ZhangYunchenY
commited on
Commit
·
f8102ed
1
Parent(s):
be21b00
[Model] bert-base-uncased-mnli
Browse files- config.json +38 -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 +721 -0
- training_args.bin +3 -0
- vocab.txt +0 -0
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/mnt/lustre/weixiuying/transformer/pretrain_models/bert-base-uncased",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"BertForSequenceClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"classifier_dropout": null,
|
| 8 |
+
"finetuning_task": "mnli",
|
| 9 |
+
"gradient_checkpointing": false,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_dropout_prob": 0.1,
|
| 12 |
+
"hidden_size": 768,
|
| 13 |
+
"id2label": {
|
| 14 |
+
"0": "entailment",
|
| 15 |
+
"1": "neutral",
|
| 16 |
+
"2": "contradiction"
|
| 17 |
+
},
|
| 18 |
+
"initializer_range": 0.02,
|
| 19 |
+
"intermediate_size": 3072,
|
| 20 |
+
"label2id": {
|
| 21 |
+
"contradiction": 2,
|
| 22 |
+
"entailment": 0,
|
| 23 |
+
"neutral": 1
|
| 24 |
+
},
|
| 25 |
+
"layer_norm_eps": 1e-12,
|
| 26 |
+
"max_position_embeddings": 512,
|
| 27 |
+
"model_type": "bert",
|
| 28 |
+
"num_attention_heads": 12,
|
| 29 |
+
"num_hidden_layers": 12,
|
| 30 |
+
"pad_token_id": 0,
|
| 31 |
+
"position_embedding_type": "absolute",
|
| 32 |
+
"problem_type": "single_label_classification",
|
| 33 |
+
"torch_dtype": "float32",
|
| 34 |
+
"transformers_version": "4.13.0.dev0",
|
| 35 |
+
"type_vocab_size": 2,
|
| 36 |
+
"use_cache": true,
|
| 37 |
+
"vocab_size": 30522
|
| 38 |
+
}
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab18e2d0c49f71cac7a139d3beb2c3a9b820c5a4a1406fb0b6fbf1390b6f70a3
|
| 3 |
+
size 876003363
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6171d37d1d3798119b2c029c2c3d69c3d3dda5c2e87cdb1b488639d2caed8c3b
|
| 3 |
+
size 438027923
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f45a648f17b4ad05c832d183d5e86c432791b7e29bf5d3290d1f56923c9c87d8
|
| 3 |
+
size 14659
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f9565d4708a7f313ee8b56b9d2bc57407d0a6dcdecc4390033a2e1323e7f286e
|
| 3 |
+
size 623
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "special_tokens_map_file": null, "name_or_path": "/mnt/lustre/weixiuying/transformer/pretrain_models/bert-base-uncased", "tokenizer_class": "BertTokenizer"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,721 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.41607236862182617,
|
| 3 |
+
"best_model_checkpoint": "output_dir/finetuned_best_mnli/checkpoint-12000",
|
| 4 |
+
"epoch": 1.9149282920469362,
|
| 5 |
+
"global_step": 23500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.04,
|
| 12 |
+
"learning_rate": 1.983702737940026e-05,
|
| 13 |
+
"loss": 0.8277,
|
| 14 |
+
"step": 500
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.04,
|
| 18 |
+
"eval_accuracy": 0.7111563932755985,
|
| 19 |
+
"eval_loss": 0.6876205801963806,
|
| 20 |
+
"eval_runtime": 133.5092,
|
| 21 |
+
"eval_samples_per_second": 73.516,
|
| 22 |
+
"eval_steps_per_second": 9.19,
|
| 23 |
+
"step": 500
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.08,
|
| 27 |
+
"learning_rate": 1.9674054758800523e-05,
