Training in progress, step 1250, checkpoint
Browse files- checkpoint-1250/config.json +39 -0
- checkpoint-1250/merges.txt +0 -0
- checkpoint-1250/optimizer.pt +3 -0
- checkpoint-1250/pytorch_model.bin +3 -0
- checkpoint-1250/rng_state.pth +3 -0
- checkpoint-1250/scheduler.pt +3 -0
- checkpoint-1250/special_tokens_map.json +15 -0
- checkpoint-1250/tokenizer.json +0 -0
- checkpoint-1250/tokenizer_config.json +57 -0
- checkpoint-1250/trainer_state.json +994 -0
- checkpoint-1250/training_args.bin +3 -0
- checkpoint-1250/vocab.json +0 -0
checkpoint-1250/config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "roberta-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"RobertaForSentimentClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"finetuning_task": "text-classification",
|
| 11 |
+
"hidden_act": "gelu",
|
| 12 |
+
"hidden_dropout_prob": 0.1,
|
| 13 |
+
"hidden_size": 768,
|
| 14 |
+
"id2label": {
|
| 15 |
+
"0": "0",
|
| 16 |
+
"1": "1",
|
| 17 |
+
"2": "2"
|
| 18 |
+
},
|
| 19 |
+
"initializer_range": 0.02,
|
| 20 |
+
"intermediate_size": 3072,
|
| 21 |
+
"label2id": {
|
| 22 |
+
"0": 0,
|
| 23 |
+
"1": 1,
|
| 24 |
+
"2": 2
|
| 25 |
+
},
|
| 26 |
+
"layer_norm_eps": 1e-05,
|
| 27 |
+
"max_position_embeddings": 514,
|
| 28 |
+
"model_type": "roberta",
|
| 29 |
+
"num_attention_heads": 12,
|
| 30 |
+
"num_hidden_layers": 12,
|
| 31 |
+
"pad_token_id": 1,
|
| 32 |
+
"position_embedding_type": "absolute",
|
| 33 |
+
"problem_type": "single_label_classification",
|
| 34 |
+
"torch_dtype": "float32",
|
| 35 |
+
"transformers_version": "4.34.1",
|
| 36 |
+
"type_vocab_size": 1,
|
| 37 |
+
"use_cache": true,
|
| 38 |
+
"vocab_size": 50265
|
| 39 |
+
}
|
checkpoint-1250/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1250/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:665db088a85a485c27f77bc079e1c94eff8d50a4e596622a4592cbf41dcf98be
|
| 3 |
+
size 997351674
|
checkpoint-1250/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cef61f3c0c9e11be2d387de7fe889e301f9df905dd31f5b0cb8e95174c9dc6b
|
| 3 |
+
size 498661166
|
checkpoint-1250/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f5f5e1352165edc12f92e0e750bb6d15292faaa25e87779b1ca57ff6b99efcc
|
| 3 |
+
size 14244
|
checkpoint-1250/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d9841a5eab4d226e0a6b69b7626b364cfdc065402ac7dbedc667e570ff5a2397
|
| 3 |
+
size 1064
|
checkpoint-1250/special_tokens_map.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"cls_token": "<s>",
|
| 4 |
+
"eos_token": "</s>",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "<mask>",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"pad_token": "<pad>",
|
| 13 |
+
"sep_token": "</s>",
|
| 14 |
+
"unk_token": "<unk>"
|
| 15 |
+
}
|
checkpoint-1250/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-1250/tokenizer_config.json
ADDED
|
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"1": {
|
| 13 |
+
"content": "<pad>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"2": {
|
| 21 |
+
"content": "</s>",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"3": {
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"50264": {
|
| 37 |
+
"content": "<mask>",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
+
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"errors": "replace",
|
| 50 |
+
"mask_token": "<mask>",
|
| 51 |
+
"model_max_length": 512,
|
| 52 |
+
"pad_token": "<pad>",
|
| 53 |
+
"sep_token": "</s>",
|
| 54 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 55 |
+
"trim_offsets": true,
|
| 56 |
+
"unk_token": "<unk>"
|
| 57 |
+
}
|
checkpoint-1250/trainer_state.json
ADDED
|
@@ -0,0 +1,994 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9405568096313017,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 1250,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 5e-07,
|
| 14 |
+
"loss": 1.1001,
