ZhangYunchenY
commited on
Commit
·
7c24058
1
Parent(s):
0d0dd81
[Model] bart-base-mnli
Browse files- config.json +76 -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 +751 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "mnli",
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "entailment",
|
| 32 |
+
"1": "neutral",
|
| 33 |
+
"2": "contradiction"
|
| 34 |
+
},
|
| 35 |
+
"init_std": 0.02,
|
| 36 |
+
"is_encoder_decoder": true,
|
| 37 |
+
"label2id": {
|
| 38 |
+
"contradiction": 2,
|
| 39 |
+
"entailment": 0,
|
| 40 |
+
"neutral": 1
|
| 41 |
+
},
|
| 42 |
+
"max_position_embeddings": 1024,
|
| 43 |
+
"model_type": "bart",
|
| 44 |
+
"no_repeat_ngram_size": 3,
|
| 45 |
+
"normalize_before": false,
|
| 46 |
+
"normalize_embedding": true,
|
| 47 |
+
"num_beams": 4,
|
| 48 |
+
"num_hidden_layers": 6,
|
| 49 |
+
"pad_token_id": 1,
|
| 50 |
+
"problem_type": "single_label_classification",
|
| 51 |
+
"scale_embedding": false,
|
| 52 |
+
"task_specific_params": {
|
| 53 |
+
"summarization": {
|
| 54 |
+
"length_penalty": 1.0,
|
| 55 |
+
"max_length": 128,
|
| 56 |
+
"min_length": 12,
|
| 57 |
+
"num_beams": 4
|
| 58 |
+
},
|
| 59 |
+
"summarization_cnn": {
|
| 60 |
+
"length_penalty": 2.0,
|
| 61 |
+
"max_length": 142,
|
| 62 |
+
"min_length": 56,
|
| 63 |
+
"num_beams": 4
|
| 64 |
+
},
|
| 65 |
+
"summarization_xsum": {
|
| 66 |
+
"length_penalty": 1.0,
|
| 67 |
+
"max_length": 62,
|
| 68 |
+
"min_length": 11,
|
| 69 |
+
"num_beams": 6
|
| 70 |
+
}
|
| 71 |
+
},
|
| 72 |
+
"torch_dtype": "float32",
|
| 73 |
+
"transformers_version": "4.16.2",
|
| 74 |
+
"use_cache": true,
|
| 75 |
+
"vocab_size": 50265
|
| 76 |
+
}
|
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:a636fceca81567feda9a97fbe87c300bda3efc94e30c8a6536c17722054d1c3b
|
| 3 |
+
size 1120272635
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:841db4a650f89881d53676f2dbb6b60d5dd535016f5df78750288d592a315d58
|
| 3 |
+
size 560157877
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5496aec79d92bec00d0d298466f9af13aa795c24cb35d010b32d5ff693480dda
|
| 3 |
+
size 14659
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95e431f1959e43f1a75113e4685ecf3b966a19950bd5c0d11a3cc24d806f0de9
|
| 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 +1,751 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 3.9928292046936114,
|
| 5 |
+
"global_step": 49000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"learning_rate": 1.9696846089836677e-05,
|
| 13 |
+
"loss": 0.7465,
|
| 14 |
+
"step": 1000
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.08,
|
| 18 |
+
"eval_accuracy": 0.7886907794192562,
|
| 19 |
+
"eval_loss": 0.5396007299423218,
|
| 20 |
+
"eval_runtime": 51.0387,
|
| 21 |
+
"eval_samples_per_second": 192.305,
|
| 22 |
+
"eval_steps_per_second": 6.015,
|
| 23 |
+
"step": 1000
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.16,
|
| 27 |
+
"learning_rate": 1.9370523258659796e-05,
|
| 28 |
+
"loss": 0.584,
|
| 29 |
+
"step": 2000
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.16,
|
| 33 |
+
"eval_accuracy": 0.8102903718797758,
|
| 34 |
+
"eval_loss": 0.4883033335208893,
|
| 35 |
+
"eval_runtime": 46.5382,
|
| 36 |
+
"eval_samples_per_second": 210.902,
|
| 37 |
+
"eval_steps_per_second": 6.597,
