ZhangYunchenY
commited on
Commit
·
de15264
1
Parent(s):
f205f75
[Model] bart-base-sst2
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 +901 -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": "sst2",
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "negative",
|
| 32 |
+
"1": "positive"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"negative": 0,
|
| 38 |
+
"positive": 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 sha256:7691083da663882dc13cef10ee60da6de916d387d448735e30c18f332b4cdffd
|
| 3 |
+
size 1120266491
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afc59a91d576043096ffd7e8b485fcf16535595cdf53d845c4ac674f8449f50c
|
| 3 |
+
size 560154805
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5d8da2bdbfddaa83aa94722059b19d38ce6c7ce79a305250c599f89b17034c24
|
| 3 |
+
size 14659
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:747ae5ba86616b53feff7e5521a7aa379393eb27a5054827d5d5dfa6e81d75a2
|
| 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 +1,901 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 8.788598574821853,
|
| 5 |
+
"global_step": 18500,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.1,
|
| 12 |
+
"learning_rate": 1.980997624703088e-05,
|
| 13 |
+
"loss": 0.4065,
|
| 14 |
+
"step": 200
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.19,
|
| 18 |
+
"learning_rate": 1.961995249406176e-05,
|
| 19 |
+
"loss": 0.3019,
|
| 20 |
+
"step": 400
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.24,
|
| 24 |
+
"eval_accuracy": 0.9059633027522935,
|
| 25 |
+
"eval_loss": 0.26677730679512024,
|
| 26 |
+
"eval_runtime": 5.719,
|
| 27 |
+
"eval_samples_per_second": 152.475,
|
| 28 |
+
"eval_steps_per_second": 4.896,
|
| 29 |
+
"step": 500
|
| 30 |
+
},
|
| 31 |
+
{
|
| 32 |
+
"epoch": 0.29,
|
| 33 |
+
"learning_rate": 1.9429928741092638e-05,
|
| 34 |
+
"loss": 0.2873,
|
| 35 |
+
"step": 600
|
| 36 |
+
},
|
| 37 |
+
{
|
| 38 |
+
"epoch": 0.38,
|
| 39 |
+
"learning_rate": 1.9239904988123516e-05,
|
| 40 |
+
"loss": 0.2756,
|
| 41 |
+
"step": 800
|
| 42 |
+
},
|
| 43 |
+
{
|
| 44 |
+
"epoch": 0.48,
|
| 45 |
+
"learning_rate": 1.9049881235154395e-05,
|
| 46 |
+
"loss": 0.2514,
|
| 47 |
+
"step": 1000
|
| 48 |
+
},
|
| 49 |
+
{
|
| 50 |
+
"epoch": 0.48,
|
| 51 |
+
"eval_accuracy": 0.9220183486238532,
|
| 52 |
+
"eval_loss": 0.20395953953266144,
|
| 53 |
+
"eval_runtime": 4.9214,
|
| 54 |
+
"eval_samples_per_second": 177.184,
|
| 55 |
+
"eval_steps_per_second": 5.689,
|
| 56 |
+
"step": 1000
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.57,
|
| 60 |
+
"learning_rate": 1.8859857482185277e-05,
|
| 61 |
+
"loss": 0.2292,
|
| 62 |
+
"step": 1200
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.67,
|
| 66 |
+
"learning_rate": 1.8669833729216152e-05,
|
| 67 |
+
"loss": 0.2223,
|
| 68 |
+
"step": 1400
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.71,
|
| 72 |
+
"eval_accuracy": 0.9254587155963303,
|
| 73 |
+
"eval_loss": 0.20957307517528534,
|
| 74 |
+
"eval_runtime": 9.3475,
|
| 75 |
+
"eval_samples_per_second": 93.287,
|
| 76 |
+
"eval_steps_per_second": 2.995,
|
| 77 |
+
"step": 1500
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 0.76,
|
| 81 |
+
"learning_rate": 1.847980997624703e-05,
|
| 82 |
+
"loss": 0.2206,
|
| 83 |
+
"step": 1600
|
| 84 |
+
},
|
| 85 |
+
{
|
| 86 |
+
"epoch": 0.86,
|
| 87 |
+
"learning_rate": 1.8289786223277913e-05,
|
| 88 |
+
"loss": 0.2177,
|
| 89 |
+
"step": 1800
|
| 90 |
+
},
|
| 91 |
+
{
|
| 92 |
+
"epoch": 0.95,
|
| 93 |
+
