Upload folder using huggingface_hub
Browse files- config.json +74 -0
- evaluation/finetuned/bart-base-imdb.json +6 -0
- merges.txt +0 -0
- pytorch_model.bin +3 -0
- special_tokens_map.json +51 -0
- tokenizer_config.json +63 -0
- training_args.bin +3 -0
- validation/finetuned/bart-base-imdb_metrics.json +806 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,74 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "facebook/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 |
+
"forced_bos_token_id": 0,
|
| 28 |
+
"forced_eos_token_id": 2,
|
| 29 |
+
"gradient_checkpointing": false,
|
| 30 |
+
"id2label": {
|
| 31 |
+
"0": "LABEL_0",
|
| 32 |
+
"1": "LABEL_1"
|
| 33 |
+
},
|
| 34 |
+
"init_std": 0.02,
|
| 35 |
+
"is_encoder_decoder": true,
|
| 36 |
+
"label2id": {
|
| 37 |
+
"LABEL_0": 0,
|
| 38 |
+
"LABEL_1": 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": "4.28.0",
|
| 72 |
+
"use_cache": true,
|
| 73 |
+
"vocab_size": 50265
|
| 74 |
+
}
|
evaluation/finetuned/bart-base-imdb.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"accuracy": 0.87968,
|
| 3 |
+
"precision": 0.8838563571659657,
|
| 4 |
+
"recall": 0.87424,
|
| 5 |
+
"f1": 0.8790218790218789
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8753124c2a4c6105f2c19c503bb8d4fc2e1bb14365acecf2d3f6cbbbd1d0e5cc
|
| 3 |
+
size 560139561
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "<s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "<mask>",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "<pad>",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "</s>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "<unk>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"bos_token": {
|
| 4 |
+
"__type": "AddedToken",
|
| 5 |
+
"content": "<s>",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false
|
| 10 |
+
},
|
| 11 |
+
"clean_up_tokenization_spaces": true,
|
| 12 |
+
"cls_token": {
|
| 13 |
+
"__type": "AddedToken",
|
| 14 |
+
"content": "<s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": true,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"eos_token": {
|
| 21 |
+
"__type": "AddedToken",
|
| 22 |
+
"content": "</s>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": true,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false
|
| 27 |
+
},
|
| 28 |
+
"errors": "replace",
|
| 29 |
+
"mask_token": {
|
| 30 |
+
"__type": "AddedToken",
|
| 31 |
+
"content": "<mask>",
|
| 32 |
+
"lstrip": true,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"model_max_length": 1024,
|
| 38 |
+
"pad_token": {
|
| 39 |
+
"__type": "AddedToken",
|
| 40 |
+
"content": "<pad>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": true,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
"sep_token": {
|
| 47 |
+
"__type": "AddedToken",
|
| 48 |
+
"content": "</s>",
|
| 49 |
+
"lstrip": false,
|
| 50 |
+
"normalized": true,
|
| 51 |
+
"rstrip": false,
|
| 52 |
+
"single_word": false
|
| 53 |
+
},
|
| 54 |
+
"tokenizer_class": "BartTokenizer",
|
| 55 |
+
"unk_token": {
|
| 56 |
+
"__type": "AddedToken",
|
| 57 |
+
"content": "<unk>",
|
| 58 |
+
"lstrip": false,
|
| 59 |
+
"normalized": true,
|
| 60 |
+
"rstrip": false,
|
| 61 |
+
"single_word": false
|
| 62 |
+
}
|