|
| 38 |
+
"step": 2000
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.24,
|
| 42 |
+
"learning_rate": 1.9044200427482912e-05,
|
| 43 |
+
"loss": 0.5483,
|
| 44 |
+
"step": 3000
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.24,
|
| 48 |
+
"eval_accuracy": 0.8145695364238411,
|
| 49 |
+
"eval_loss": 0.47581160068511963,
|
| 50 |
+
"eval_runtime": 46.7271,
|
| 51 |
+
"eval_samples_per_second": 210.049,
|
| 52 |
+
"eval_steps_per_second": 6.57,
|
| 53 |
+
"step": 3000
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.33,
|
| 57 |
+
"learning_rate": 1.8717877596306028e-05,
|
| 58 |
+
"loss": 0.5228,
|
| 59 |
+
"step": 4000
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.33,
|
| 63 |
+
"eval_accuracy": 0.8207845134997452,
|
| 64 |
+
"eval_loss": 0.45740216970443726,
|
| 65 |
+
"eval_runtime": 45.9826,
|
| 66 |
+
"eval_samples_per_second": 213.45,
|
| 67 |
+
"eval_steps_per_second": 6.676,
|
| 68 |
+
"step": 4000
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.41,
|
| 72 |
+
"learning_rate": 1.8391554765129143e-05,
|
| 73 |
+
"loss": 0.5012,
|
| 74 |
+
"step": 5000
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.41,
|
| 78 |
+
"eval_accuracy": 0.8290371879775853,
|
| 79 |
+
"eval_loss": 0.4382418990135193,
|
| 80 |
+
"eval_runtime": 46.0661,
|
| 81 |
+
"eval_samples_per_second": 213.063,
|
| 82 |
+
"eval_steps_per_second": 6.664,
|
| 83 |
+
"step": 5000
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.49,
|
| 87 |
+
"learning_rate": 1.8065231933952262e-05,
|
| 88 |
+
"loss": 0.4915,
|
| 89 |
+
"step": 6000
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.49,
|
| 93 |
+
"eval_accuracy": 0.8333163525216505,
|
| 94 |
+
"eval_loss": 0.4435715079307556,
|
| 95 |
+
"eval_runtime": 47.0204,
|
| 96 |
+
"eval_samples_per_second": 208.739,
|
| 97 |
+
"eval_steps_per_second": 6.529,
|
| 98 |
+
"step": 6000
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 0.57,
|
| 102 |
+
"learning_rate": 1.7738909102775378e-05,
|
| 103 |
+
"loss": 0.4858,
|
| 104 |
+
"step": 7000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.57,
|
| 108 |
+
"eval_accuracy": 0.8344370860927153,
|
| 109 |
+
"eval_loss": 0.43664801120758057,
|
| 110 |
+
"eval_runtime": 46.4417,
|
| 111 |
+
"eval_samples_per_second": 211.34,
|
| 112 |
+
"eval_steps_per_second": 6.61,
|
| 113 |
+
"step": 7000
|
| 114 |
+
},
|
| 115 |
+
{
|
| 116 |
+
"epoch": 0.65,
|
| 117 |
+
"learning_rate": 1.7412586271598494e-05,
|
| 118 |
+
"loss": 0.4766,
|
| 119 |
+
"step": 8000
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 0.65,
|
| 123 |
+
"eval_accuracy": 0.8361691288843607,
|
| 124 |
+
"eval_loss": 0.42201751470565796,
|
| 125 |
+
"eval_runtime": 47.0497,
|
| 126 |
+
"eval_samples_per_second": 208.609,
|
| 127 |
+
"eval_steps_per_second": 6.525,
|
| 128 |
+
"step": 8000
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.73,
|
| 132 |
+
"learning_rate": 1.708626344042161e-05,
|
| 133 |
+
"loss": 0.4643,
|
| 134 |
+
"step": 9000
|
| 135 |
+
},
|
| 136 |
+
{
|
| 137 |
+
"epoch": 0.73,
|
| 138 |
+
"eval_accuracy": 0.8390219052470708,
|
| 139 |
+
"eval_loss": 0.4428311586380005,
|
| 140 |
+
"eval_runtime": 46.1174,
|
| 141 |
+
"eval_samples_per_second": 212.826,
|
| 142 |
+