|
| 15 |
+
"step": 10
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.02,
|
| 19 |
+
"learning_rate": 1e-06,
|
| 20 |
+
"loss": 1.0661,
|
| 21 |
+
"step": 20
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 1.5e-06,
|
| 26 |
+
"loss": 1.0782,
|
| 27 |
+
"step": 30
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.03,
|
| 31 |
+
"learning_rate": 2e-06,
|
| 32 |
+
"loss": 1.0578,
|
| 33 |
+
"step": 40
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.04,
|
| 37 |
+
"learning_rate": 2.5e-06,
|
| 38 |
+
"loss": 1.0395,
|
| 39 |
+
"step": 50
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.04,
|
| 43 |
+
"eval_accuracy": 0.4754781102152329,
|
| 44 |
+
"eval_loss": 1.0322505235671997,
|
| 45 |
+
"eval_runtime": 49.5848,
|
| 46 |
+
"eval_samples_per_second": 605.307,
|
| 47 |
+
"eval_steps_per_second": 1.19,
|
| 48 |
+
"step": 50
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"epoch": 0.05,
|
| 52 |
+
"learning_rate": 3e-06,
|
| 53 |
+
"loss": 1.0308,
|
| 54 |
+
"step": 60
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 0.05,
|
| 58 |
+
"learning_rate": 3.5e-06,
|
| 59 |
+
"loss": 1.0044,
|
| 60 |
+
"step": 70
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.06,
|
| 64 |
+
"learning_rate": 4e-06,
|
| 65 |
+
"loss": 1.0398,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.07,
|
| 70 |
+
"learning_rate": 4.5e-06,
|
| 71 |
+
"loss": 1.0116,
|
| 72 |
+
"step": 90
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.08,
|
| 76 |
+
"learning_rate": 5e-06,
|
| 77 |
+
"loss": 1.0067,
|
| 78 |
+
"step": 100
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.08,
|
| 82 |
+
"eval_accuracy": 0.5313187179316319,
|
| 83 |
+
"eval_loss": 0.9863238334655762,
|
| 84 |
+
"eval_runtime": 49.2356,
|
| 85 |
+
"eval_samples_per_second": 609.599,
|
| 86 |
+
"eval_steps_per_second": 1.198,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.08,
|
| 91 |
+
"learning_rate": 5.5e-06,
|
| 92 |
+
"loss": 1.0131,
|
| 93 |
+
"step": 110
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09,
|
| 97 |
+
"learning_rate": 6e-06,
|
| 98 |
+
"loss": 1.0235,
|
| 99 |
+
"step": 120
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.1,
|
| 103 |
+
"learning_rate": 6.5e-06,
|
| 104 |
+
"loss": 1.0073,
|
| 105 |
+
"step": 130
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.11,
|
| 109 |
+
"learning_rate": 7e-06,
|
| 110 |
+
"loss": 0.9856,
|
| 111 |
+
"step": 140
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.11,
|
| 115 |
+
"learning_rate": 7.5e-06,
|
| 116 |
+
"loss": 1.0062,
|
| 117 |
+
"step": 150
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.11,
|
| 121 |
+
"eval_accuracy": 0.5358499366962084,
|
| 122 |
+
"eval_loss": 0.9735665917396545,
|
| 123 |
+
"eval_runtime": 49.4568,
|
| 124 |
+
"eval_samples_per_second": 606.874,
|
| 125 |
+
"eval_steps_per_second": 1.193,
|
| 126 |
+
"step": 150
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"epoch": 0.12,
|
| 130 |
+
"learning_rate": 8e-06,
|
| 131 |
+
"loss": 0.9622,
|
| 132 |
+
"step": 160
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"epoch": 0.13,
|
| 136 |
+
"learning_rate": 8.500000000000002e-06,
|
| 137 |
+
"loss": 0.9583,
|
| 138 |
+
"step": 170
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.14,
|
| 142 |
+
"learning_rate": 9e-06,
|
| 143 |
+
"loss": 0.987,
|
| 144 |
+
"step": 180
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.14,
|
| 148 |
+
"learning_rate": 9.5e-06,
|
| 149 |
+
"loss": 0.9995,
|
| 150 |
+
"step": 190
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.15,
|
| 154 |
+
"learning_rate": 1e-05,
|
| 155 |
+
"loss": 0.9953,
|
| 156 |
+
"step": 200
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.15,
|
| 160 |
+
"eval_accuracy": 0.5406476977410541,
|
| 161 |
+
"eval_loss": 0.9847397804260254,
|
| 162 |
+
"eval_runtime": 49.5469,
|
| 163 |
+