"learning_rate": 1.809976247030879e-05,
|
| 94 |
+
"loss": 0.2141,
|
| 95 |
+
"step": 2000
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.95,
|
| 99 |
+
"eval_accuracy": 0.9197247706422018,
|
| 100 |
+
"eval_loss": 0.21411468088626862,
|
| 101 |
+
"eval_runtime": 5.5585,
|
| 102 |
+
"eval_samples_per_second": 156.877,
|
| 103 |
+
"eval_steps_per_second": 5.037,
|
| 104 |
+
"step": 2000
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 1.05,
|
| 108 |
+
"learning_rate": 1.790973871733967e-05,
|
| 109 |
+
"loss": 0.191,
|
| 110 |
+
"step": 2200
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 1.14,
|
| 114 |
+
"learning_rate": 1.7719714964370545e-05,
|
| 115 |
+
"loss": 0.1615,
|
| 116 |
+
"step": 2400
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 1.19,
|
| 120 |
+
"eval_accuracy": 0.9277522935779816,
|
| 121 |
+
"eval_loss": 0.23593279719352722,
|
| 122 |
+
"eval_runtime": 6.3221,
|
| 123 |
+
"eval_samples_per_second": 137.929,
|
| 124 |
+
"eval_steps_per_second": 4.429,
|
| 125 |
+
"step": 2500
|
| 126 |
+
},
|
| 127 |
+
{
|
| 128 |
+
"epoch": 1.24,
|
| 129 |
+
"learning_rate": 1.7529691211401427e-05,
|
| 130 |
+
"loss": 0.1598,
|
| 131 |
+
"step": 2600
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 1.33,
|
| 135 |
+
"learning_rate": 1.7339667458432306e-05,
|
| 136 |
+
"loss": 0.1513,
|
| 137 |
+
"step": 2800
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"epoch": 1.43,
|
| 141 |
+
"learning_rate": 1.7149643705463184e-05,
|
| 142 |
+
"loss": 0.1696,
|
| 143 |
+
"step": 3000
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 1.43,
|
| 147 |
+
"eval_accuracy": 0.9277522935779816,
|
| 148 |
+
"eval_loss": 0.22338584065437317,
|
| 149 |
+
"eval_runtime": 4.5931,
|
| 150 |
+
"eval_samples_per_second": 189.852,
|
| 151 |
+
"eval_steps_per_second": 6.096,
|
| 152 |
+
"step": 3000
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 1.52,
|
| 156 |
+
"learning_rate": 1.6959619952494063e-05,
|
| 157 |
+
"loss": 0.1598,
|
| 158 |
+
"step": 3200
|
| 159 |
+
},
|
| 160 |
+
{
|
| 161 |
+
"epoch": 1.62,
|
| 162 |
+
"learning_rate": 1.676959619952494e-05,
|
| 163 |
+
"loss": 0.1704,
|
| 164 |
+
"step": 3400
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 1.66,
|
| 168 |
+
"eval_accuracy": 0.926605504587156,
|
| 169 |
+
"eval_loss": 0.20875951647758484,
|
| 170 |
+
"eval_runtime": 5.0919,
|
| 171 |
+
"eval_samples_per_second": 171.251,
|
| 172 |
+
"eval_steps_per_second": 5.499,
|
| 173 |
+
"step": 3500
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 1.71,
|
| 177 |
+
"learning_rate": 1.657957244655582e-05,
|
| 178 |
+
"loss": 0.1584,
|
| 179 |
+
"step": 3600
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"epoch": 1.81,
|
| 183 |
+
"learning_rate": 1.63895486935867e-05,
|
| 184 |
+
"loss": 0.171,
|
| 185 |
+
"step": 3800
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 1.9,
|
| 189 |
+
"learning_rate": 1.6199524940617578e-05,
|
| 190 |
+
"loss": 0.1443,
|
| 191 |
+
"step": 4000
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 1.9,
|
| 195 |
+
"eval_accuracy": 0.9288990825688074,
|
| 196 |
+
"eval_loss": 0.22995886206626892,
|
| 197 |
+
"eval_runtime": 5.7731,
|
| 198 |
+
"eval_samples_per_second": 151.046,
|
| 199 |
+
"eval_steps_per_second": 4.85,
|
| 200 |
+
"step": 4000
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 2.0,
|
| 204 |
+
"learning_rate": 1.6009501187648456e-05,
|
| 205 |
+
"loss": 0.1498,
|
| 206 |
+
"step": 4200
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 2.09,