"eval_steps_per_second": 6.657,
|
| 143 |
+
"step": 9000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.81,
|
| 147 |
+
"learning_rate": 1.675994060924473e-05,
|
| 148 |
+
"loss": 0.4593,
|
| 149 |
+
"step": 10000
|
| 150 |
+
},
|
| 151 |
+
{
|
| 152 |
+
"epoch": 0.81,
|
| 153 |
+
"eval_accuracy": 0.8371879775853286,
|
| 154 |
+
"eval_loss": 0.43534818291664124,
|
| 155 |
+
"eval_runtime": 50.18,
|
| 156 |
+
"eval_samples_per_second": 195.596,
|
| 157 |
+
"eval_steps_per_second": 6.118,
|
| 158 |
+
"step": 10000
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 0.9,
|
| 162 |
+
"learning_rate": 1.6433617778067844e-05,
|
| 163 |
+
"loss": 0.46,
|
| 164 |
+
"step": 11000
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.9,
|
| 168 |
+
"eval_accuracy": 0.8424859908303617,
|
| 169 |
+
"eval_loss": 0.4115181863307953,
|
| 170 |
+
"eval_runtime": 53.0256,
|
| 171 |
+
"eval_samples_per_second": 185.099,
|
| 172 |
+
"eval_steps_per_second": 5.79,
|
| 173 |
+
"step": 11000
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.98,
|
| 177 |
+
"learning_rate": 1.610729494689096e-05,
|
| 178 |
+
"loss": 0.4537,
|
| 179 |
+
"step": 12000
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 0.98,
|
| 183 |
+
"eval_accuracy": 0.8446255731023943,
|
| 184 |
+
"eval_loss": 0.4107950031757355,
|
| 185 |
+
"eval_runtime": 46.5601,
|
| 186 |
+
"eval_samples_per_second": 210.803,
|
| 187 |
+
"eval_steps_per_second": 6.594,
|
| 188 |
+
"step": 12000
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 1.06,
|
| 192 |
+
"learning_rate": 1.5780972115714076e-05,
|
| 193 |
+
"loss": 0.3982,
|
| 194 |
+
"step": 13000
|
| 195 |
+
},
|
| 196 |
+
{
|
| 197 |
+
"epoch": 1.06,
|
| 198 |
+
"eval_accuracy": 0.8461538461538461,
|
| 199 |
+
"eval_loss": 0.4335910677909851,
|
| 200 |
+
"eval_runtime": 47.058,
|
| 201 |
+
"eval_samples_per_second": 208.572,
|
| 202 |
+
"eval_steps_per_second": 6.524,
|
| 203 |
+
"step": 13000
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 1.14,
|
| 207 |
+
"learning_rate": 1.545464928453719e-05,
|
| 208 |
+
"loss": 0.3781,
|
| 209 |
+
"step": 14000
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 1.14,
|
| 213 |
+
"eval_accuracy": 0.8492103922567499,
|
| 214 |
+
"eval_loss": 0.4207431674003601,
|
| 215 |
+
"eval_runtime": 46.2518,
|
| 216 |
+
"eval_samples_per_second": 212.208,
|
| 217 |
+
"eval_steps_per_second": 6.638,
|
| 218 |
+
"step": 14000
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 1.22,
|
| 222 |
+
"learning_rate": 1.512832645336031e-05,
|
| 223 |
+
"loss": 0.3871,
|
| 224 |
+
"step": 15000
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 1.22,
|
| 228 |
+
"eval_accuracy": 0.8451349974528782,
|
| 229 |
+
"eval_loss": 0.4314253032207489,
|
| 230 |
+
"eval_runtime": 46.2026,
|
| 231 |
+
"eval_samples_per_second": 212.434,
|
| 232 |
+
"eval_steps_per_second": 6.645,
|
| 233 |
+
"step": 15000
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 1.3,
|
| 237 |
+
"learning_rate": 1.4802003622183428e-05,
|
| 238 |
+
"loss": 0.3789,
|
| 239 |
+
"step": 16000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 1.3,
|
| 243 |
+
"eval_accuracy": 0.8504330106979113,
|
| 244 |
+
"eval_loss": 0.3989640772342682,
|
| 245 |
+
"eval_runtime": 46.611,