| 63 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74bf110f9e06bb315f4660f113cb354f5f08cb176a7f599ce1a4bc2f272dd885
|
| 3 |
+
size 3579
|
validation/finetuned/bart-base-imdb_metrics.json
ADDED
|
@@ -0,0 +1,806 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"loss": 0.6041,
|
| 4 |
+
"learning_rate": 4.96e-05,
|
| 5 |
+
"epoch": 0.04,
|
| 6 |
+
"step": 100
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"loss": 0.5209,
|
| 10 |
+
"learning_rate": 4.92e-05,
|
| 11 |
+
"epoch": 0.08,
|
| 12 |
+
"step": 200
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"loss": 0.4233,
|
| 16 |
+
"learning_rate": 4.88e-05,
|
| 17 |
+
"epoch": 0.12,
|
| 18 |
+
"step": 300
|
| 19 |
+
},
|
| 20 |
+
{
|
| 21 |
+
"loss": 0.5037,
|
| 22 |
+
"learning_rate": 4.8400000000000004e-05,
|
| 23 |
+
"epoch": 0.16,
|
| 24 |
+
"step": 400
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"loss": 0.4433,
|
| 28 |
+
"learning_rate": 4.8e-05,
|
| 29 |
+
"epoch": 0.2,
|
| 30 |
+
"step": 500
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"loss": 0.4772,
|
| 34 |
+
"learning_rate": 4.76e-05,
|
| 35 |
+
"epoch": 0.24,
|
| 36 |
+
"step": 600
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"loss": 0.4241,
|
| 40 |
+
"learning_rate": 4.72e-05,
|
| 41 |
+
"epoch": 0.28,
|
| 42 |
+
"step": 700
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"loss": 0.4217,
|
| 46 |
+
"learning_rate": 4.6800000000000006e-05,
|
| 47 |
+
"epoch": 0.32,
|
| 48 |
+
"step": 800
|
| 49 |
+
},
|
| 50 |
+
{
|
| 51 |
+
"loss": 0.4178,
|
| 52 |
+
"learning_rate": 4.64e-05,
|
| 53 |
+
"epoch": 0.36,
|
| 54 |
+
"step": 900
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"loss": 0.401,
|
| 58 |
+
"learning_rate": 4.600000000000001e-05,
|
| 59 |
+
"epoch": 0.4,
|
| 60 |
+
"step": 1000
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"loss": 0.4261,
|
| 64 |
+
"learning_rate": 4.5600000000000004e-05,
|
| 65 |
+
"epoch": 0.44,
|
| 66 |
+
"step": 1100
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"loss": 0.4151,
|
| 70 |
+
"learning_rate": 4.52e-05,
|
| 71 |
+
"epoch": 0.48,
|
| 72 |
+
"step": 1200
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"loss": 0.3708,
|
| 76 |
+
"learning_rate": 4.4800000000000005e-05,
|
| 77 |
+
"epoch": 0.52,
|
| 78 |
+
"step": 1300
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"loss": 0.3927,
|
| 82 |
+
"learning_rate": 4.44e-05,
|
| 83 |
+
"epoch": 0.56,
|
| 84 |
+
"step": 1400
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"loss": 0.4078,
|
| 88 |
+
"learning_rate": 4.4000000000000006e-05,
|
| 89 |
+
"epoch": 0.6,
|
| 90 |
+
"step": 1500
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"loss": 0.3713,
|
| 94 |
+
"learning_rate": 4.36e-05,
|
| 95 |
+
"epoch": 0.64,
|
| 96 |
+
"step": 1600
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"loss": 0.3777,
|
| 100 |
+
"learning_rate": 4.32e-05,
|
| 101 |
+
"epoch": 0.68,
|
| 102 |
+
"step": 1700
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"loss": 0.411,
|
| 106 |
+
"learning_rate": 4.2800000000000004e-05,
|
| 107 |
+
"epoch": 0.72,
|
| 108 |
+
"step": 1800
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"loss": 0.3814,
|
| 112 |
+
"learning_rate": 4.24e-05,
|
| 113 |
+
"epoch": 0.76,
|
| 114 |
+