|
| 210 |
+
"learning_rate": 1.5819477434679335e-05,
|
| 211 |
+
"loss": 0.1212,
|
| 212 |
+
"step": 4400
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 2.14,
|
| 216 |
+
"eval_accuracy": 0.9311926605504587,
|
| 217 |
+
"eval_loss": 0.25349077582359314,
|
| 218 |
+
"eval_runtime": 4.9282,
|
| 219 |
+
"eval_samples_per_second": 176.941,
|
| 220 |
+
"eval_steps_per_second": 5.682,
|
| 221 |
+
"step": 4500
|
| 222 |
+
},
|
| 223 |
+
{
|
| 224 |
+
"epoch": 2.19,
|
| 225 |
+
"learning_rate": 1.5629453681710217e-05,
|
| 226 |
+
"loss": 0.133,
|
| 227 |
+
"step": 4600
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 2.28,
|
| 231 |
+
"learning_rate": 1.5439429928741095e-05,
|
| 232 |
+
"loss": 0.1213,
|
| 233 |
+
"step": 4800
|
| 234 |
+
},
|
| 235 |
+
{
|
| 236 |
+
"epoch": 2.38,
|
| 237 |
+
"learning_rate": 1.5249406175771972e-05,
|
| 238 |
+
"loss": 0.1283,
|
| 239 |
+
"step": 5000
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 2.38,
|
| 243 |
+
"eval_accuracy": 0.9277522935779816,
|
| 244 |
+
"eval_loss": 0.2518787384033203,
|
| 245 |
+
"eval_runtime": 6.251,
|
| 246 |
+
"eval_samples_per_second": 139.497,
|
| 247 |
+
"eval_steps_per_second": 4.479,
|
| 248 |
+
"step": 5000
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 2.47,
|
| 252 |
+
"learning_rate": 1.5059382422802851e-05,
|
| 253 |
+
"loss": 0.12,
|
| 254 |
+
"step": 5200
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 2.57,
|
| 258 |
+
"learning_rate": 1.4869358669833731e-05,
|
| 259 |
+
"loss": 0.1313,
|
| 260 |
+
"step": 5400
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 2.61,
|
| 264 |
+
"eval_accuracy": 0.9094036697247706,
|
| 265 |
+
"eval_loss": 0.3524125814437866,
|
| 266 |
+
"eval_runtime": 5.7105,
|
| 267 |
+
"eval_samples_per_second": 152.701,
|
| 268 |
+
"eval_steps_per_second": 4.903,
|
| 269 |
+
"step": 5500
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 2.66,
|
| 273 |
+
"learning_rate": 1.467933491686461e-05,
|
| 274 |
+
"loss": 0.1196,
|
| 275 |
+
"step": 5600
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 2.76,
|
| 279 |
+
"learning_rate": 1.4489311163895487e-05,
|
| 280 |
+
"loss": 0.123,
|
| 281 |
+
"step": 5800
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 2.85,
|
| 285 |
+
"learning_rate": 1.4299287410926367e-05,
|
| 286 |
+
"loss": 0.1304,
|
| 287 |
+
"step": 6000
|
| 288 |
+
},
|
| 289 |
+
{
|
| 290 |
+
"epoch": 2.85,
|
| 291 |
+
"eval_accuracy": 0.9243119266055045,
|
| 292 |
+
"eval_loss": 0.24740684032440186,
|
| 293 |
+
"eval_runtime": 11.1285,
|
| 294 |
+
"eval_samples_per_second": 78.357,
|
| 295 |
+
"eval_steps_per_second": 2.516,
|
| 296 |
+
"step": 6000
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 2.95,
|
| 300 |
+
"learning_rate": 1.4109263657957246e-05,
|
| 301 |
+
"loss": 0.1248,
|
| 302 |
+
"step": 6200
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 3.04,
|
| 306 |
+
"learning_rate": 1.3919239904988124e-05,
|
| 307 |
+
"loss": 0.1061,
|
| 308 |
+
"step": 6400
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 3.09,
|
| 312 |
+
"eval_accuracy": 0.9231651376146789,
|
| 313 |
+
"eval_loss": 0.2941964566707611,
|
| 314 |
+
"eval_runtime": 8.2674,
|
| 315 |
+
"eval_samples_per_second": 105.475,
|
| 316 |
+
"eval_steps_per_second": 3.387,
|
| 317 |
+
"step": 6500
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 3.14,
|
| 321 |
+
"learning_rate": 1.3729216152019003e-05,
|
| 322 |
+
"loss": 0.0876,
|
| 323 |
+
"step": 6600
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"epoch": 3.23,