"eval_samples_per_second": 605.769,
|
| 164 |
+
"eval_steps_per_second": 1.191,
|
| 165 |
+
"step": 200
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.16,
|
| 169 |
+
"learning_rate": 1.0500000000000001e-05,
|
| 170 |
+
"loss": 0.9894,
|
| 171 |
+
"step": 210
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.17,
|
| 175 |
+
"learning_rate": 1.1e-05,
|
| 176 |
+
"loss": 0.9857,
|
| 177 |
+
"step": 220
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.17,
|
| 181 |
+
"learning_rate": 1.15e-05,
|
| 182 |
+
"loss": 0.9806,
|
| 183 |
+
"step": 230
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.18,
|
| 187 |
+
"learning_rate": 1.2e-05,
|
| 188 |
+
"loss": 0.9802,
|
| 189 |
+
"step": 240
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.19,
|
| 193 |
+
"learning_rate": 1.25e-05,
|
| 194 |
+
"loss": 0.9559,
|
| 195 |
+
"step": 250
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.19,
|
| 199 |
+
"eval_accuracy": 0.5136269740787632,
|
| 200 |
+
"eval_loss": 1.0206754207611084,
|
| 201 |
+
"eval_runtime": 49.5108,
|
| 202 |
+
"eval_samples_per_second": 606.212,
|
| 203 |
+
"eval_steps_per_second": 1.192,
|
| 204 |
+
"step": 250
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.2,
|
| 208 |
+
"learning_rate": 1.3e-05,
|
| 209 |
+
"loss": 0.9877,
|
| 210 |
+
"step": 260
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.2,
|
| 214 |
+
"learning_rate": 1.35e-05,
|
| 215 |
+
"loss": 0.9878,
|
| 216 |
+
"step": 270
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.21,
|
| 220 |
+
"learning_rate": 1.4e-05,
|
| 221 |
+
"loss": 0.9646,
|
| 222 |
+
"step": 280
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"epoch": 0.22,
|
| 226 |
+
"learning_rate": 1.4500000000000002e-05,
|
| 227 |
+
"loss": 0.9598,
|
| 228 |
+
"step": 290
|
| 229 |
+
},
|
| 230 |
+
{
|
| 231 |
+
"epoch": 0.23,
|
| 232 |
+
"learning_rate": 1.5e-05,
|
| 233 |
+
"loss": 0.9567,
|
| 234 |
+
"step": 300
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.23,
|
| 238 |
+
"eval_accuracy": 0.5693676284400613,
|
| 239 |
+
"eval_loss": 0.9298574924468994,
|
| 240 |
+
"eval_runtime": 49.5798,
|
| 241 |
+
"eval_samples_per_second": 605.367,
|
| 242 |
+
"eval_steps_per_second": 1.19,
|
| 243 |
+
"step": 300
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.23,
|
| 247 |
+
"learning_rate": 1.55e-05,
|
| 248 |
+
"loss": 0.9659,
|
| 249 |
+
"step": 310
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.24,
|
| 253 |
+
"learning_rate": 1.6e-05,
|
| 254 |
+
"loss": 0.9803,
|
| 255 |
+
"step": 320
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.25,
|
| 259 |
+
"learning_rate": 1.65e-05,
|
| 260 |
+
"loss": 0.959,
|
| 261 |
+
"step": 330
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.26,
|
| 265 |
+
"learning_rate": 1.7000000000000003e-05,
|
| 266 |
+
"loss": 0.9298,
|
| 267 |
+
"step": 340
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.26,
|
| 271 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 272 |
+
"loss": 0.8923,
|
| 273 |
+
"step": 350
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.26,
|
| 277 |
+
"eval_accuracy": 0.603285133604318,
|
| 278 |
+
"eval_loss": 0.8731092810630798,
|
| 279 |
+
"eval_runtime": 49.5126,
|
| 280 |
+
"eval_samples_per_second": 606.189,
|
| 281 |
+
"eval_steps_per_second": 1.192,
|
| 282 |
+
"step": 350
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.27,
|
| 286 |
+
"learning_rate": 1.8e-05,
|
| 287 |
+
"loss": 0.9255,
|
| 288 |
+
"step": 360
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.28,
|
| 292 |
+
"learning_rate": 1.85e-05,
|
| 293 |
+
"loss": 0.9567,
|
| 294 |
+
"step": 370
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 0.29,
|
| 298 |
+
"learning_rate": 1.9e-05,
|
| 299 |
+
"loss": 0.9135,
|
| 300 |
+
"step": 380
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"epoch": 0.29,
|
| 304 |
+