|
| 246 |
+
"eval_samples_per_second": 210.572,
|
| 247 |
+
"eval_steps_per_second": 6.586,
|
| 248 |
+
"step": 16000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 1.39,
|
| 252 |
+
"learning_rate": 1.4475680791006544e-05,
|
| 253 |
+
"loss": 0.3848,
|
| 254 |
+
"step": 17000
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 1.39,
|
| 258 |
+
"eval_accuracy": 0.8482934284258787,
|
| 259 |
+
"eval_loss": 0.4063809812068939,
|
| 260 |
+
"eval_runtime": 46.0252,
|
| 261 |
+
"eval_samples_per_second": 213.253,
|
| 262 |
+
"eval_steps_per_second": 6.67,
|
| 263 |
+
"step": 17000
|
| 264 |
+
},
|
| 265 |
+
{
|
| 266 |
+
"epoch": 1.47,
|
| 267 |
+
"learning_rate": 1.4149357959829661e-05,
|
| 268 |
+
"loss": 0.3771,
|
| 269 |
+
"step": 18000
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 1.47,
|
| 273 |
+
"eval_accuracy": 0.8446255731023943,
|
| 274 |
+
"eval_loss": 0.43143340945243835,
|
| 275 |
+
"eval_runtime": 46.514,
|
| 276 |
+
"eval_samples_per_second": 211.012,
|
| 277 |
+
"eval_steps_per_second": 6.6,
|
| 278 |
+
"step": 18000
|
| 279 |
+
},
|
| 280 |
+
{
|
| 281 |
+
"epoch": 1.55,
|
| 282 |
+
"learning_rate": 1.3823035128652777e-05,
|
| 283 |
+
"loss": 0.3754,
|
| 284 |
+
"step": 19000
|
| 285 |
+
},
|
| 286 |
+
{
|
| 287 |
+
"epoch": 1.55,
|
| 288 |
+
"eval_accuracy": 0.8511462047885889,
|
| 289 |
+
"eval_loss": 0.4237792193889618,
|
| 290 |
+
"eval_runtime": 47.005,
|
| 291 |
+
"eval_samples_per_second": 208.808,
|
| 292 |
+
"eval_steps_per_second": 6.531,
|
| 293 |
+
"step": 19000
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"epoch": 1.63,
|
| 297 |
+
"learning_rate": 1.3496712297475893e-05,
|
| 298 |
+
"loss": 0.378,
|
| 299 |
+
"step": 20000
|
| 300 |
+
},
|
| 301 |
+
{
|
| 302 |
+
"epoch": 1.63,
|
| 303 |
+
"eval_accuracy": 0.8496179317371371,
|
| 304 |
+
"eval_loss": 0.4224611818790436,
|
| 305 |
+
"eval_runtime": 46.124,
|
| 306 |
+
"eval_samples_per_second": 212.796,
|
| 307 |
+
"eval_steps_per_second": 6.656,
|
| 308 |
+
"step": 20000
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 1.71,
|
| 312 |
+
"learning_rate": 1.3170389466299012e-05,
|
| 313 |
+
"loss": 0.3747,
|
| 314 |
+
"step": 21000
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 1.71,
|
| 318 |
+
"eval_accuracy": 0.8504330106979113,
|
| 319 |
+
"eval_loss": 0.39967572689056396,
|
| 320 |
+
"eval_runtime": 45.9739,
|
| 321 |
+
"eval_samples_per_second": 213.49,
|
| 322 |
+
"eval_steps_per_second": 6.678,
|
| 323 |
+
"step": 21000
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 1.79,
|
| 327 |
+
"learning_rate": 1.2844066635122128e-05,
|
| 328 |
+
"loss": 0.3715,
|
| 329 |
+
"step": 22000
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 1.79,
|
| 333 |
+
"eval_accuracy": 0.8466632705043301,
|
| 334 |
+
"eval_loss": 0.42271146178245544,
|
| 335 |
+
"eval_runtime": 46.4472,
|
| 336 |
+
"eval_samples_per_second": 211.315,
|
| 337 |
+
"eval_steps_per_second": 6.61,
|
| 338 |
+
"step": 22000
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 1.87,
|
| 342 |
+
"learning_rate": 1.2517743803945243e-05,
|
| 343 |
+
"loss": 0.369,
|
| 344 |
+
"step": 23000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 1.87,
|
| 348 |
+
"eval_accuracy": 0.8543046357615894,
|