|
| 327 |
+
"learning_rate": 1.3539192399049883e-05,
|
| 328 |
+
"loss": 0.0922,
|
| 329 |
+
"step": 6800
|
| 330 |
+
},
|
| 331 |
+
{
|
| 332 |
+
"epoch": 3.33,
|
| 333 |
+
"learning_rate": 1.3349168646080762e-05,
|
| 334 |
+
"loss": 0.0988,
|
| 335 |
+
"step": 7000
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 3.33,
|
| 339 |
+
"eval_accuracy": 0.9311926605504587,
|
| 340 |
+
"eval_loss": 0.2566107213497162,
|
| 341 |
+
"eval_runtime": 6.2677,
|
| 342 |
+
"eval_samples_per_second": 139.127,
|
| 343 |
+
"eval_steps_per_second": 4.467,
|
| 344 |
+
"step": 7000
|
| 345 |
+
},
|
| 346 |
+
{
|
| 347 |
+
"epoch": 3.42,
|
| 348 |
+
"learning_rate": 1.3159144893111639e-05,
|
| 349 |
+
"loss": 0.1097,
|
| 350 |
+
"step": 7200
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"epoch": 3.52,
|
| 354 |
+
"learning_rate": 1.296912114014252e-05,
|
| 355 |
+
"loss": 0.0938,
|
| 356 |
+
"step": 7400
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 3.56,
|
| 360 |
+
"eval_accuracy": 0.930045871559633,
|
| 361 |
+
"eval_loss": 0.31746456027030945,
|
| 362 |
+
"eval_runtime": 4.983,
|
| 363 |
+
"eval_samples_per_second": 174.994,
|
| 364 |
+
"eval_steps_per_second": 5.619,
|
| 365 |
+
"step": 7500
|
| 366 |
+
},
|
| 367 |
+
{
|
| 368 |
+
"epoch": 3.61,
|
| 369 |
+
"learning_rate": 1.2779097387173398e-05,
|
| 370 |
+
"loss": 0.1079,
|
| 371 |
+
"step": 7600
|
| 372 |
+
},
|
| 373 |
+
{
|
| 374 |
+
"epoch": 3.71,
|
| 375 |
+
"learning_rate": 1.2589073634204277e-05,
|
| 376 |
+
"loss": 0.1023,
|
| 377 |
+
"step": 7800
|
| 378 |
+
},
|
| 379 |
+
{
|
| 380 |
+
"epoch": 3.8,
|
| 381 |
+
"learning_rate": 1.2399049881235155e-05,
|
| 382 |
+
"loss": 0.1015,
|
| 383 |
+
"step": 8000
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 3.8,
|
| 387 |
+
"eval_accuracy": 0.9311926605504587,
|
| 388 |
+
"eval_loss": 0.3047061264514923,
|
| 389 |
+
"eval_runtime": 5.0268,
|
| 390 |
+
"eval_samples_per_second": 173.471,
|
| 391 |
+
"eval_steps_per_second": 5.57,
|
| 392 |
+
"step": 8000
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 3.9,
|
| 396 |
+
"learning_rate": 1.2209026128266036e-05,
|
| 397 |
+
"loss": 0.1076,
|
| 398 |
+
"step": 8200
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 3.99,
|
| 402 |
+
"learning_rate": 1.2019002375296912e-05,
|
| 403 |
+
"loss": 0.1103,
|
| 404 |
+
"step": 8400
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 4.04,
|
| 408 |
+
"eval_accuracy": 0.9277522935779816,
|
| 409 |
+
"eval_loss": 0.34547296166419983,
|
| 410 |
+
"eval_runtime": 6.2445,
|
| 411 |
+
"eval_samples_per_second": 139.642,
|
| 412 |
+
"eval_steps_per_second": 4.484,
|
| 413 |
+
"step": 8500
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 4.09,
|
| 417 |
+
"learning_rate": 1.1828978622327791e-05,
|
| 418 |
+
"loss": 0.0766,
|
| 419 |
+
"step": 8600
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 4.18,
|
| 423 |
+
"learning_rate": 1.1638954869358671e-05,
|
| 424 |
+
"loss": 0.0778,
|
| 425 |
+
"step": 8800
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 4.28,
|
| 429 |
+
"learning_rate": 1.144893111638955e-05,
|
| 430 |
+
"loss": 0.0841,
|
| 431 |
+
"step": 9000
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 4.28,
|
| 435 |
+
"eval_accuracy": 0.9185779816513762,
|
| 436 |
+
"eval_loss": 0.37421032786369324,
|
| 437 |
+
"eval_runtime": 5.4233,
|
| 438 |
+
"eval_samples_per_second": 160.787,
|
| 439 |
+
"eval_steps_per_second": 5.163,
|
| 440 |
+
"step": 9000
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 4.37,