|
| 28 |
+
"loss": 0.6598,
|
| 29 |
+
"step": 1000
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.08,
|
| 33 |
+
"eval_accuracy": 0.7539480387162506,
|
| 34 |
+
"eval_loss": 0.6054476499557495,
|
| 35 |
+
"eval_runtime": 151.2877,
|
| 36 |
+
"eval_samples_per_second": 64.876,
|
| 37 |
+
"eval_steps_per_second": 8.11,
|
| 38 |
+
"step": 1000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.12,
|
| 42 |
+
"learning_rate": 1.9511082138200782e-05,
|
| 43 |
+
"loss": 0.6012,
|
| 44 |
+
"step": 1500
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.12,
|
| 48 |
+
"eval_accuracy": 0.7814569536423841,
|
| 49 |
+
"eval_loss": 0.5584900975227356,
|
| 50 |
+
"eval_runtime": 160.2112,
|
| 51 |
+
"eval_samples_per_second": 61.263,
|
| 52 |
+
"eval_steps_per_second": 7.659,
|
| 53 |
+
"step": 1500
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.16,
|
| 57 |
+
"learning_rate": 1.9348109517601044e-05,
|
| 58 |
+
"loss": 0.5589,
|
| 59 |
+
"step": 2000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.16,
|
| 63 |
+
"eval_accuracy": 0.7909322465613856,
|
| 64 |
+
"eval_loss": 0.5319538116455078,
|
| 65 |
+
"eval_runtime": 160.4115,
|
| 66 |
+
"eval_samples_per_second": 61.186,
|
| 67 |
+
"eval_steps_per_second": 7.649,
|
| 68 |
+
"step": 2000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.2,
|
| 72 |
+
"learning_rate": 1.9185136897001307e-05,
|
| 73 |
+
"loss": 0.5631,
|
| 74 |
+
"step": 2500
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.2,
|
| 78 |
+
"eval_accuracy": 0.7811512990320937,
|
| 79 |
+
"eval_loss": 0.5446802973747253,
|
| 80 |
+
"eval_runtime": 190.5286,
|
| 81 |
+
"eval_samples_per_second": 51.515,
|
| 82 |
+
"eval_steps_per_second": 6.44,
|
| 83 |
+
"step": 2500
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.24,
|
| 87 |
+
"learning_rate": 1.9022164276401566e-05,
|
| 88 |
+
"loss": 0.5556,
|
| 89 |
+
"step": 3000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.24,
|
| 93 |
+
"eval_accuracy": 0.795109526235354,
|
| 94 |
+
"eval_loss": 0.5091724991798401,
|
| 95 |
+
"eval_runtime": 100.2906,
|
| 96 |
+
"eval_samples_per_second": 97.866,
|
| 97 |
+
"eval_steps_per_second": 12.234,
|
| 98 |
+
"step": 3000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.29,
|
| 102 |
+
"learning_rate": 1.8859191655801828e-05,
|
| 103 |
+
"loss": 0.5311,
|
| 104 |
+
"step": 3500
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.29,
|
| 108 |
+
"eval_accuracy": 0.8002037697401936,
|
| 109 |
+
"eval_loss": 0.5131673216819763,
|
| 110 |
+
"eval_runtime": 106.1752,
|
| 111 |
+
"eval_samples_per_second": 92.442,
|
| 112 |
+
"eval_steps_per_second": 11.556,
|
| 113 |
+
"step": 3500
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.33,
|
| 117 |
+
"learning_rate": 1.8696219035202087e-05,
|
| 118 |
+
"loss": 0.5119,
|
| 119 |
+
"step": 4000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.33,
|
| 123 |
+
"eval_accuracy": 0.8132450331125828,
|
| 124 |
+
"eval_loss": 0.47580984234809875,
|
| 125 |
+
"eval_runtime": 84.6709,
|
| 126 |
+
"eval_samples_per_second": 115.919,
|
| 127 |
+
"eval_steps_per_second": 14.491,
|
| 128 |
+