"step": 1900
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"loss": 0.3919,
|
| 118 |
+
"learning_rate": 4.2e-05,
|
| 119 |
+
"epoch": 0.8,
|
| 120 |
+
"step": 2000
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"loss": 0.3652,
|
| 124 |
+
"learning_rate": 4.16e-05,
|
| 125 |
+
"epoch": 0.84,
|
| 126 |
+
"step": 2100
|
| 127 |
+
},
|
| 128 |
+
{
|
| 129 |
+
"loss": 0.3796,
|
| 130 |
+
"learning_rate": 4.12e-05,
|
| 131 |
+
"epoch": 0.88,
|
| 132 |
+
"step": 2200
|
| 133 |
+
},
|
| 134 |
+
{
|
| 135 |
+
"loss": 0.3786,
|
| 136 |
+
"learning_rate": 4.08e-05,
|
| 137 |
+
"epoch": 0.92,
|
| 138 |
+
"step": 2300
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"loss": 0.3473,
|
| 142 |
+
"learning_rate": 4.0400000000000006e-05,
|
| 143 |
+
"epoch": 0.96,
|
| 144 |
+
"step": 2400
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"loss": 0.3614,
|
| 148 |
+
"learning_rate": 4e-05,
|
| 149 |
+
"epoch": 1.0,
|
| 150 |
+
"step": 2500
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"eval_loss": 0.3348940908908844,
|
| 154 |
+
"eval_accuracy": 0.877,
|
| 155 |
+
"eval_runtime": 21.2829,
|
| 156 |
+
"eval_samples_per_second": 234.931,
|
| 157 |
+
"eval_steps_per_second": 29.366,
|
| 158 |
+
"epoch": 1.0,
|
| 159 |
+
"step": 2500
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"loss": 0.2709,
|
| 163 |
+
"learning_rate": 3.960000000000001e-05,
|
| 164 |
+
"epoch": 1.04,
|
| 165 |
+
"step": 2600
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"loss": 0.3136,
|
| 169 |
+
"learning_rate": 3.9200000000000004e-05,
|
| 170 |
+
"epoch": 1.08,
|
| 171 |
+
"step": 2700
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"loss": 0.308,
|
| 175 |
+
"learning_rate": 3.88e-05,
|
| 176 |
+
"epoch": 1.12,
|
| 177 |
+
"step": 2800
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"loss": 0.2667,
|
| 181 |
+
"learning_rate": 3.8400000000000005e-05,
|
| 182 |
+
"epoch": 1.16,
|
| 183 |
+
"step": 2900
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"loss": 0.2971,
|
| 187 |
+
"learning_rate": 3.8e-05,
|
| 188 |
+
"epoch": 1.2,
|
| 189 |
+
"step": 3000
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"loss": 0.2902,
|
| 193 |
+
"learning_rate": 3.76e-05,
|
| 194 |
+
"epoch": 1.24,
|
| 195 |
+
"step": 3100
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"loss": 0.324,
|
| 199 |
+
"learning_rate": 3.72e-05,
|
| 200 |
+
"epoch": 1.28,
|
| 201 |
+
"step": 3200
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"loss": 0.291,
|
| 205 |
+
"learning_rate": 3.68e-05,
|
| 206 |
+
"epoch": 1.32,
|
| 207 |
+
"step": 3300
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"loss": 0.2522,
|
| 211 |
+
"learning_rate": 3.6400000000000004e-05,
|
| 212 |
+
"epoch": 1.36,
|
| 213 |
+
"step": 3400
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"loss": 0.2756,
|
| 217 |
+
"learning_rate": 3.6e-05,
|
| 218 |
+
"epoch": 1.4,
|
| 219 |
+
"step": 3500
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"loss": 0.3068,
|
| 223 |
+
"learning_rate": 3.56e-05,
|
| 224 |
+
"epoch": 1.44,
|
| 225 |
+
"step": 3600
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"loss": 0.3102,
|
| 229 |
+
"learning_rate": 3.52e-05,
|
| 230 |
+
"epoch": 1.48,
|
| 231 |
+
"step": 3700