|
| 444 |
+
"learning_rate": 1.1258907363420429e-05,
|
| 445 |
+
"loss": 0.0774,
|
| 446 |
+
"step": 9200
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 4.47,
|
| 450 |
+
"learning_rate": 1.1068883610451307e-05,
|
| 451 |
+
"loss": 0.0839,
|
| 452 |
+
"step": 9400
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 4.51,
|
| 456 |
+
"eval_accuracy": 0.9220183486238532,
|
| 457 |
+
"eval_loss": 0.3504032492637634,
|
| 458 |
+
"eval_runtime": 6.6438,
|
| 459 |
+
"eval_samples_per_second": 131.249,
|
| 460 |
+
"eval_steps_per_second": 4.214,
|
| 461 |
+
"step": 9500
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 4.56,
|
| 465 |
+
"learning_rate": 1.0878859857482188e-05,
|
| 466 |
+
"loss": 0.0857,
|
| 467 |
+
"step": 9600
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 4.66,
|
| 471 |
+
"learning_rate": 1.0688836104513065e-05,
|
| 472 |
+
"loss": 0.091,
|
| 473 |
+
"step": 9800
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 4.75,
|
| 477 |
+
"learning_rate": 1.0498812351543943e-05,
|
| 478 |
+
"loss": 0.0858,
|
| 479 |
+
"step": 10000
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 4.75,
|
| 483 |
+
"eval_accuracy": 0.9288990825688074,
|
| 484 |
+
"eval_loss": 0.2815171778202057,
|
| 485 |
+
"eval_runtime": 4.9169,
|
| 486 |
+
"eval_samples_per_second": 177.347,
|
| 487 |
+
"eval_steps_per_second": 5.695,
|
| 488 |
+
"step": 10000
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 4.85,
|
| 492 |
+
"learning_rate": 1.0308788598574823e-05,
|
| 493 |
+
"loss": 0.0852,
|
| 494 |
+
"step": 10200
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 4.94,
|
| 498 |
+
"learning_rate": 1.0118764845605702e-05,
|
| 499 |
+
"loss": 0.0897,
|
| 500 |
+
"step": 10400
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 4.99,
|
| 504 |
+
"eval_accuracy": 0.9220183486238532,
|
| 505 |
+
"eval_loss": 0.3205639123916626,
|
| 506 |
+
"eval_runtime": 7.2765,
|
| 507 |
+
"eval_samples_per_second": 119.839,
|
| 508 |
+
"eval_steps_per_second": 3.848,
|
| 509 |
+
"step": 10500
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 5.04,
|
| 513 |
+
"learning_rate": 9.92874109263658e-06,
|
| 514 |
+
"loss": 0.076,
|
| 515 |
+
"step": 10600
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 5.13,
|
| 519 |
+
"learning_rate": 9.73871733966746e-06,
|
| 520 |
+
"loss": 0.067,
|
| 521 |
+
"step": 10800
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 5.23,
|
| 525 |
+
"learning_rate": 9.548693586698338e-06,
|
| 526 |
+
"loss": 0.0641,
|
| 527 |
+
"step": 11000
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 5.23,
|
| 531 |
+
"eval_accuracy": 0.9334862385321101,
|
| 532 |
+
"eval_loss": 0.32430100440979004,
|
| 533 |
+
"eval_runtime": 5.6582,
|
| 534 |
+
"eval_samples_per_second": 154.113,
|
| 535 |
+
"eval_steps_per_second": 4.949,
|
| 536 |
+
"step": 11000
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 5.32,
|
| 540 |
+
"learning_rate": 9.358669833729217e-06,
|
| 541 |
+
"loss": 0.0657,
|
| 542 |
+
"step": 11200
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 5.42,
|
| 546 |
+
"learning_rate": 9.168646080760095e-06,
|
| 547 |
+
"loss": 0.0758,
|
| 548 |
+
"step": 11400
|
| 549 |
+
},
|
| 550 |
+
{
|
| 551 |
+
"epoch": 5.46,
|
| 552 |
+
"eval_accuracy": 0.9311926605504587,
|
| 553 |
+
"eval_loss": 0.29846712946891785,
|
| 554 |
+
"eval_runtime": 4.9813,
|
| 555 |
+
"eval_samples_per_second": 175.054,
|
| 556 |
+
"eval_steps_per_second": 5.621,
|
| 557 |
+
"step": 11500