"learning_rate": 1.95e-05,
|
| 305 |
+
"loss": 0.8978,
|
| 306 |
+
"step": 390
|
| 307 |
+
},
|
| 308 |
+
{
|
| 309 |
+
"epoch": 0.3,
|
| 310 |
+
"learning_rate": 2e-05,
|
| 311 |
+
"loss": 0.9617,
|
| 312 |
+
"step": 400
|
| 313 |
+
},
|
| 314 |
+
{
|
| 315 |
+
"epoch": 0.3,
|
| 316 |
+
"eval_accuracy": 0.5401479309655494,
|
| 317 |
+
"eval_loss": 0.9500759840011597,
|
| 318 |
+
"eval_runtime": 49.5248,
|
| 319 |
+
"eval_samples_per_second": 606.04,
|
| 320 |
+
"eval_steps_per_second": 1.191,
|
| 321 |
+
"step": 400
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.31,
|
| 325 |
+
"learning_rate": 2.05e-05,
|
| 326 |
+
"loss": 0.9387,
|
| 327 |
+
"step": 410
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.32,
|
| 331 |
+
"learning_rate": 2.1000000000000002e-05,
|
| 332 |
+
"loss": 0.8832,
|
| 333 |
+
"step": 420
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.32,
|
| 337 |
+
"learning_rate": 2.1499999999999997e-05,
|
| 338 |
+
"loss": 0.9087,
|
| 339 |
+
"step": 430
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.33,
|
| 343 |
+
"learning_rate": 2.2e-05,
|
| 344 |
+
"loss": 0.9192,
|
| 345 |
+
"step": 440
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.34,
|
| 349 |
+
"learning_rate": 2.2499999999999998e-05,
|
| 350 |
+
"loss": 0.8456,
|
| 351 |
+
"step": 450
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.34,
|
| 355 |
+
"eval_accuracy": 0.6245085626707536,
|
| 356 |
+
"eval_loss": 0.8298193216323853,
|
| 357 |
+
"eval_runtime": 49.5226,
|
| 358 |
+
"eval_samples_per_second": 606.066,
|
| 359 |
+
"eval_steps_per_second": 1.191,
|
| 360 |
+
"step": 450
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.35,
|
| 364 |
+
"learning_rate": 2.3e-05,
|
| 365 |
+
"loss": 0.8511,
|
| 366 |
+
"step": 460
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.35,
|
| 370 |
+
"learning_rate": 2.3500000000000002e-05,
|
| 371 |
+
"loss": 0.9211,
|
| 372 |
+
"step": 470
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.36,
|
| 376 |
+
"learning_rate": 2.4e-05,
|
| 377 |
+
"loss": 0.8416,
|
| 378 |
+
"step": 480
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.37,
|
| 382 |
+
"learning_rate": 2.4500000000000003e-05,
|
| 383 |
+
"loss": 0.849,
|
| 384 |
+
"step": 490
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.38,
|
| 388 |
+
"learning_rate": 2.5e-05,
|
| 389 |
+
"loss": 0.8098,
|
| 390 |
+
"step": 500
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.38,
|
| 394 |
+
"eval_accuracy": 0.6523622309588859,
|
| 395 |
+
"eval_loss": 0.771039605140686,
|
| 396 |
+
"eval_runtime": 49.4859,
|
| 397 |
+
"eval_samples_per_second": 606.517,
|
| 398 |
+
"eval_steps_per_second": 1.192,
|
| 399 |
+
"step": 500
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.38,
|
| 403 |
+
"learning_rate": 2.55e-05,
|
| 404 |
+
"loss": 0.8406,
|
| 405 |
+
"step": 510
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.39,
|
| 409 |
+
"learning_rate": 2.6e-05,
|
| 410 |
+
"loss": 0.8868,
|
| 411 |
+
"step": 520
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.4,
|
| 415 |
+
"learning_rate": 2.65e-05,
|
| 416 |
+
"loss": 0.8206,
|
| 417 |
+
"step": 530
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.41,
|
| 421 |
+
"learning_rate": 2.7e-05,
|
| 422 |
+
"loss": 0.7607,
|
| 423 |
+
"step": 540
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.41,
|
| 427 |
+
"learning_rate": 2.75e-05,
|
| 428 |
+
"loss": 0.6892,
|
| 429 |
+
"step": 550
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.41,
|
| 433 |
+
"eval_accuracy": 0.7312254281335376,
|
| 434 |
+
"eval_loss": 0.670229971408844,
|
| 435 |
+
"eval_runtime": 49.5662,
|
| 436 |
+
"eval_samples_per_second": 605.533,
|
| 437 |
+
"eval_steps_per_second": 1.19,
|
| 438 |
+
"step": 550
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.42,
|
| 442 |
+
"learning_rate": 2.8e-05,
|
| 443 |
+
"loss": 0.7065,