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"loss": 0.3165,
|
| 235 |
+
"learning_rate": 3.48e-05,
|
| 236 |
+
"epoch": 1.52,
|
| 237 |
+
"step": 3800
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"loss": 0.3054,
|
| 241 |
+
"learning_rate": 3.4399999999999996e-05,
|
| 242 |
+
"epoch": 1.56,
|
| 243 |
+
"step": 3900
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"loss": 0.306,
|
| 247 |
+
"learning_rate": 3.4000000000000007e-05,
|
| 248 |
+
"epoch": 1.6,
|
| 249 |
+
"step": 4000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"loss": 0.2712,
|
| 253 |
+
"learning_rate": 3.3600000000000004e-05,
|
| 254 |
+
"epoch": 1.64,
|
| 255 |
+
"step": 4100
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"loss": 0.3108,
|
| 259 |
+
"learning_rate": 3.32e-05,
|
| 260 |
+
"epoch": 1.68,
|
| 261 |
+
"step": 4200
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"loss": 0.2824,
|
| 265 |
+
"learning_rate": 3.2800000000000004e-05,
|
| 266 |
+
"epoch": 1.72,
|
| 267 |
+
"step": 4300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"loss": 0.2654,
|
| 271 |
+
"learning_rate": 3.24e-05,
|
| 272 |
+
"epoch": 1.76,
|
| 273 |
+
"step": 4400
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"loss": 0.337,
|
| 277 |
+
"learning_rate": 3.2000000000000005e-05,
|
| 278 |
+
"epoch": 1.8,
|
| 279 |
+
"step": 4500
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"loss": 0.2684,
|
| 283 |
+
"learning_rate": 3.16e-05,
|
| 284 |
+
"epoch": 1.84,
|
| 285 |
+
"step": 4600
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"loss": 0.2993,
|
| 289 |
+
"learning_rate": 3.12e-05,
|
| 290 |
+
"epoch": 1.88,
|
| 291 |
+
"step": 4700
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"loss": 0.3057,
|
| 295 |
+
"learning_rate": 3.08e-05,
|
| 296 |
+
"epoch": 1.92,
|
| 297 |
+
"step": 4800
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"loss": 0.3327,
|
| 301 |
+
"learning_rate": 3.04e-05,
|
| 302 |
+
"epoch": 1.96,
|
| 303 |
+
"step": 4900
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"loss": 0.2699,
|
| 307 |
+
"learning_rate": 3e-05,
|
| 308 |
+
"epoch": 2.0,
|
| 309 |
+
"step": 5000
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"eval_loss": 0.5084385275840759,
|
| 313 |
+
"eval_accuracy": 0.88,
|
| 314 |
+
"eval_runtime": 15.3223,
|
| 315 |
+
"eval_samples_per_second": 326.323,
|
| 316 |
+
"eval_steps_per_second": 40.79,
|
| 317 |
+
"epoch": 2.0,
|
| 318 |
+
"step": 5000
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"loss": 0.186,
|
| 322 |
+
"learning_rate": 2.96e-05,
|
| 323 |
+
"epoch": 2.04,
|
| 324 |
+
"step": 5100
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"loss": 0.2181,
|
| 328 |
+
"learning_rate": 2.9199999999999998e-05,
|
| 329 |
+
"epoch": 2.08,
|
| 330 |
+
"step": 5200
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"loss": 0.1703,
|
| 334 |
+
"learning_rate": 2.88e-05,
|
| 335 |
+
"epoch": 2.12,
|
| 336 |
+
"step": 5300
|
| 337 |
+
},
|
| 338 |
+
{
|
| 339 |
+
"loss": 0.1659,
|
| 340 |
+
"learning_rate": 2.84e-05,
|
| 341 |
+
"epoch": 2.16,
|
| 342 |
+
"step": 5400
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"loss": 0.1902,
|
| 346 |
+
"learning_rate": 2.8000000000000003e-05,
|
| 347 |
+
"epoch": 2.2,
|