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 5.51,
|
| 561 |
+
"learning_rate": 8.978622327790974e-06,
|
| 562 |
+
"loss": 0.0705,
|
| 563 |
+
"step": 11600
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 5.61,
|
| 567 |
+
"learning_rate": 8.788598574821854e-06,
|
| 568 |
+
"loss": 0.065,
|
| 569 |
+
"step": 11800
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 5.7,
|
| 573 |
+
"learning_rate": 8.598574821852733e-06,
|
| 574 |
+
"loss": 0.0744,
|
| 575 |
+
"step": 12000
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 5.7,
|
| 579 |
+
"eval_accuracy": 0.9151376146788991,
|
| 580 |
+
"eval_loss": 0.35644832253456116,
|
| 581 |
+
"eval_runtime": 5.3372,
|
| 582 |
+
"eval_samples_per_second": 163.382,
|
| 583 |
+
"eval_steps_per_second": 5.246,
|
| 584 |
+
"step": 12000
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 5.8,
|
| 588 |
+
"learning_rate": 8.408551068883611e-06,
|
| 589 |
+
"loss": 0.07,
|
| 590 |
+
"step": 12200
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 5.89,
|
| 594 |
+
"learning_rate": 8.21852731591449e-06,
|
| 595 |
+
"loss": 0.0735,
|
| 596 |
+
"step": 12400
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 5.94,
|
| 600 |
+
"eval_accuracy": 0.9220183486238532,
|
| 601 |
+
"eval_loss": 0.36781516671180725,
|
| 602 |
+
"eval_runtime": 5.0223,
|
| 603 |
+
"eval_samples_per_second": 173.627,
|
| 604 |
+
"eval_steps_per_second": 5.575,
|
| 605 |
+
"step": 12500
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 5.99,
|
| 609 |
+
"learning_rate": 8.028503562945369e-06,
|
| 610 |
+
"loss": 0.0683,
|
| 611 |
+
"step": 12600
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 6.08,
|
| 615 |
+
"learning_rate": 7.838479809976247e-06,
|
| 616 |
+
"loss": 0.0519,
|
| 617 |
+
"step": 12800
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 6.18,
|
| 621 |
+
"learning_rate": 7.648456057007126e-06,
|
| 622 |
+
"loss": 0.0581,
|
| 623 |
+
"step": 13000
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 6.18,
|
| 627 |
+
"eval_accuracy": 0.9323394495412844,
|
| 628 |
+
"eval_loss": 0.3235052824020386,
|
| 629 |
+
"eval_runtime": 5.3353,
|
| 630 |
+
"eval_samples_per_second": 163.439,
|
| 631 |
+
"eval_steps_per_second": 5.248,
|
| 632 |
+
"step": 13000
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 6.27,
|
| 636 |
+
"learning_rate": 7.458432304038005e-06,
|
| 637 |
+
"loss": 0.0575,
|
| 638 |
+
"step": 13200
|
| 639 |
+
},
|
| 640 |
+
{
|
| 641 |
+
"epoch": 6.37,
|
| 642 |
+
"learning_rate": 7.268408551068884e-06,
|
| 643 |
+
"loss": 0.0605,
|
| 644 |
+
"step": 13400
|
| 645 |
+
},
|
| 646 |
+
{
|
| 647 |
+
"epoch": 6.41,
|
| 648 |
+
"eval_accuracy": 0.9254587155963303,
|
| 649 |
+
"eval_loss": 0.3677641451358795,
|
| 650 |
+
"eval_runtime": 4.1548,
|
| 651 |
+
"eval_samples_per_second": 209.877,
|
| 652 |
+
"eval_steps_per_second": 6.739,
|
| 653 |
+
"step": 13500
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 6.46,
|
| 657 |
+
"learning_rate": 7.0783847980997635e-06,
|
| 658 |
+
"loss": 0.0548,
|
| 659 |
+
"step": 13600
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 6.56,
|
| 663 |
+
"learning_rate": 6.888361045130641e-06,
|
| 664 |
+
"loss": 0.054,
|
| 665 |
+
"step": 13800
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 6.65,
|
| 669 |
+
"learning_rate": 6.698337292161521e-06,
|
| 670 |
+
"loss": 0.0608,
|
| 671 |
+
"step": 14000
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 6.65,
|
| 675 |
+
"eval_accuracy": 0.9231651376146789,
|
| 676 |
+