|
| 444 |
+
"step": 560
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.43,
|
| 448 |
+
"learning_rate": 2.85e-05,
|
| 449 |
+
"loss": 0.7075,
|
| 450 |
+
"step": 570
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 0.44,
|
| 454 |
+
"learning_rate": 2.9000000000000004e-05,
|
| 455 |
+
"loss": 0.6793,
|
| 456 |
+
"step": 580
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.44,
|
| 460 |
+
"learning_rate": 2.95e-05,
|
| 461 |
+
"loss": 0.6057,
|
| 462 |
+
"step": 590
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.45,
|
| 466 |
+
"learning_rate": 3e-05,
|
| 467 |
+
"loss": 0.5794,
|
| 468 |
+
"step": 600
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.45,
|
| 472 |
+
"eval_accuracy": 0.7694409275671353,
|
| 473 |
+
"eval_loss": 0.6066040396690369,
|
| 474 |
+
"eval_runtime": 49.5056,
|
| 475 |
+
"eval_samples_per_second": 606.275,
|
| 476 |
+
"eval_steps_per_second": 1.192,
|
| 477 |
+
"step": 600
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.46,
|
| 481 |
+
"learning_rate": 3.05e-05,
|
| 482 |
+
"loss": 0.609,
|
| 483 |
+
"step": 610
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.47,
|
| 487 |
+
"learning_rate": 3.1e-05,
|
| 488 |
+
"loss": 0.6058,
|
| 489 |
+
"step": 620
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.47,
|
| 493 |
+
"learning_rate": 3.15e-05,
|
| 494 |
+
"loss": 0.5518,
|
| 495 |
+
"step": 630
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.48,
|
| 499 |
+
"learning_rate": 3.2e-05,
|
| 500 |
+
"loss": 0.6132,
|
| 501 |
+
"step": 640
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.49,
|
| 505 |
+
"learning_rate": 3.2500000000000004e-05,
|
| 506 |
+
"loss": 0.5262,
|
| 507 |
+
"step": 650
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.49,
|
| 511 |
+
"eval_accuracy": 0.8218498034250683,
|
| 512 |
+
"eval_loss": 0.4961170256137848,
|
| 513 |
+
"eval_runtime": 49.5394,
|
| 514 |
+
"eval_samples_per_second": 605.861,
|
| 515 |
+
"eval_steps_per_second": 1.191,
|
| 516 |
+
"step": 650
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"epoch": 0.5,
|
| 520 |
+
"learning_rate": 3.3e-05,
|
| 521 |
+
"loss": 0.5355,
|
| 522 |
+
"step": 660
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.5,
|
| 526 |
+
"learning_rate": 3.35e-05,
|
| 527 |
+
"loss": 0.4905,
|
| 528 |
+
"step": 670
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.51,
|
| 532 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 533 |
+
"loss": 0.4992,
|
| 534 |
+
"step": 680
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 0.52,
|
| 538 |
+
"learning_rate": 3.4500000000000005e-05,
|
| 539 |
+
"loss": 0.4959,
|
| 540 |
+
"step": 690
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 0.53,
|
| 544 |
+
"learning_rate": 3.5000000000000004e-05,
|
| 545 |
+
"loss": 0.4693,
|
| 546 |
+
"step": 700
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.53,
|
| 550 |
+
"eval_accuracy": 0.851469314319984,
|
| 551 |
+
"eval_loss": 0.43606042861938477,
|
| 552 |
+
"eval_runtime": 49.5557,
|
| 553 |
+
"eval_samples_per_second": 605.662,
|
| 554 |
+
"eval_steps_per_second": 1.191,
|
| 555 |
+
"step": 700
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.53,
|
| 559 |
+
"learning_rate": 3.5499999999999996e-05,
|
| 560 |
+
"loss": 0.4725,
|
| 561 |
+
"step": 710
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.54,
|
| 565 |
+
"learning_rate": 3.6e-05,
|
| 566 |
+
"loss": 0.5033,
|
| 567 |
+
"step": 720
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.55,
|
| 571 |
+
"learning_rate": 3.65e-05,
|
| 572 |
+
"loss": 0.4679,
|
| 573 |
+
"step": 730
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.56,
|
| 577 |
+
"learning_rate": 3.7e-05,
|
| 578 |
+
"loss": 0.4639,
|
| 579 |
+
"step": 740
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.56,
|
| 583 |
+
"learning_rate": 3.75e-05,
|
| 584 |
+
"loss": 0.434,