| 348 |
+
"step": 5500
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"loss": 0.1995,
|
| 352 |
+
"learning_rate": 2.7600000000000003e-05,
|
| 353 |
+
"epoch": 2.24,
|
| 354 |
+
"step": 5600
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"loss": 0.1832,
|
| 358 |
+
"learning_rate": 2.7200000000000004e-05,
|
| 359 |
+
"epoch": 2.28,
|
| 360 |
+
"step": 5700
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"loss": 0.1706,
|
| 364 |
+
"learning_rate": 2.6800000000000004e-05,
|
| 365 |
+
"epoch": 2.32,
|
| 366 |
+
"step": 5800
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"loss": 0.2174,
|
| 370 |
+
"learning_rate": 2.64e-05,
|
| 371 |
+
"epoch": 2.36,
|
| 372 |
+
"step": 5900
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"loss": 0.2241,
|
| 376 |
+
"learning_rate": 2.6000000000000002e-05,
|
| 377 |
+
"epoch": 2.4,
|
| 378 |
+
"step": 6000
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"loss": 0.2098,
|
| 382 |
+
"learning_rate": 2.5600000000000002e-05,
|
| 383 |
+
"epoch": 2.44,
|
| 384 |
+
"step": 6100
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"loss": 0.1512,
|
| 388 |
+
"learning_rate": 2.5200000000000003e-05,
|
| 389 |
+
"epoch": 2.48,
|
| 390 |
+
"step": 6200
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"loss": 0.2344,
|
| 394 |
+
"learning_rate": 2.48e-05,
|
| 395 |
+
"epoch": 2.52,
|
| 396 |
+
"step": 6300
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"loss": 0.1956,
|
| 400 |
+
"learning_rate": 2.44e-05,
|
| 401 |
+
"epoch": 2.56,
|
| 402 |
+
"step": 6400
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"loss": 0.1951,
|
| 406 |
+
"learning_rate": 2.4e-05,
|
| 407 |
+
"epoch": 2.6,
|
| 408 |
+
"step": 6500
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"loss": 0.1961,
|
| 412 |
+
"learning_rate": 2.36e-05,
|
| 413 |
+
"epoch": 2.64,
|
| 414 |
+
"step": 6600
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"loss": 0.174,
|
| 418 |
+
"learning_rate": 2.32e-05,
|
| 419 |
+
"epoch": 2.68,
|
| 420 |
+
"step": 6700
|
| 421 |
+
},
|
| 422 |
+
{
|
| 423 |
+
"loss": 0.1917,
|
| 424 |
+
"learning_rate": 2.2800000000000002e-05,
|
| 425 |
+
"epoch": 2.72,
|
| 426 |
+
"step": 6800
|
| 427 |
+
},
|
| 428 |
+
{
|
| 429 |
+
"loss": 0.181,
|
| 430 |
+
"learning_rate": 2.2400000000000002e-05,
|
| 431 |
+
"epoch": 2.76,
|
| 432 |
+
"step": 6900
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"loss": 0.2041,
|
| 436 |
+
"learning_rate": 2.2000000000000003e-05,
|
| 437 |
+
"epoch": 2.8,
|
| 438 |
+
"step": 7000
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"loss": 0.199,
|
| 442 |
+
"learning_rate": 2.16e-05,
|
| 443 |
+
"epoch": 2.84,
|
| 444 |
+
"step": 7100
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"loss": 0.2355,
|
| 448 |
+
"learning_rate": 2.12e-05,
|
| 449 |
+
"epoch": 2.88,
|
| 450 |
+
"step": 7200
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"loss": 0.1697,
|
| 454 |
+
"learning_rate": 2.08e-05,
|
| 455 |
+
"epoch": 2.92,
|
| 456 |
+
"step": 7300
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"loss": 0.1874,
|
| 460 |
+
"learning_rate": 2.04e-05,
|
| 461 |
+
"epoch": 2.96,
|
| 462 |
+
"step": 7400
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"loss": 0.1661,
|