"eval_loss": 0.35537707805633545,
|
| 677 |
+
"eval_runtime": 5.0168,
|
| 678 |
+
"eval_samples_per_second": 173.816,
|
| 679 |
+
"eval_steps_per_second": 5.581,
|
| 680 |
+
"step": 14000
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 6.75,
|
| 684 |
+
"learning_rate": 6.508313539192399e-06,
|
| 685 |
+
"loss": 0.0589,
|
| 686 |
+
"step": 14200
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 6.84,
|
| 690 |
+
"learning_rate": 6.318289786223278e-06,
|
| 691 |
+
"loss": 0.055,
|
| 692 |
+
"step": 14400
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 6.89,
|
| 696 |
+
"eval_accuracy": 0.9277522935779816,
|
| 697 |
+
"eval_loss": 0.3431534171104431,
|
| 698 |
+
"eval_runtime": 5.9333,
|
| 699 |
+
"eval_samples_per_second": 146.968,
|
| 700 |
+
"eval_steps_per_second": 4.719,
|
| 701 |
+
"step": 14500
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 6.94,
|
| 705 |
+
"learning_rate": 6.1282660332541575e-06,
|
| 706 |
+
"loss": 0.062,
|
| 707 |
+
"step": 14600
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 7.03,
|
| 711 |
+
"learning_rate": 5.938242280285036e-06,
|
| 712 |
+
"loss": 0.0571,
|
| 713 |
+
"step": 14800
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 7.13,
|
| 717 |
+
"learning_rate": 5.748218527315916e-06,
|
| 718 |
+
"loss": 0.0498,
|
| 719 |
+
"step": 15000
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 7.13,
|
| 723 |
+
"eval_accuracy": 0.9288990825688074,
|
| 724 |
+
"eval_loss": 0.3633643090724945,
|
| 725 |
+
"eval_runtime": 4.8896,
|
| 726 |
+
"eval_samples_per_second": 178.339,
|
| 727 |
+
"eval_steps_per_second": 5.726,
|
| 728 |
+
"step": 15000
|
| 729 |
+
},
|
| 730 |
+
{
|
| 731 |
+
"epoch": 7.22,
|
| 732 |
+
"learning_rate": 5.558194774346793e-06,
|
| 733 |
+
"loss": 0.0569,
|
| 734 |
+
"step": 15200
|
| 735 |
+
},
|
| 736 |
+
{
|
| 737 |
+
"epoch": 7.32,
|
| 738 |
+
"learning_rate": 5.368171021377673e-06,
|
| 739 |
+
"loss": 0.0531,
|
| 740 |
+
"step": 15400
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 7.36,
|
| 744 |
+
"eval_accuracy": 0.9277522935779816,
|
| 745 |
+
"eval_loss": 0.34541434049606323,
|
| 746 |
+
"eval_runtime": 5.4179,
|
| 747 |
+
"eval_samples_per_second": 160.949,
|
| 748 |
+
"eval_steps_per_second": 5.168,
|
| 749 |
+
"step": 15500
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 7.41,
|
| 753 |
+
"learning_rate": 5.178147268408551e-06,
|
| 754 |
+
"loss": 0.0501,
|
| 755 |
+
"step": 15600
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 7.51,
|
| 759 |
+
"learning_rate": 4.98812351543943e-06,
|
| 760 |
+
"loss": 0.0501,
|
| 761 |
+
"step": 15800
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 7.6,
|
| 765 |
+
"learning_rate": 4.798099762470309e-06,
|
| 766 |
+
"loss": 0.0521,
|
| 767 |
+
"step": 16000
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 7.6,
|
| 771 |
+
"eval_accuracy": 0.9243119266055045,
|
| 772 |
+
"eval_loss": 0.3439008593559265,
|
| 773 |
+
"eval_runtime": 4.9353,
|
| 774 |
+
"eval_samples_per_second": 176.685,
|
| 775 |
+
"eval_steps_per_second": 5.673,
|
| 776 |
+
"step": 16000
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 7.7,
|
| 780 |
+
"learning_rate": 4.608076009501188e-06,
|
| 781 |
+
"loss": 0.0452,
|
| 782 |
+
"step": 16200
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 7.79,
|
| 786 |
+
"learning_rate": 4.418052256532067e-06,
|
| 787 |
+
"loss": 0.0481,
|
| 788 |
+
"step": 16400
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 7.84,
|
| 792 |
+
"eval_accuracy": 0.9254587155963303,