|
| 585 |
+
"step": 750
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.56,
|
| 589 |
+
"eval_accuracy": 0.8657293263143866,
|
| 590 |
+
"eval_loss": 0.41026708483695984,
|
| 591 |
+
"eval_runtime": 49.5112,
|
| 592 |
+
"eval_samples_per_second": 606.206,
|
| 593 |
+
"eval_steps_per_second": 1.192,
|
| 594 |
+
"step": 750
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 0.57,
|
| 598 |
+
"learning_rate": 3.8e-05,
|
| 599 |
+
"loss": 0.3815,
|
| 600 |
+
"step": 760
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 0.58,
|
| 604 |
+
"learning_rate": 3.85e-05,
|
| 605 |
+
"loss": 0.4073,
|
| 606 |
+
"step": 770
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.59,
|
| 610 |
+
"learning_rate": 3.9e-05,
|
| 611 |
+
"loss": 0.424,
|
| 612 |
+
"step": 780
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.59,
|
| 616 |
+
"learning_rate": 3.95e-05,
|
| 617 |
+
"loss": 0.3867,
|
| 618 |
+
"step": 790
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.6,
|
| 622 |
+
"learning_rate": 4e-05,
|
| 623 |
+
"loss": 0.463,
|
| 624 |
+
"step": 800
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 0.6,
|
| 628 |
+
"eval_accuracy": 0.8671286732858,
|
| 629 |
+
"eval_loss": 0.3895261585712433,
|
| 630 |
+
"eval_runtime": 49.5727,
|
| 631 |
+
"eval_samples_per_second": 605.455,
|
| 632 |
+
"eval_steps_per_second": 1.19,
|
| 633 |
+
"step": 800
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.61,
|
| 637 |
+
"learning_rate": 4.05e-05,
|
| 638 |
+
"loss": 0.407,
|
| 639 |
+
"step": 810
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.62,
|
| 643 |
+
"learning_rate": 4.1e-05,
|
| 644 |
+
"loss": 0.4077,
|
| 645 |
+
"step": 820
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.62,
|
| 649 |
+
"learning_rate": 4.1500000000000006e-05,
|
| 650 |
+
"loss": 0.4015,
|
| 651 |
+
"step": 830
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.63,
|
| 655 |
+
"learning_rate": 4.2000000000000004e-05,
|
| 656 |
+
"loss": 0.3652,
|
| 657 |
+
"step": 840
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.64,
|
| 661 |
+
"learning_rate": 4.25e-05,
|
| 662 |
+
"loss": 0.411,
|
| 663 |
+
"step": 850
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.64,
|
| 667 |
+
"eval_accuracy": 0.8794895715332844,
|
| 668 |
+
"eval_loss": 0.36858388781547546,
|
| 669 |
+
"eval_runtime": 49.5593,
|
| 670 |
+
"eval_samples_per_second": 605.618,
|
| 671 |
+
"eval_steps_per_second": 1.19,
|
| 672 |
+
"step": 850
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.65,
|
| 676 |
+
"learning_rate": 4.2999999999999995e-05,
|
| 677 |
+
"loss": 0.4162,
|
| 678 |
+
"step": 860
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"epoch": 0.65,
|
| 682 |
+
"learning_rate": 4.35e-05,
|
| 683 |
+
"loss": 0.3985,
|
| 684 |
+
"step": 870
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 0.66,
|
| 688 |
+
"learning_rate": 4.4e-05,
|
| 689 |
+
"loss": 0.3925,
|
| 690 |
+
"step": 880
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.67,
|
| 694 |
+
"learning_rate": 4.45e-05,
|
| 695 |
+
"loss": 0.3621,
|
| 696 |
+
"step": 890
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.68,
|
| 700 |
+
"learning_rate": 4.4999999999999996e-05,
|
| 701 |
+
"loss": 0.3715,
|
| 702 |
+
"step": 900
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"epoch": 0.68,
|
| 706 |
+
"eval_accuracy": 0.8932164989671486,
|
| 707 |
+
"eval_loss": 0.33608904480934143,
|
| 708 |
+
"eval_runtime": 49.5424,
|
| 709 |
+
"eval_samples_per_second": 605.825,
|
| 710 |
+
"eval_steps_per_second": 1.191,
|
| 711 |
+
"step": 900
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.68,
|
| 715 |
+
"learning_rate": 4.55e-05,
|
| 716 |
+
"loss": 0.3337,
|
| 717 |
+
"step": 910
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.69,
|
| 721 |
+
"learning_rate": 4.6e-05,
|
| 722 |
+
"loss": 0.3592,
|
| 723 |
+
"step": 920