"step": 4000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.37,
|
| 132 |
+
"learning_rate": 1.853324641460235e-05,
|
| 133 |
+
"loss": 0.4988,
|
| 134 |
+
"step": 4500
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.37,
|
| 138 |
+
"eval_accuracy": 0.8033622007131941,
|
| 139 |
+
"eval_loss": 0.5015984177589417,
|
| 140 |
+
"eval_runtime": 120.1676,
|
| 141 |
+
"eval_samples_per_second": 81.678,
|
| 142 |
+
"eval_steps_per_second": 10.211,
|
| 143 |
+
"step": 4500
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.41,
|
| 147 |
+
"learning_rate": 1.837027379400261e-05,
|
| 148 |
+
"loss": 0.509,
|
| 149 |
+
"step": 5000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.41,
|
| 153 |
+
"eval_accuracy": 0.8169128884360672,
|
| 154 |
+
"eval_loss": 0.4686170220375061,
|
| 155 |
+
"eval_runtime": 115.84,
|
| 156 |
+
"eval_samples_per_second": 84.729,
|
| 157 |
+
"eval_steps_per_second": 10.592,
|
| 158 |
+
"step": 5000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.45,
|
| 162 |
+
"learning_rate": 1.820730117340287e-05,
|
| 163 |
+
"loss": 0.5033,
|
| 164 |
+
"step": 5500
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.45,
|
| 168 |
+
"eval_accuracy": 0.8121242995415181,
|
| 169 |
+
"eval_loss": 0.4700980484485626,
|
| 170 |
+
"eval_runtime": 103.4737,
|
| 171 |
+
"eval_samples_per_second": 94.855,
|
| 172 |
+
"eval_steps_per_second": 11.858,
|
| 173 |
+
"step": 5500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.49,
|
| 177 |
+
"learning_rate": 1.804432855280313e-05,
|
| 178 |
+
"loss": 0.4834,
|
| 179 |
+
"step": 6000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.49,
|
| 183 |
+
"eval_accuracy": 0.8227203260315843,
|
| 184 |
+
"eval_loss": 0.4637387990951538,
|
| 185 |
+
"eval_runtime": 110.8909,
|
| 186 |
+
"eval_samples_per_second": 88.51,
|
| 187 |
+
"eval_steps_per_second": 11.065,
|
| 188 |
+
"step": 6000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.53,
|
| 192 |
+
"learning_rate": 1.788135593220339e-05,
|
| 193 |
+
"loss": 0.4863,
|
| 194 |
+
"step": 6500
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 0.53,
|
| 198 |
+
"eval_accuracy": 0.8237391747325522,
|
| 199 |
+
"eval_loss": 0.45791763067245483,
|
| 200 |
+
"eval_runtime": 95.3317,
|
| 201 |
+
"eval_samples_per_second": 102.956,
|
| 202 |
+
"eval_steps_per_second": 12.871,
|
| 203 |
+
"step": 6500
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.57,
|
| 207 |
+
"learning_rate": 1.771838331160365e-05,
|
| 208 |
+
"loss": 0.4829,
|
| 209 |
+
"step": 7000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.57,
|
| 213 |
+
"eval_accuracy": 0.823331635252165,
|
| 214 |
+
"eval_loss": 0.463431179523468,
|
| 215 |
+
"eval_runtime": 94.439,
|
| 216 |
+
"eval_samples_per_second": 103.93,
|
| 217 |
+
"eval_steps_per_second": 12.993,
|
| 218 |
+
"step": 7000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.61,
|
| 222 |
+
"learning_rate": 1.7555410691003914e-05,
|
| 223 |
+
"loss": 0.4819,
|
| 224 |
+
"step": 7500
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.61,
|
| 228 |
+
"eval_accuracy": 0.8260825267447784,
|
| 229 |
+
"eval_loss": 0.4441950023174286,
|
| 230 |
+