|
| 793 |
+
"eval_loss": 0.36306628584861755,
|
| 794 |
+
"eval_runtime": 5.8137,
|
| 795 |
+
"eval_samples_per_second": 149.99,
|
| 796 |
+
"eval_steps_per_second": 4.816,
|
| 797 |
+
"step": 16500
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 7.89,
|
| 801 |
+
"learning_rate": 4.228028503562946e-06,
|
| 802 |
+
"loss": 0.0514,
|
| 803 |
+
"step": 16600
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 7.98,
|
| 807 |
+
"learning_rate": 4.038004750593825e-06,
|
| 808 |
+
"loss": 0.0486,
|
| 809 |
+
"step": 16800
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 8.08,
|
| 813 |
+
"learning_rate": 3.8479809976247036e-06,
|
| 814 |
+
"loss": 0.0386,
|
| 815 |
+
"step": 17000
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 8.08,
|
| 819 |
+
"eval_accuracy": 0.930045871559633,
|
| 820 |
+
"eval_loss": 0.37118515372276306,
|
| 821 |
+
"eval_runtime": 6.6001,
|
| 822 |
+
"eval_samples_per_second": 132.12,
|
| 823 |
+
"eval_steps_per_second": 4.242,
|
| 824 |
+
"step": 17000
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 8.17,
|
| 828 |
+
"learning_rate": 3.657957244655582e-06,
|
| 829 |
+
"loss": 0.036,
|
| 830 |
+
"step": 17200
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 8.27,
|
| 834 |
+
"learning_rate": 3.467933491686461e-06,
|
| 835 |
+
"loss": 0.0399,
|
| 836 |
+
"step": 17400
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 8.31,
|
| 840 |
+
"eval_accuracy": 0.9346330275229358,
|
| 841 |
+
"eval_loss": 0.3605540692806244,
|
| 842 |
+
"eval_runtime": 5.1639,
|
| 843 |
+
"eval_samples_per_second": 168.866,
|
| 844 |
+
"eval_steps_per_second": 5.422,
|
| 845 |
+
"step": 17500
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 8.36,
|
| 849 |
+
"learning_rate": 3.27790973871734e-06,
|
| 850 |
+
"loss": 0.0436,
|
| 851 |
+
"step": 17600
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 8.46,
|
| 855 |
+
"learning_rate": 3.0878859857482185e-06,
|
| 856 |
+
"loss": 0.0417,
|
| 857 |
+
"step": 17800
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 8.55,
|
| 861 |
+
"learning_rate": 2.897862232779098e-06,
|
| 862 |
+
"loss": 0.048,
|
| 863 |
+
"step": 18000
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 8.55,
|
| 867 |
+
"eval_accuracy": 0.9380733944954128,
|
| 868 |
+
"eval_loss": 0.3584529757499695,
|
| 869 |
+
"eval_runtime": 5.8003,
|
| 870 |
+
"eval_samples_per_second": 150.337,
|
| 871 |
+
"eval_steps_per_second": 4.827,
|
| 872 |
+
"step": 18000
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 8.65,
|
| 876 |
+
"learning_rate": 2.7078384798099766e-06,
|
| 877 |
+
"loss": 0.0384,
|
| 878 |
+
"step": 18200
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 8.74,
|
| 882 |
+
"learning_rate": 2.5178147268408552e-06,
|
| 883 |
+
"loss": 0.0522,
|
| 884 |
+
"step": 18400
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 8.79,
|
| 888 |
+
"eval_accuracy": 0.9334862385321101,
|
| 889 |
+
"eval_loss": 0.337113618850708,
|
| 890 |
+
"eval_runtime": 5.4571,
|
| 891 |
+
"eval_samples_per_second": 159.791,
|
| 892 |
+
"eval_steps_per_second": 5.131,
|
| 893 |
+
"step": 18500
|
| 894 |
+
}
|
| 895 |
+
],
|
| 896 |
+
"max_steps": 21050,
|
| 897 |
+
"num_train_epochs": 10,
|
| 898 |
+
"total_flos": 4.538296624748544e+16,
|
| 899 |
+
"trial_name": null,
|
| 900 |
+
"trial_params": null
|
| 901 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3710f21d166d379b2367b3df014954a82ba55fb2396cc31733d9c6634f5c7e5e
|
| 3 |
+
size 2991
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|