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.7,
|
| 727 |
+
"learning_rate": 4.65e-05,
|
| 728 |
+
"loss": 0.3845,
|
| 729 |
+
"step": 930
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.71,
|
| 733 |
+
"learning_rate": 4.7000000000000004e-05,
|
| 734 |
+
"loss": 0.4175,
|
| 735 |
+
"step": 940
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.71,
|
| 739 |
+
"learning_rate": 4.75e-05,
|
| 740 |
+
"loss": 0.4039,
|
| 741 |
+
"step": 950
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.71,
|
| 745 |
+
"eval_accuracy": 0.8966815486106484,
|
| 746 |
+
"eval_loss": 0.3278920352458954,
|
| 747 |
+
"eval_runtime": 49.6606,
|
| 748 |
+
"eval_samples_per_second": 604.383,
|
| 749 |
+
"eval_steps_per_second": 1.188,
|
| 750 |
+
"step": 950
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.72,
|
| 754 |
+
"learning_rate": 4.8e-05,
|
| 755 |
+
"loss": 0.3474,
|
| 756 |
+
"step": 960
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.73,
|
| 760 |
+
"learning_rate": 4.85e-05,
|
| 761 |
+
"loss": 0.3804,
|
| 762 |
+
"step": 970
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.74,
|
| 766 |
+
"learning_rate": 4.9000000000000005e-05,
|
| 767 |
+
"loss": 0.3432,
|
| 768 |
+
"step": 980
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.74,
|
| 772 |
+
"learning_rate": 4.9500000000000004e-05,
|
| 773 |
+
"loss": 0.3184,
|
| 774 |
+
"step": 990
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 0.75,
|
| 778 |
+
"learning_rate": 5e-05,
|
| 779 |
+
"loss": 0.369,
|
| 780 |
+
"step": 1000
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.75,
|
| 784 |
+
"eval_accuracy": 0.9011461318051576,
|
| 785 |
+
"eval_loss": 0.33548465371131897,
|
| 786 |
+
"eval_runtime": 49.6573,
|
| 787 |
+
"eval_samples_per_second": 604.422,
|
| 788 |
+
"eval_steps_per_second": 1.188,
|
| 789 |
+
"step": 1000
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.76,
|
| 793 |
+
"learning_rate": 5.05e-05,
|
| 794 |
+
"loss": 0.3818,
|
| 795 |
+
"step": 1010
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.77,
|
| 799 |
+
"learning_rate": 5.1e-05,
|
| 800 |
+
"loss": 0.3616,
|
| 801 |
+
"step": 1020
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.78,
|
| 805 |
+
"learning_rate": 5.15e-05,
|
| 806 |
+
"loss": 0.3579,
|
| 807 |
+
"step": 1030
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.78,
|
| 811 |
+
"learning_rate": 5.2e-05,
|
| 812 |
+
"loss": 0.3208,
|
| 813 |
+
"step": 1040
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.79,
|
| 817 |
+
"learning_rate": 5.25e-05,
|
| 818 |
+
"loss": 0.3217,
|
| 819 |
+
"step": 1050
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.79,
|
| 823 |
+
"eval_accuracy": 0.9045778636636237,
|
| 824 |
+
"eval_loss": 0.3070036768913269,
|
| 825 |
+
"eval_runtime": 49.5744,
|
| 826 |
+
"eval_samples_per_second": 605.433,
|
| 827 |
+
"eval_steps_per_second": 1.19,
|
| 828 |
+
"step": 1050
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"epoch": 0.8,
|
| 832 |
+
"learning_rate": 5.3e-05,
|
| 833 |
+
"loss": 0.367,
|
| 834 |
+
"step": 1060
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 0.81,
|
| 838 |
+
"learning_rate": 5.35e-05,
|
| 839 |
+
"loss": 0.3484,
|
| 840 |
+
"step": 1070
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.81,
|
| 844 |
+
"learning_rate": 5.4e-05,
|
| 845 |
+
"loss": 0.3242,
|
| 846 |
+
"step": 1080
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.82,
|
| 850 |
+
"learning_rate": 5.45e-05,
|
| 851 |
+
"loss": 0.3312,
|
| 852 |
+
"step": 1090
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.83,
|
| 856 |
+
"learning_rate": 5.5e-05,
|
| 857 |
+
"loss": 0.3182,
|
| 858 |
+
"step": 1100
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.83,
|
| 862 |
+
"eval_accuracy": 0.8963150529752782,
|
| 863 |
+
"eval_loss": 0.33996570110321045,
|
| 864 |
+
"eval_runtime": 49.5694,