"eval_runtime": 106.424,
|
| 231 |
+
"eval_samples_per_second": 92.225,
|
| 232 |
+
"eval_steps_per_second": 11.529,
|
| 233 |
+
"step": 7500
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 0.65,
|
| 237 |
+
"learning_rate": 1.7392438070404173e-05,
|
| 238 |
+
"loss": 0.4763,
|
| 239 |
+
"step": 8000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.65,
|
| 243 |
+
"eval_accuracy": 0.8212939378502292,
|
| 244 |
+
"eval_loss": 0.44791945815086365,
|
| 245 |
+
"eval_runtime": 88.0696,
|
| 246 |
+
"eval_samples_per_second": 111.446,
|
| 247 |
+
"eval_steps_per_second": 13.932,
|
| 248 |
+
"step": 8000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.69,
|
| 252 |
+
"learning_rate": 1.7229465449804435e-05,
|
| 253 |
+
"loss": 0.4738,
|
| 254 |
+
"step": 8500
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.69,
|
| 258 |
+
"eval_accuracy": 0.8275089149261334,
|
| 259 |
+
"eval_loss": 0.45088809728622437,
|
| 260 |
+
"eval_runtime": 92.5901,
|
| 261 |
+
"eval_samples_per_second": 106.005,
|
| 262 |
+
"eval_steps_per_second": 13.252,
|
| 263 |
+
"step": 8500
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 0.73,
|
| 267 |
+
"learning_rate": 1.7066492829204694e-05,
|
| 268 |
+
"loss": 0.4687,
|
| 269 |
+
"step": 9000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.73,
|
| 273 |
+
"eval_accuracy": 0.8311767702496179,
|
| 274 |
+
"eval_loss": 0.43536150455474854,
|
| 275 |
+
"eval_runtime": 126.1698,
|
| 276 |
+
"eval_samples_per_second": 77.792,
|
| 277 |
+
"eval_steps_per_second": 9.725,
|
| 278 |
+
"step": 9000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 0.77,
|
| 282 |
+
"learning_rate": 1.6903520208604957e-05,
|
| 283 |
+
"loss": 0.468,
|
| 284 |
+
"step": 9500
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 0.77,
|
| 288 |
+
"eval_accuracy": 0.8322975038206827,
|
| 289 |
+
"eval_loss": 0.43157872557640076,
|
| 290 |
+
"eval_runtime": 113.9939,
|
| 291 |
+
"eval_samples_per_second": 86.101,
|
| 292 |
+
"eval_steps_per_second": 10.764,
|
| 293 |
+
"step": 9500
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 0.81,
|
| 297 |
+
"learning_rate": 1.6740547588005215e-05,
|
| 298 |
+
"loss": 0.4529,
|
| 299 |
+
"step": 10000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 0.81,
|
| 303 |
+
"eval_accuracy": 0.8317880794701987,
|
| 304 |
+
"eval_loss": 0.42749524116516113,
|
| 305 |
+
"eval_runtime": 115.1753,
|
| 306 |
+
"eval_samples_per_second": 85.218,
|
| 307 |
+
"eval_steps_per_second": 10.653,
|
| 308 |
+
"step": 10000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.86,
|
| 312 |
+
"learning_rate": 1.6577574967405478e-05,
|
| 313 |
+
"loss": 0.4617,
|
| 314 |
+
"step": 10500
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.86,
|
| 318 |
+
"eval_accuracy": 0.8309730005094244,
|
| 319 |
+
"eval_loss": 0.43376246094703674,
|
| 320 |
+
"eval_runtime": 139.6786,
|
| 321 |
+
"eval_samples_per_second": 70.268,
|
| 322 |
+
"eval_steps_per_second": 8.784,
|
| 323 |
+
"step": 10500
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 0.9,
|
| 327 |
+
"learning_rate": 1.6414602346805737e-05,
|
| 328 |
+
"loss": 0.4534,
|
| 329 |
+