| 349 |
+
"eval_loss": 0.3938461244106293,
|
| 350 |
+
"eval_runtime": 47.3838,
|
| 351 |
+
"eval_samples_per_second": 207.138,
|
| 352 |
+
"eval_steps_per_second": 6.479,
|
| 353 |
+
"step": 23000
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 1.96,
|
| 357 |
+
"learning_rate": 1.2191420972768359e-05,
|
| 358 |
+
"loss": 0.3645,
|
| 359 |
+
"step": 24000
|
| 360 |
+
},
|
| 361 |
+
{
|
| 362 |
+
"epoch": 1.96,
|
| 363 |
+
"eval_accuracy": 0.8500254712175241,
|
| 364 |
+
"eval_loss": 0.41426172852516174,
|
| 365 |
+
"eval_runtime": 45.9093,
|
| 366 |
+
"eval_samples_per_second": 213.791,
|
| 367 |
+
"eval_steps_per_second": 6.687,
|
| 368 |
+
"step": 24000
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 2.04,
|
| 372 |
+
"learning_rate": 1.1865098141591478e-05,
|
| 373 |
+
"loss": 0.3413,
|
| 374 |
+
"step": 25000
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 2.04,
|
| 378 |
+
"eval_accuracy": 0.8531839021905248,
|
| 379 |
+
"eval_loss": 0.43976131081581116,
|
| 380 |
+
"eval_runtime": 46.649,
|
| 381 |
+
"eval_samples_per_second": 210.401,
|
| 382 |
+
"eval_steps_per_second": 6.581,
|
| 383 |
+
"step": 25000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 2.12,
|
| 387 |
+
"learning_rate": 1.1538775310414594e-05,
|
| 388 |
+
"loss": 0.3014,
|
| 389 |
+
"step": 26000
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 2.12,
|
| 393 |
+
"eval_accuracy": 0.8570555272542028,
|
| 394 |
+
"eval_loss": 0.4210617244243622,
|
| 395 |
+
"eval_runtime": 46.539,
|
| 396 |
+
"eval_samples_per_second": 210.898,
|
| 397 |
+
"eval_steps_per_second": 6.597,
|
| 398 |
+
"step": 26000
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 2.2,
|
| 402 |
+
"learning_rate": 1.121245247923771e-05,
|
| 403 |
+
"loss": 0.2941,
|
| 404 |
+
"step": 27000
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 2.2,
|
| 408 |
+
"eval_accuracy": 0.8554253693326541,
|
| 409 |
+
"eval_loss": 0.43391153216362,
|
| 410 |
+
"eval_runtime": 46.5124,
|
| 411 |
+
"eval_samples_per_second": 211.019,
|
| 412 |
+
"eval_steps_per_second": 6.6,
|
| 413 |
+
"step": 27000
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 2.28,
|
| 417 |
+
"learning_rate": 1.0886129648060829e-05,
|
| 418 |
+
"loss": 0.2979,
|
| 419 |
+
"step": 28000
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 2.28,
|
| 423 |
+
"eval_accuracy": 0.8607233825776872,
|
| 424 |
+
"eval_loss": 0.42420682311058044,
|
| 425 |
+
"eval_runtime": 147.2489,
|
| 426 |
+
"eval_samples_per_second": 66.656,
|
| 427 |
+
"eval_steps_per_second": 2.085,
|
| 428 |
+
"step": 28000
|
| 429 |
+
},
|
| 430 |
+
{
|
| 431 |
+
"epoch": 2.36,
|
| 432 |
+
"learning_rate": 1.0559806816883944e-05,
|
| 433 |
+
"loss": 0.3056,
|
| 434 |
+
"step": 29000
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"epoch": 2.36,
|
| 438 |
+
"eval_accuracy": 0.8541008660213958,
|
| 439 |
+
"eval_loss": 0.4425140619277954,
|
| 440 |
+
"eval_runtime": 46.1358,
|
| 441 |
+
"eval_samples_per_second": 212.741,
|
| 442 |
+
"eval_steps_per_second": 6.654,
|
| 443 |
+
"step": 29000
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 2.44,
|
| 447 |
+
"learning_rate": 1.023348398570706e-05,
|
| 448 |
+
"loss": 0.2953,
|
| 449 |
+
"step": 30000