|
| 865 |
+
"eval_samples_per_second": 605.494,
|
| 866 |
+
"eval_steps_per_second": 1.19,
|
| 867 |
+
"step": 1100
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.84,
|
| 871 |
+
"learning_rate": 5.55e-05,
|
| 872 |
+
"loss": 0.3059,
|
| 873 |
+
"step": 1110
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.84,
|
| 877 |
+
"learning_rate": 5.6e-05,
|
| 878 |
+
"loss": 0.3308,
|
| 879 |
+
"step": 1120
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.85,
|
| 883 |
+
"learning_rate": 5.6500000000000005e-05,
|
| 884 |
+
"loss": 0.3294,
|
| 885 |
+
"step": 1130
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.86,
|
| 889 |
+
"learning_rate": 5.7e-05,
|
| 890 |
+
"loss": 0.2979,
|
| 891 |
+
"step": 1140
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.87,
|
| 895 |
+
"learning_rate": 5.75e-05,
|
| 896 |
+
"loss": 0.3454,
|
| 897 |
+
"step": 1150
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.87,
|
| 901 |
+
"eval_accuracy": 0.9106417005397481,
|
| 902 |
+
"eval_loss": 0.29532137513160706,
|
| 903 |
+
"eval_runtime": 49.5343,
|
| 904 |
+
"eval_samples_per_second": 605.924,
|
| 905 |
+
"eval_steps_per_second": 1.191,
|
| 906 |
+
"step": 1150
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.87,
|
| 910 |
+
"learning_rate": 5.800000000000001e-05,
|
| 911 |
+
"loss": 0.3369,
|
| 912 |
+
"step": 1160
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.88,
|
| 916 |
+
"learning_rate": 5.8500000000000006e-05,
|
| 917 |
+
"loss": 0.312,
|
| 918 |
+
"step": 1170
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"epoch": 0.89,
|
| 922 |
+
"learning_rate": 5.9e-05,
|
| 923 |
+
"loss": 0.2897,
|
| 924 |
+
"step": 1180
|
| 925 |
+
},
|
| 926 |
+
{
|
| 927 |
+
"epoch": 0.9,
|
| 928 |
+
"learning_rate": 5.9499999999999996e-05,
|
| 929 |
+
"loss": 0.2938,
|
| 930 |
+
"step": 1190
|
| 931 |
+
},
|
| 932 |
+
{
|
| 933 |
+
"epoch": 0.9,
|
| 934 |
+
"learning_rate": 6e-05,
|
| 935 |
+
"loss": 0.3278,
|
| 936 |
+
"step": 1200
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.9,
|
| 940 |
+
"eval_accuracy": 0.892616778836543,
|
| 941 |
+
"eval_loss": 0.3169938027858734,
|
| 942 |
+
"eval_runtime": 49.5317,
|
| 943 |
+
"eval_samples_per_second": 605.955,
|
| 944 |
+
"eval_steps_per_second": 1.191,
|
| 945 |
+
"step": 1200
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.91,
|
| 949 |
+
"learning_rate": 6.05e-05,
|
| 950 |
+
"loss": 0.33,
|
| 951 |
+
"step": 1210
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.92,
|
| 955 |
+
"learning_rate": 6.1e-05,
|
| 956 |
+
"loss": 0.2844,
|
| 957 |
+
"step": 1220
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.93,
|
| 961 |
+
"learning_rate": 6.15e-05,
|
| 962 |
+
"loss": 0.305,
|
| 963 |
+
"step": 1230
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.93,
|
| 967 |
+
"learning_rate": 6.2e-05,
|
| 968 |
+
"loss": 0.3118,
|
| 969 |
+
"step": 1240
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.94,
|
| 973 |
+
"learning_rate": 6.25e-05,
|
| 974 |
+
"loss": 0.2586,
|
| 975 |
+
"step": 1250
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.94,
|
| 979 |
+
"eval_accuracy": 0.9156726860798294,
|
| 980 |
+
"eval_loss": 0.27952006459236145,
|
| 981 |
+
"eval_runtime": 49.5827,
|
| 982 |
+
"eval_samples_per_second": 605.332,
|
| 983 |
+
"eval_steps_per_second": 1.19,
|
| 984 |
+
"step": 1250
|
| 985 |
+
}
|
| 986 |
+
],
|
| 987 |
+
"logging_steps": 10,
|
| 988 |
+
"max_steps": 3987,
|
| 989 |
+
"num_train_epochs": 3,
|
| 990 |
+
"save_steps": 250,
|
| 991 |
+
"total_flos": 4.209814536192e+16,
|
| 992 |
+
"trial_name": null,
|
| 993 |
+
"trial_params": null
|
| 994 |
+
}
|
checkpoint-1250/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:842788c44aca7ccbca2d57d8869e43eb15da3880b4cadb0b091bb46a3e020fcc
|
| 3 |
+
size 4536
|
checkpoint-1250/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|