"step": 11000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 0.9,
|
| 333 |
+
"eval_accuracy": 0.8359653591441671,
|
| 334 |
+
"eval_loss": 0.42552220821380615,
|
| 335 |
+
"eval_runtime": 96.9513,
|
| 336 |
+
"eval_samples_per_second": 101.236,
|
| 337 |
+
"eval_steps_per_second": 12.656,
|
| 338 |
+
"step": 11000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.94,
|
| 342 |
+
"learning_rate": 1.6251629726206e-05,
|
| 343 |
+
"loss": 0.4536,
|
| 344 |
+
"step": 11500
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 0.94,
|
| 348 |
+
"eval_accuracy": 0.8359653591441671,
|
| 349 |
+
"eval_loss": 0.41881263256073,
|
| 350 |
+
"eval_runtime": 108.0698,
|
| 351 |
+
"eval_samples_per_second": 90.821,
|
| 352 |
+
"eval_steps_per_second": 11.354,
|
| 353 |
+
"step": 11500
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.98,
|
| 357 |
+
"learning_rate": 1.608865710560626e-05,
|
| 358 |
+
"loss": 0.4551,
|
| 359 |
+
"step": 12000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 0.98,
|
| 363 |
+
"eval_accuracy": 0.8391237901171676,
|
| 364 |
+
"eval_loss": 0.41607236862182617,
|
| 365 |
+
"eval_runtime": 89.8988,
|
| 366 |
+
"eval_samples_per_second": 109.178,
|
| 367 |
+
"eval_steps_per_second": 13.649,
|
| 368 |
+
"step": 12000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 1.02,
|
| 372 |
+
"learning_rate": 1.592568448500652e-05,
|
| 373 |
+
"loss": 0.4006,
|
| 374 |
+
"step": 12500
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 1.02,
|
| 378 |
+
"eval_accuracy": 0.8356597045338767,
|
| 379 |
+
"eval_loss": 0.4454086124897003,
|
| 380 |
+
"eval_runtime": 91.709,
|
| 381 |
+
"eval_samples_per_second": 107.023,
|
| 382 |
+
"eval_steps_per_second": 13.379,
|
| 383 |
+
"step": 12500
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 1.06,
|
| 387 |
+
"learning_rate": 1.576271186440678e-05,
|
| 388 |
+
"loss": 0.3355,
|
| 389 |
+
"step": 13000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.06,
|
| 393 |
+
"eval_accuracy": 0.840855832908813,
|
| 394 |
+
"eval_loss": 0.44230031967163086,
|
| 395 |
+
"eval_runtime": 93.3849,
|
| 396 |
+
"eval_samples_per_second": 105.103,
|
| 397 |
+
"eval_steps_per_second": 13.139,
|
| 398 |
+
"step": 13000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 1.1,
|
| 402 |
+
"learning_rate": 1.5599739243807042e-05,
|
| 403 |
+
"loss": 0.3309,
|
| 404 |
+
"step": 13500
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.1,
|
| 408 |
+
"eval_accuracy": 0.8339276617422313,
|
| 409 |
+
"eval_loss": 0.4691074788570404,
|
| 410 |
+
"eval_runtime": 81.8679,
|
| 411 |
+
"eval_samples_per_second": 119.888,
|
| 412 |
+
"eval_steps_per_second": 14.988,
|
| 413 |
+
"step": 13500
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 1.14,
|
| 417 |
+
"learning_rate": 1.54367666232073e-05,
|
| 418 |
+
"loss": 0.3416,
|
| 419 |
+
"step": 14000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 1.14,
|
| 423 |
+
"eval_accuracy": 0.8397350993377484,
|
| 424 |
+
"eval_loss": 0.4406871497631073,
|
| 425 |
+
"eval_runtime": 80.3421,
|
| 426 |
+
"eval_samples_per_second": 122.165,
|
| 427 |
+
"eval_steps_per_second": 15.272,
|
| 428 |
+