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 2.44,
|
| 453 |
+
"eval_accuracy": 0.8592969943963321,
|
| 454 |
+
"eval_loss": 0.41613587737083435,
|
| 455 |
+
"eval_runtime": 47.1744,
|
| 456 |
+
"eval_samples_per_second": 208.058,
|
| 457 |
+
"eval_steps_per_second": 6.508,
|
| 458 |
+
"step": 30000
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 2.53,
|
| 462 |
+
"learning_rate": 9.907161154530178e-06,
|
| 463 |
+
"loss": 0.2935,
|
| 464 |
+
"step": 31000
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 2.53,
|
| 468 |
+
"eval_accuracy": 0.8588894549159449,
|
| 469 |
+
"eval_loss": 0.4042932987213135,
|
| 470 |
+
"eval_runtime": 46.2425,
|
| 471 |
+
"eval_samples_per_second": 212.251,
|
| 472 |
+
"eval_steps_per_second": 6.639,
|
| 473 |
+
"step": 31000
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 2.61,
|
| 477 |
+
"learning_rate": 9.580838323353295e-06,
|
| 478 |
+
"loss": 0.3018,
|
| 479 |
+
"step": 32000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 2.61,
|
| 483 |
+
"eval_accuracy": 0.8497198166072338,
|
| 484 |
+
"eval_loss": 0.4361600875854492,
|
| 485 |
+
"eval_runtime": 45.7305,
|
| 486 |
+
"eval_samples_per_second": 214.627,
|
| 487 |
+
"eval_steps_per_second": 6.713,
|
| 488 |
+
"step": 32000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 2.69,
|
| 492 |
+
"learning_rate": 9.25451549217641e-06,
|
| 493 |
+
"loss": 0.3046,
|
| 494 |
+
"step": 33000
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 2.69,
|
| 498 |
+
"eval_accuracy": 0.8528782475802343,
|
| 499 |
+
"eval_loss": 0.43105748295783997,
|
| 500 |
+
"eval_runtime": 47.0154,
|
| 501 |
+
"eval_samples_per_second": 208.761,
|
| 502 |
+
"eval_steps_per_second": 6.53,
|
| 503 |
+
"step": 33000
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 2.77,
|
| 507 |
+
"learning_rate": 8.928192660999528e-06,
|
| 508 |
+
"loss": 0.2982,
|
| 509 |
+
"step": 34000
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 2.77,
|
| 513 |
+
"eval_accuracy": 0.8610290371879776,
|
| 514 |
+
"eval_loss": 0.40264639258384705,
|
| 515 |
+
"eval_runtime": 46.7153,
|
| 516 |
+
"eval_samples_per_second": 210.103,
|
| 517 |
+
"eval_steps_per_second": 6.572,
|
| 518 |
+
"step": 34000
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 2.85,
|
| 522 |
+
"learning_rate": 8.601869829822644e-06,
|
| 523 |
+
"loss": 0.2983,
|
| 524 |
+
"step": 35000
|
| 525 |
+
},
|
| 526 |
+
{
|
| 527 |
+
"epoch": 2.85,
|
| 528 |
+
"eval_accuracy": 0.856444218033622,
|
| 529 |
+
"eval_loss": 0.40915054082870483,
|
| 530 |
+
"eval_runtime": 46.1785,
|
| 531 |
+
"eval_samples_per_second": 212.545,
|
| 532 |
+
"eval_steps_per_second": 6.648,
|
| 533 |
+
"step": 35000
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 2.93,
|
| 537 |
+
"learning_rate": 8.275546998645761e-06,
|
| 538 |
+
"loss": 0.2987,
|
| 539 |
+
"step": 36000
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 2.93,
|
| 543 |
+
"eval_accuracy": 0.8551197147223637,
|
| 544 |
+
"eval_loss": 0.41256535053253174,
|
| 545 |
+
"eval_runtime": 46.0319,
|
| 546 |
+
"eval_samples_per_second": 213.222,
|
| 547 |
+
"eval_steps_per_second": 6.669,
|
| 548 |
+
"step": 36000
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 3.01,
|
| 552 |
+
"learning_rate": 7.949224167468877e-06,