| 466 |
+
"learning_rate": 2e-05,
|
| 467 |
+
"epoch": 3.0,
|
| 468 |
+
"step": 7500
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"eval_loss": 0.5631409883499146,
|
| 472 |
+
"eval_accuracy": 0.8748,
|
| 473 |
+
"eval_runtime": 15.3171,
|
| 474 |
+
"eval_samples_per_second": 326.433,
|
| 475 |
+
"eval_steps_per_second": 40.804,
|
| 476 |
+
"epoch": 3.0,
|
| 477 |
+
"step": 7500
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"loss": 0.0818,
|
| 481 |
+
"learning_rate": 1.9600000000000002e-05,
|
| 482 |
+
"epoch": 3.04,
|
| 483 |
+
"step": 7600
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"loss": 0.1223,
|
| 487 |
+
"learning_rate": 1.9200000000000003e-05,
|
| 488 |
+
"epoch": 3.08,
|
| 489 |
+
"step": 7700
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"loss": 0.0665,
|
| 493 |
+
"learning_rate": 1.88e-05,
|
| 494 |
+
"epoch": 3.12,
|
| 495 |
+
"step": 7800
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"loss": 0.1201,
|
| 499 |
+
"learning_rate": 1.84e-05,
|
| 500 |
+
"epoch": 3.16,
|
| 501 |
+
"step": 7900
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"loss": 0.1272,
|
| 505 |
+
"learning_rate": 1.8e-05,
|
| 506 |
+
"epoch": 3.2,
|
| 507 |
+
"step": 8000
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"loss": 0.1297,
|
| 511 |
+
"learning_rate": 1.76e-05,
|
| 512 |
+
"epoch": 3.24,
|
| 513 |
+
"step": 8100
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"loss": 0.1356,
|
| 517 |
+
"learning_rate": 1.7199999999999998e-05,
|
| 518 |
+
"epoch": 3.28,
|
| 519 |
+
"step": 8200
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"loss": 0.1045,
|
| 523 |
+
"learning_rate": 1.6800000000000002e-05,
|
| 524 |
+
"epoch": 3.32,
|
| 525 |
+
"step": 8300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"loss": 0.0732,
|
| 529 |
+
"learning_rate": 1.6400000000000002e-05,
|
| 530 |
+
"epoch": 3.36,
|
| 531 |
+
"step": 8400
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"loss": 0.1483,
|
| 535 |
+
"learning_rate": 1.6000000000000003e-05,
|
| 536 |
+
"epoch": 3.4,
|
| 537 |
+
"step": 8500
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"loss": 0.1237,
|
| 541 |
+
"learning_rate": 1.56e-05,
|
| 542 |
+
"epoch": 3.44,
|
| 543 |
+
"step": 8600
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"loss": 0.1001,
|
| 547 |
+
"learning_rate": 1.52e-05,
|
| 548 |
+
"epoch": 3.48,
|
| 549 |
+
"step": 8700
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"loss": 0.1757,
|
| 553 |
+
"learning_rate": 1.48e-05,
|
| 554 |
+
"epoch": 3.52,
|
| 555 |
+
"step": 8800
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"loss": 0.1236,
|
| 559 |
+
"learning_rate": 1.44e-05,
|
| 560 |
+
"epoch": 3.56,
|
| 561 |
+
"step": 8900
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"loss": 0.1255,
|
| 565 |
+
"learning_rate": 1.4000000000000001e-05,
|
| 566 |
+
"epoch": 3.6,
|
| 567 |
+
"step": 9000
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"loss": 0.0719,
|
| 571 |
+
"learning_rate": 1.3600000000000002e-05,
|
| 572 |
+
"epoch": 3.64,
|
| 573 |
+
"step": 9100
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"loss": 0.108,
|
| 577 |
+
"learning_rate": 1.32e-05,
|
| 578 |
+
"epoch": 3.68,
|
| 579 |
+
"step": 9200