"step": 14000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 1.18,
|
| 432 |
+
"learning_rate": 1.5273794002607563e-05,
|
| 433 |
+
"loss": 0.3463,
|
| 434 |
+
"step": 14500
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 1.18,
|
| 438 |
+
"eval_accuracy": 0.8371879775853286,
|
| 439 |
+
"eval_loss": 0.445261150598526,
|
| 440 |
+
"eval_runtime": 83.1773,
|
| 441 |
+
"eval_samples_per_second": 118.001,
|
| 442 |
+
"eval_steps_per_second": 14.752,
|
| 443 |
+
"step": 14500
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 1.22,
|
| 447 |
+
"learning_rate": 1.5110821382007822e-05,
|
| 448 |
+
"loss": 0.3447,
|
| 449 |
+
"step": 15000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 1.22,
|
| 453 |
+
"eval_accuracy": 0.8397350993377484,
|
| 454 |
+
"eval_loss": 0.4480521082878113,
|
| 455 |
+
"eval_runtime": 93.0739,
|
| 456 |
+
"eval_samples_per_second": 105.454,
|
| 457 |
+
"eval_steps_per_second": 13.183,
|
| 458 |
+
"step": 15000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.26,
|
| 462 |
+
"learning_rate": 1.4947848761408083e-05,
|
| 463 |
+
"loss": 0.3302,
|
| 464 |
+
"step": 15500
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 1.26,
|
| 468 |
+
"eval_accuracy": 0.8403464085583291,
|
| 469 |
+
"eval_loss": 0.462993860244751,
|
| 470 |
+
"eval_runtime": 98.4254,
|
| 471 |
+
"eval_samples_per_second": 99.72,
|
| 472 |
+
"eval_steps_per_second": 12.466,
|
| 473 |
+
"step": 15500
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 1.3,
|
| 477 |
+
"learning_rate": 1.4784876140808346e-05,
|
| 478 |
+
"loss": 0.3366,
|
| 479 |
+
"step": 16000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.3,
|
| 483 |
+
"eval_accuracy": 0.8402445236882323,
|
| 484 |
+
"eval_loss": 0.4278508424758911,
|
| 485 |
+
"eval_runtime": 80.9392,
|
| 486 |
+
"eval_samples_per_second": 121.264,
|
| 487 |
+
"eval_steps_per_second": 15.16,
|
| 488 |
+
"step": 16000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 1.34,
|
| 492 |
+
"learning_rate": 1.4621903520208606e-05,
|
| 493 |
+
"loss": 0.3446,
|
| 494 |
+
"step": 16500
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 1.34,
|
| 498 |
+
"eval_accuracy": 0.8444218033622007,
|
| 499 |
+
"eval_loss": 0.4328218996524811,
|
| 500 |
+
"eval_runtime": 88.6359,
|
| 501 |
+
"eval_samples_per_second": 110.734,
|
| 502 |
+
"eval_steps_per_second": 13.843,
|
| 503 |
+
"step": 16500
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 1.39,
|
| 507 |
+
"learning_rate": 1.4458930899608867e-05,
|
| 508 |
+
"loss": 0.3442,
|
| 509 |
+
"step": 17000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 1.39,
|
| 513 |
+
"eval_accuracy": 0.8421803362200713,
|
| 514 |
+
"eval_loss": 0.4372538924217224,
|
| 515 |
+
"eval_runtime": 90.5486,
|
| 516 |
+
"eval_samples_per_second": 108.395,
|
| 517 |
+
"eval_steps_per_second": 13.551,
|
| 518 |
+
"step": 17000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.43,
|
| 522 |
+
"learning_rate": 1.4295958279009128e-05,
|
| 523 |
+
"loss": 0.3431,
|
| 524 |
+
"step": 17500
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 1.43,
|
| 528 |
+
"eval_accuracy": 0.8425878757004585,
|
| 529 |
+