|
| 553 |
+
"loss": 0.2893,
|
| 554 |
+
"step": 37000
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 3.01,
|
| 558 |
+
"eval_accuracy": 0.8574630667345899,
|
| 559 |
+
"eval_loss": 0.45308130979537964,
|
| 560 |
+
"eval_runtime": 46.1413,
|
| 561 |
+
"eval_samples_per_second": 212.716,
|
| 562 |
+
"eval_steps_per_second": 6.653,
|
| 563 |
+
"step": 37000
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 3.1,
|
| 567 |
+
"learning_rate": 7.622901336291994e-06,
|
| 568 |
+
"loss": 0.2413,
|
| 569 |
+
"step": 38000
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 3.1,
|
| 573 |
+
"eval_accuracy": 0.8611309220580744,
|
| 574 |
+
"eval_loss": 0.44799548387527466,
|
| 575 |
+
"eval_runtime": 45.9836,
|
| 576 |
+
"eval_samples_per_second": 213.446,
|
| 577 |
+
"eval_steps_per_second": 6.676,
|
| 578 |
+
"step": 38000
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 3.18,
|
| 582 |
+
"learning_rate": 7.296578505115111e-06,
|
| 583 |
+
"loss": 0.2376,
|
| 584 |
+
"step": 39000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 3.18,
|
| 588 |
+
"eval_accuracy": 0.8607233825776872,
|
| 589 |
+
"eval_loss": 0.4475202262401581,
|
| 590 |
+
"eval_runtime": 45.5836,
|
| 591 |
+
"eval_samples_per_second": 215.319,
|
| 592 |
+
"eval_steps_per_second": 6.735,
|
| 593 |
+
"step": 39000
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 3.26,
|
| 597 |
+
"learning_rate": 6.9702556739382275e-06,
|
| 598 |
+
"loss": 0.2399,
|
| 599 |
+
"step": 40000
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 3.26,
|
| 603 |
+
"eval_accuracy": 0.8579724910850739,
|
| 604 |
+
"eval_loss": 0.4466216266155243,
|
| 605 |
+
"eval_runtime": 48.0904,
|
| 606 |
+
"eval_samples_per_second": 204.095,
|
| 607 |
+
"eval_steps_per_second": 6.384,
|
| 608 |
+
"step": 40000
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 3.34,
|
| 612 |
+
"learning_rate": 6.643932842761345e-06,
|
| 613 |
+
"loss": 0.2411,
|
| 614 |
+
"step": 41000
|
| 615 |
+
},
|
| 616 |
+
{
|
| 617 |
+
"epoch": 3.34,
|
| 618 |
+
"eval_accuracy": 0.8579724910850739,
|
| 619 |
+
"eval_loss": 0.44625383615493774,
|
| 620 |
+
"eval_runtime": 46.3779,
|
| 621 |
+
"eval_samples_per_second": 211.631,
|
| 622 |
+
"eval_steps_per_second": 6.62,
|
| 623 |
+
"step": 41000
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 3.42,
|
| 627 |
+
"learning_rate": 6.317610011584461e-06,
|
| 628 |
+
"loss": 0.2461,
|
| 629 |
+
"step": 42000
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 3.42,
|
| 633 |
+
"eval_accuracy": 0.8574630667345899,
|
| 634 |
+
"eval_loss": 0.45237523317337036,
|
| 635 |
+
"eval_runtime": 46.2979,
|
| 636 |
+
"eval_samples_per_second": 211.997,
|
| 637 |
+
"eval_steps_per_second": 6.631,
|
| 638 |
+
"step": 42000
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 3.5,
|
| 642 |
+
"learning_rate": 5.991287180407578e-06,
|
| 643 |
+
"loss": 0.2433,
|
| 644 |
+
"step": 43000
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 3.5,
|
| 648 |
+
"eval_accuracy": 0.8600101884870097,
|
| 649 |
+
"eval_loss": 0.4503074884414673,
|
| 650 |
+
"eval_runtime": 46.049,
|
| 651 |
+
"eval_samples_per_second": 213.143,
|
| 652 |
+
"eval_steps_per_second": 6.667,
|
| 653 |
+
"step": 43000