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"loss": 0.1364,
|
| 583 |
+
"learning_rate": 1.2800000000000001e-05,
|
| 584 |
+
"epoch": 3.72,
|
| 585 |
+
"step": 9300
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"loss": 0.0662,
|
| 589 |
+
"learning_rate": 1.24e-05,
|
| 590 |
+
"epoch": 3.76,
|
| 591 |
+
"step": 9400
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"loss": 0.1386,
|
| 595 |
+
"learning_rate": 1.2e-05,
|
| 596 |
+
"epoch": 3.8,
|
| 597 |
+
"step": 9500
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"loss": 0.1232,
|
| 601 |
+
"learning_rate": 1.16e-05,
|
| 602 |
+
"epoch": 3.84,
|
| 603 |
+
"step": 9600
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"loss": 0.1021,
|
| 607 |
+
"learning_rate": 1.1200000000000001e-05,
|
| 608 |
+
"epoch": 3.88,
|
| 609 |
+
"step": 9700
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"loss": 0.0687,
|
| 613 |
+
"learning_rate": 1.08e-05,
|
| 614 |
+
"epoch": 3.92,
|
| 615 |
+
"step": 9800
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"loss": 0.1154,
|
| 619 |
+
"learning_rate": 1.04e-05,
|
| 620 |
+
"epoch": 3.96,
|
| 621 |
+
"step": 9900
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"loss": 0.0793,
|
| 625 |
+
"learning_rate": 1e-05,
|
| 626 |
+
"epoch": 4.0,
|
| 627 |
+
"step": 10000
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"eval_loss": 0.6433278322219849,
|
| 631 |
+
"eval_accuracy": 0.8848,
|
| 632 |
+
"eval_runtime": 14.9452,
|
| 633 |
+
"eval_samples_per_second": 334.554,
|
| 634 |
+
"eval_steps_per_second": 41.819,
|
| 635 |
+
"epoch": 4.0,
|
| 636 |
+
"step": 10000
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"loss": 0.0458,
|
| 640 |
+
"learning_rate": 9.600000000000001e-06,
|
| 641 |
+
"epoch": 4.04,
|
| 642 |
+
"step": 10100
|
| 643 |
+
},
|
| 644 |
+
{
|
| 645 |
+
"loss": 0.0631,
|
| 646 |
+
"learning_rate": 9.2e-06,
|
| 647 |
+
"epoch": 4.08,
|
| 648 |
+
"step": 10200
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"loss": 0.0713,
|
| 652 |
+
"learning_rate": 8.8e-06,
|
| 653 |
+
"epoch": 4.12,
|
| 654 |
+
"step": 10300
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"loss": 0.0299,
|
| 658 |
+
"learning_rate": 8.400000000000001e-06,
|
| 659 |
+
"epoch": 4.16,
|
| 660 |
+
"step": 10400
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"loss": 0.0614,
|
| 664 |
+
"learning_rate": 8.000000000000001e-06,
|
| 665 |
+
"epoch": 4.2,
|
| 666 |
+
"step": 10500
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"loss": 0.0618,
|
| 670 |
+
"learning_rate": 7.6e-06,
|
| 671 |
+
"epoch": 4.24,
|
| 672 |
+
"step": 10600
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"loss": 0.0571,
|
| 676 |
+
"learning_rate": 7.2e-06,
|
| 677 |
+
"epoch": 4.28,
|
| 678 |
+
"step": 10700
|
| 679 |
+
},
|
| 680 |
+
{
|
| 681 |
+
"loss": 0.0365,
|
| 682 |
+
"learning_rate": 6.800000000000001e-06,
|
| 683 |
+
"epoch": 4.32,
|
| 684 |
+
"step": 10800
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"loss": 0.0361,
|
| 688 |
+
"learning_rate": 6.4000000000000006e-06,
|
| 689 |
+
"epoch": 4.36,
|
| 690 |
+
"step": 10900
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"loss": 0.0566,
|
| 694 |
+
"learning_rate": 6e-06,
|
| 695 |
+
"epoch": 4.4,
|
| 696 |
+