"eval_loss": 0.444231778383255,
|
| 530 |
+
"eval_runtime": 104.7466,
|
| 531 |
+
"eval_samples_per_second": 93.702,
|
| 532 |
+
"eval_steps_per_second": 11.714,
|
| 533 |
+
"step": 17500
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.47,
|
| 537 |
+
"learning_rate": 1.4132985658409388e-05,
|
| 538 |
+
"loss": 0.3388,
|
| 539 |
+
"step": 18000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 1.47,
|
| 543 |
+
"eval_accuracy": 0.8358634742740703,
|
| 544 |
+
"eval_loss": 0.4574286937713623,
|
| 545 |
+
"eval_runtime": 79.912,
|
| 546 |
+
"eval_samples_per_second": 122.823,
|
| 547 |
+
"eval_steps_per_second": 15.354,
|
| 548 |
+
"step": 18000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 1.51,
|
| 552 |
+
"learning_rate": 1.3970013037809649e-05,
|
| 553 |
+
"loss": 0.3403,
|
| 554 |
+
"step": 18500
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.51,
|
| 558 |
+
"eval_accuracy": 0.8423841059602649,
|
| 559 |
+
"eval_loss": 0.4366081953048706,
|
| 560 |
+
"eval_runtime": 80.6484,
|
| 561 |
+
"eval_samples_per_second": 121.701,
|
| 562 |
+
"eval_steps_per_second": 15.214,
|
| 563 |
+
"step": 18500
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.55,
|
| 567 |
+
"learning_rate": 1.380704041720991e-05,
|
| 568 |
+
"loss": 0.3421,
|
| 569 |
+
"step": 19000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.55,
|
| 573 |
+
"eval_accuracy": 0.8441161487519103,
|
| 574 |
+
"eval_loss": 0.4383392930030823,
|
| 575 |
+
"eval_runtime": 105.6168,
|
| 576 |
+
"eval_samples_per_second": 92.93,
|
| 577 |
+
"eval_steps_per_second": 11.617,
|
| 578 |
+
"step": 19000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 1.59,
|
| 582 |
+
"learning_rate": 1.364406779661017e-05,
|
| 583 |
+
"loss": 0.3405,
|
| 584 |
+
"step": 19500
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.59,
|
| 588 |
+
"eval_accuracy": 0.8411614875191035,
|
| 589 |
+
"eval_loss": 0.4455229938030243,
|
| 590 |
+
"eval_runtime": 99.6387,
|
| 591 |
+
"eval_samples_per_second": 98.506,
|
| 592 |
+
"eval_steps_per_second": 12.314,
|
| 593 |
+
"step": 19500
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 1.63,
|
| 597 |
+
"learning_rate": 1.3481095176010431e-05,
|
| 598 |
+
"loss": 0.3448,
|
| 599 |
+
"step": 20000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 1.63,
|
| 603 |
+
"eval_accuracy": 0.8385124808965868,
|
| 604 |
+
"eval_loss": 0.4386064112186432,
|
| 605 |
+
"eval_runtime": 86.9871,
|
| 606 |
+
"eval_samples_per_second": 112.833,
|
| 607 |
+
"eval_steps_per_second": 14.106,
|
| 608 |
+
"step": 20000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 1.67,
|
| 612 |
+
"learning_rate": 1.3318122555410693e-05,
|
| 613 |
+
"loss": 0.3346,
|
| 614 |
+
"step": 20500
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 1.67,
|
| 618 |
+
"eval_accuracy": 0.8416709118695873,
|
| 619 |
+
"eval_loss": 0.4354933500289917,
|
| 620 |
+
"eval_runtime": 90.9919,
|
| 621 |
+
"eval_samples_per_second": 107.867,
|
| 622 |
+
"eval_steps_per_second": 13.485,
|
| 623 |
+
"step": 20500
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 1.71,
|
| 627 |
+
"learning_rate": 1.3155149934810954e-05,
