
+
"step": 11200
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 3.48,
|
| 447 |
+
"learning_rate": 6.938934772712494e-06,
|
| 448 |
+
"loss": 0.1834,
|
| 449 |
+
"step": 11400
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 3.54,
|
| 453 |
+
"learning_rate": 6.873902581777981e-06,
|
| 454 |
+
"loss": 0.1887,
|
| 455 |
+
"step": 11600
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 3.6,
|
| 459 |
+
"learning_rate": 6.808870390843468e-06,
|
| 460 |
+
"loss": 0.1865,
|
| 461 |
+
"step": 11800
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 3.67,
|
| 465 |
+
"learning_rate": 6.743838199908955e-06,
|
| 466 |
+
"loss": 0.1975,
|
| 467 |
+
"step": 12000
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 3.67,
|
| 471 |
+
"eval_accuracy": 0.9178107267069375,
|
| 472 |
+
"eval_loss": 0.21930640935897827,
|
| 473 |
+
"eval_runtime": 24.5268,
|
| 474 |
+
"eval_samples_per_second": 222.736,
|
| 475 |
+
"eval_steps_per_second": 6.972,
|
| 476 |
+
"step": 12000
|
| 477 |
+
},
|
| 478 |
+
{
|
| 479 |
+
"epoch": 3.73,
|
| 480 |
+
"learning_rate": 6.678806008974443e-06,
|
| 481 |
+
"loss": 0.1905,
|
| 482 |
+
"step": 12200
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 3.79,
|
| 486 |
+
"learning_rate": 6.613773818039931e-06,
|
| 487 |
+
"loss": 0.1925,
|
| 488 |
+
"step": 12400
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 3.85,
|
| 492 |
+
"learning_rate": 6.5487416271054175e-06,
|
| 493 |
+
"loss": 0.1962,
|
| 494 |
+
"step": 12600
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 3.91,
|
| 498 |
+
"learning_rate": 6.483709436170905e-06,
|
| 499 |
+
"loss": 0.1821,
|
| 500 |
+
"step": 12800
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 3.97,
|
| 504 |
+
"learning_rate": 6.418677245236392e-06,
|
| 505 |
+
"loss": 0.1832,
|
| 506 |
+
"step": 13000
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 3.97,
|
| 510 |
+
"eval_accuracy": 0.9207395204100312,
|
| 511 |
+
"eval_loss": 0.22072818875312805,
|
| 512 |
+
"eval_runtime": 25.907,
|
| 513 |
+
"eval_samples_per_second": 210.87,
|
| 514 |
+
"eval_steps_per_second": 6.601,
|
| 515 |
+
"step": 13000
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 4.03,
|
| 519 |
+
"learning_rate": 6.35364505430188e-06,
|
| 520 |
+
"loss": 0.1752,
|
| 521 |
+
"step": 13200
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 4.09,
|
| 525 |
+
"learning_rate": 6.2886128633673675e-06,
|
| 526 |
+
"loss": 0.1565,
|
| 527 |
+
"step": 13400
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 4.15,
|
| 531 |
+
"learning_rate": 6.223580672432855e-06,
|
| 532 |
+
"loss": 0.1647,
|
| 533 |
+
"step": 13600
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 4.22,
|
| 537 |
+
"learning_rate": 6.158548481498342e-06,
|
| 538 |
+
"loss": 0.1488,
|
| 539 |
+
"step": 13800
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 4.28,
|
| 543 |
+
"learning_rate": 6.09351629056383e-06,
|
| 544 |
+
"loss": 0.1639,
|
| 545 |
+
"step": 14000
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 4.28,
|
| 549 |
+
"eval_accuracy": 0.9207395204100312,
|
| 550 |
+
"eval_loss": 0.2469523698091507,
|
| 551 |
+
"eval_runtime": 24.3069,
|
| 552 |
+
"eval_samples_per_second": 224.751,
|
| 553 |
+
"eval_steps_per_second": 7.035,
|
| 554 |
+
"step": 14000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 4.34,
|
| 558 |
+
"learning_rate": 6.028484099629317e-06,
|
| 559 |
+
"loss": 0.1652,
|
| 560 |
+
"step": 14200
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 4.4,
|
| 564 |
+
"learning_rate": 5.9634519086948035e-06,
|
| 565 |
+
"loss": 0.1675,
|
| 566 |
+
"step": 14400
|
| 567 |
+
},
|
| 568 |
+
{
|
| 569 |
+
"epoch": 4.46,
|
| 570 |
+
"learning_rate": 5.898419717760292e-06,
|
| 571 |
+
"loss": 0.1517,
|
| 572 |
+
"step": 14600
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 4.52,
|
| 576 |
+
"learning_rate": 5.833387526825779e-06,
|
| 577 |
+
"loss": 0.1543,
|
| 578 |
+
"step": 14800
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 4.58,
|
| 582 |
+
"learning_rate": 5.768355335891267e-06,
|
| 583 |
+
"loss": 0.1717,
|
| 584 |
+
"step": 15000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 4.58,
|
| 588 |
+
"eval_accuracy": 0.9231191652937946,
|
| 589 |
+
"eval_loss": 0.23586037755012512,
|
| 590 |
+
"eval_runtime": 24.1493,
|
| 591 |
+
"eval_samples_per_second": 226.218,
|
| 592 |
+
"eval_steps_per_second": 7.081,
|
| 593 |
+
"step": 15000
|
| 594 |
+
}
|
| 595 |
+
],
|
| 596 |
+
"max_steps": 32740,
|
| 597 |
+
"num_train_epochs": 10,
|
| 598 |
+
"total_flos": 3.6794803116288e+16,
|
| 599 |
+
"trial_name": null,
|
| 600 |
+
"trial_params": null
|
| 601 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb099309cc21fb78772567bef42fa8cc80608e82318b04a366d61b3c19e5cdbd
|
| 3 |
+
size 2991
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|