"step": 11000
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"loss": 0.0951,
|
| 700 |
+
"learning_rate": 5.600000000000001e-06,
|
| 701 |
+
"epoch": 4.44,
|
| 702 |
+
"step": 11100
|
| 703 |
+
},
|
| 704 |
+
{
|
| 705 |
+
"loss": 0.059,
|
| 706 |
+
"learning_rate": 5.2e-06,
|
| 707 |
+
"epoch": 4.48,
|
| 708 |
+
"step": 11200
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"loss": 0.0859,
|
| 712 |
+
"learning_rate": 4.800000000000001e-06,
|
| 713 |
+
"epoch": 4.52,
|
| 714 |
+
"step": 11300
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"loss": 0.0459,
|
| 718 |
+
"learning_rate": 4.4e-06,
|
| 719 |
+
"epoch": 4.56,
|
| 720 |
+
"step": 11400
|
| 721 |
+
},
|
| 722 |
+
{
|
| 723 |
+
"loss": 0.0662,
|
| 724 |
+
"learning_rate": 4.000000000000001e-06,
|
| 725 |
+
"epoch": 4.6,
|
| 726 |
+
"step": 11500
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"loss": 0.0751,
|
| 730 |
+
"learning_rate": 3.6e-06,
|
| 731 |
+
"epoch": 4.64,
|
| 732 |
+
"step": 11600
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"loss": 0.0779,
|
| 736 |
+
"learning_rate": 3.2000000000000003e-06,
|
| 737 |
+
"epoch": 4.68,
|
| 738 |
+
"step": 11700
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"loss": 0.0626,
|
| 742 |
+
"learning_rate": 2.8000000000000003e-06,
|
| 743 |
+
"epoch": 4.72,
|
| 744 |
+
"step": 11800
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"loss": 0.0658,
|
| 748 |
+
"learning_rate": 2.4000000000000003e-06,
|
| 749 |
+
"epoch": 4.76,
|
| 750 |
+
"step": 11900
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"loss": 0.0771,
|
| 754 |
+
"learning_rate": 2.0000000000000003e-06,
|
| 755 |
+
"epoch": 4.8,
|
| 756 |
+
"step": 12000
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"loss": 0.055,
|
| 760 |
+
"learning_rate": 1.6000000000000001e-06,
|
| 761 |
+
"epoch": 4.84,
|
| 762 |
+
"step": 12100
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"loss": 0.0754,
|
| 766 |
+
"learning_rate": 1.2000000000000002e-06,
|
| 767 |
+
"epoch": 4.88,
|
| 768 |
+
"step": 12200
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"loss": 0.0384,
|
| 772 |
+
"learning_rate": 8.000000000000001e-07,
|
| 773 |
+
"epoch": 4.92,
|
| 774 |
+
"step": 12300
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"loss": 0.059,
|
| 778 |
+
"learning_rate": 4.0000000000000003e-07,
|
| 779 |
+
"epoch": 4.96,
|
| 780 |
+
"step": 12400
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"loss": 0.0588,
|
| 784 |
+
"learning_rate": 0.0,
|
| 785 |
+
"epoch": 5.0,
|
| 786 |
+
"step": 12500
|
| 787 |
+
},
|
| 788 |
+
{
|
| 789 |
+
"eval_loss": 0.6770138144493103,
|
| 790 |
+
"eval_accuracy": 0.8826,
|
| 791 |
+
"eval_runtime": 15.3605,
|
| 792 |
+
"eval_samples_per_second": 325.51,
|
| 793 |
+
"eval_steps_per_second": 40.689,
|
| 794 |
+
"epoch": 5.0,
|
| 795 |
+
"step": 12500
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"train_runtime": 1110.2182,
|
| 799 |
+
"train_samples_per_second": 90.072,
|
| 800 |
+
"train_steps_per_second": 11.259,
|
| 801 |
+
"total_flos": 7667181312000000.0,
|
| 802 |
+
"train_loss": 0.215138486328125,
|
| 803 |
+
"epoch": 5.0,
|
| 804 |
+
"step": 12500
|
| 805 |
+
}
|
| 806 |
+
]
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|