|
| 628 |
+
"loss": 0.3475,
|
| 629 |
+
"step": 21000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 1.71,
|
| 633 |
+
"eval_accuracy": 0.8372898624554254,
|
| 634 |
+
"eval_loss": 0.4339876174926758,
|
| 635 |
+
"eval_runtime": 89.1677,
|
| 636 |
+
"eval_samples_per_second": 110.073,
|
| 637 |
+
"eval_steps_per_second": 13.761,
|
| 638 |
+
"step": 21000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 1.75,
|
| 642 |
+
"learning_rate": 1.2992177314211213e-05,
|
| 643 |
+
"loss": 0.3378,
|
| 644 |
+
"step": 21500
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 1.75,
|
| 648 |
+
"eval_accuracy": 0.8469689251146205,
|
| 649 |
+
"eval_loss": 0.4287373125553131,
|
| 650 |
+
"eval_runtime": 93.5816,
|
| 651 |
+
"eval_samples_per_second": 104.882,
|
| 652 |
+
"eval_steps_per_second": 13.112,
|
| 653 |
+
"step": 21500
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 1.79,
|
| 657 |
+
"learning_rate": 1.2829204693611474e-05,
|
| 658 |
+
"loss": 0.3454,
|
| 659 |
+
"step": 22000
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 1.79,
|
| 663 |
+
"eval_accuracy": 0.8434029546612328,
|
| 664 |
+
"eval_loss": 0.43279626965522766,
|
| 665 |
+
"eval_runtime": 108.513,
|
| 666 |
+
"eval_samples_per_second": 90.45,
|
| 667 |
+
"eval_steps_per_second": 11.307,
|
| 668 |
+
"step": 22000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.83,
|
| 672 |
+
"learning_rate": 1.2666232073011735e-05,
|
| 673 |
+
"loss": 0.3423,
|
| 674 |
+
"step": 22500
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 1.83,
|
| 678 |
+
"eval_accuracy": 0.8433010697911361,
|
| 679 |
+
"eval_loss": 0.4425649344921112,
|
| 680 |
+
"eval_runtime": 91.9329,
|
| 681 |
+
"eval_samples_per_second": 106.763,
|
| 682 |
+
"eval_steps_per_second": 13.347,
|
| 683 |
+
"step": 22500
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.87,
|
| 687 |
+
"learning_rate": 1.2503259452411995e-05,
|
| 688 |
+
"loss": 0.3292,
|
| 689 |
+
"step": 23000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.87,
|
| 693 |
+
"eval_accuracy": 0.845236882322975,
|
| 694 |
+
"eval_loss": 0.424352765083313,
|
| 695 |
+
"eval_runtime": 101.4887,
|
| 696 |
+
"eval_samples_per_second": 96.71,
|
| 697 |
+
"eval_steps_per_second": 12.09,
|
| 698 |
+
"step": 23000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.91,
|
| 702 |
+
"learning_rate": 1.2340286831812256e-05,
|
| 703 |
+
"loss": 0.3363,
|
| 704 |
+
"step": 23500
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 1.91,
|
| 708 |
+
"eval_accuracy": 0.8494141619969434,
|
| 709 |
+
"eval_loss": 0.4183717668056488,
|
| 710 |
+
"eval_runtime": 104.207,
|
| 711 |
+
"eval_samples_per_second": 94.188,
|
| 712 |
+
"eval_steps_per_second": 11.775,
|
| 713 |
+
"step": 23500
|
| 714 |
+
}
|
| 715 |
+
],
|
| 716 |
+
"max_steps": 61360,
|
| 717 |
+
"num_train_epochs": 5,
|
| 718 |
+
"total_flos": 4.946519097615514e+16,
|
| 719 |
+
"trial_name": null,
|
| 720 |
+
"trial_params": null
|
| 721 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ba0e0d1671f8fc721ffb52e771268b5bfb02a1c629ab734077f34d6f1e75165
|
| 3 |
+
size 2927
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|