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 3.59,
|
| 657 |
+
"learning_rate": 5.664964349230695e-06,
|
| 658 |
+
"loss": 0.2427,
|
| 659 |
+
"step": 44000
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 3.59,
|
| 663 |
+
"eval_accuracy": 0.8616403464085584,
|
| 664 |
+
"eval_loss": 0.4240187704563141,
|
| 665 |
+
"eval_runtime": 46.0142,
|
| 666 |
+
"eval_samples_per_second": 213.304,
|
| 667 |
+
"eval_steps_per_second": 6.672,
|
| 668 |
+
"step": 44000
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 3.67,
|
| 672 |
+
"learning_rate": 5.338641518053811e-06,
|
| 673 |
+
"loss": 0.2354,
|
| 674 |
+
"step": 45000
|
| 675 |
+
},
|
| 676 |
+
{
|
| 677 |
+
"epoch": 3.67,
|
| 678 |
+
"eval_accuracy": 0.8609271523178808,
|
| 679 |
+
"eval_loss": 0.42988237738609314,
|
| 680 |
+
"eval_runtime": 46.9338,
|
| 681 |
+
"eval_samples_per_second": 209.125,
|
| 682 |
+
"eval_steps_per_second": 6.541,
|
| 683 |
+
"step": 45000
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 3.75,
|
| 687 |
+
"learning_rate": 5.012318686876928e-06,
|
| 688 |
+
"loss": 0.2401,
|
| 689 |
+
"step": 46000
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 3.75,
|
| 693 |
+
"eval_accuracy": 0.8600101884870097,
|
| 694 |
+
"eval_loss": 0.4482932388782501,
|
| 695 |
+
"eval_runtime": 46.836,
|
| 696 |
+
"eval_samples_per_second": 209.561,
|
| 697 |
+
"eval_steps_per_second": 6.555,
|
| 698 |
+
"step": 46000
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 3.83,
|
| 702 |
+
"learning_rate": 4.685995855700044e-06,
|
| 703 |
+
"loss": 0.2396,
|
| 704 |
+
"step": 47000
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 3.83,
|
| 708 |
+
"eval_accuracy": 0.8579724910850739,
|
| 709 |
+
"eval_loss": 0.4487365782260895,
|
| 710 |
+
"eval_runtime": 47.4992,
|
| 711 |
+
"eval_samples_per_second": 206.635,
|
| 712 |
+
"eval_steps_per_second": 6.463,
|
| 713 |
+
"step": 47000
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 3.91,
|
| 717 |
+
"learning_rate": 4.359673024523161e-06,
|
| 718 |
+
"loss": 0.2327,
|
| 719 |
+
"step": 48000
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 3.91,
|
| 723 |
+
"eval_accuracy": 0.8613346917982679,
|
| 724 |
+
"eval_loss": 0.4441225230693817,
|
| 725 |
+
"eval_runtime": 46.3347,
|
| 726 |
+
"eval_samples_per_second": 211.828,
|
| 727 |
+
"eval_steps_per_second": 6.626,
|
| 728 |
+
"step": 48000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 3.99,
|
| 732 |
+
"learning_rate": 4.0333501933462775e-06,
|
| 733 |
+
"loss": 0.2336,
|
| 734 |
+
"step": 49000
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 3.99,
|
| 738 |
+
"eval_accuracy": 0.8644931227712684,
|
| 739 |
+
"eval_loss": 0.4395711421966553,
|
| 740 |
+
"eval_runtime": 47.7718,
|
| 741 |
+
"eval_samples_per_second": 205.456,
|
| 742 |
+
"eval_steps_per_second": 6.426,
|
| 743 |
+
"step": 49000
|
| 744 |
+
}
|
| 745 |
+
],
|
| 746 |
+
"max_steps": 61360,
|
| 747 |
+
"num_train_epochs": 5,
|
| 748 |
+
"total_flos": 1.2022186898599373e+17,
|
| 749 |
+
"trial_name": null,
|
| 750 |
+
"trial_params": null
|
| 751 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c063beffa5629baa9fe8e38412f704068d6a4c30a34c5cc70d4866f81fac8eb5
|
| 3 |
+
size 2991
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|