Upload 13 files
Browse files- config.json +52 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- optimizer.pt +3 -0
- preprocessor_config.json +26 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +51 -0
- tokenizer.json +0 -0
- tokenizer_config.json +80 -0
- trainer_state.json +913 -0
- training_args.bin +3 -0
- vocab.json +0 -0
config.json
ADDED
|
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "microsoft/layoutlmv3-base",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"LayoutLMv3ForTokenClassification"
|
| 5 |
+
],
|
| 6 |
+
"attention_probs_dropout_prob": 0.1,
|
| 7 |
+
"bos_token_id": 0,
|
| 8 |
+
"classifier_dropout": null,
|
| 9 |
+
"coordinate_size": 128,
|
| 10 |
+
"eos_token_id": 2,
|
| 11 |
+
"has_relative_attention_bias": true,
|
| 12 |
+
"has_spatial_attention_bias": true,
|
| 13 |
+
"hidden_act": "gelu",
|
| 14 |
+
"hidden_dropout_prob": 0.1,
|
| 15 |
+
"hidden_size": 768,
|
| 16 |
+
"id2label": {
|
| 17 |
+
"0": "B-Course",
|
| 18 |
+
"1": "I-Course",
|
| 19 |
+
"2": "GPA",
|
| 20 |
+
"3": "O"
|
| 21 |
+
},
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"input_size": 224,
|
| 24 |
+
"intermediate_size": 3072,
|
| 25 |
+
"label2id": {
|
| 26 |
+
"B-Course": 0,
|
| 27 |
+
"GPA": 2,
|
| 28 |
+
"I-Course": 1,
|
| 29 |
+
"O": 3
|
| 30 |
+
},
|
| 31 |
+
"layer_norm_eps": 1e-05,
|
| 32 |
+
"max_2d_position_embeddings": 1024,
|
| 33 |
+
"max_position_embeddings": 514,
|
| 34 |
+
"max_rel_2d_pos": 256,
|
| 35 |
+
"max_rel_pos": 128,
|
| 36 |
+
"model_type": "layoutlmv3",
|
| 37 |
+
"num_attention_heads": 12,
|
| 38 |
+
"num_channels": 3,
|
| 39 |
+
"num_hidden_layers": 12,
|
| 40 |
+
"pad_token_id": 1,
|
| 41 |
+
"patch_size": 16,
|
| 42 |
+
"rel_2d_pos_bins": 64,
|
| 43 |
+
"rel_pos_bins": 32,
|
| 44 |
+
"second_input_size": 112,
|
| 45 |
+
"shape_size": 128,
|
| 46 |
+
"text_embed": true,
|
| 47 |
+
"torch_dtype": "float32",
|
| 48 |
+
"transformers_version": "4.49.0.dev0",
|
| 49 |
+
"type_vocab_size": 1,
|
| 50 |
+
"visual_embed": true,
|
| 51 |
+
"vocab_size": 50265
|
| 52 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06eaab7c0a83cf04e312d85d1f3a67dc9717e46073d35ca620282c58d37aa29e
|
| 3 |
+
size 501346304
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61bf734f6fa01f8b11fb4f044257778edb2c9b61e7ba0cdda7d6543b36ed5d74
|
| 3 |
+
size 1002801594
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"apply_ocr": false,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.5,
|
| 8 |
+
0.5,
|
| 9 |
+
0.5
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "LayoutLMv3ImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.5,
|
| 14 |
+
0.5,
|
| 15 |
+
0.5
|
| 16 |
+
],
|
| 17 |
+
"ocr_lang": null,
|
| 18 |
+
"processor_class": "LayoutLMv3Processor",
|
| 19 |
+
"resample": 2,
|
| 20 |
+
"rescale_factor": 0.00392156862745098,
|
| 21 |
+
"size": {
|
| 22 |
+
"height": 224,
|
| 23 |
+
"width": 224
|
| 24 |
+
},
|
| 25 |
+
"tesseract_config": ""
|
| 26 |
+
}
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d8fb39e3828c3c150006a2da427e39d0a1b616782bb70378bdb3db112621fb3
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fcd60da393ff67ad2f08779377eeaa08189a6bf520f752442788825d9bce1449
|
| 3 |
+
size 1064
|
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.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,80 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 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": true,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
}
|
| 44 |
+
},
|
| 45 |
+
"apply_ocr": false,
|
| 46 |
+
"bos_token": "<s>",
|
| 47 |
+
"clean_up_tokenization_spaces": false,
|
| 48 |
+
"cls_token": "<s>",
|
| 49 |
+
"cls_token_box": [
|
| 50 |
+
0,
|
| 51 |
+
0,
|
| 52 |
+
0,
|
| 53 |
+
0
|
| 54 |
+
],
|
| 55 |
+
"eos_token": "</s>",
|
| 56 |
+
"errors": "replace",
|
| 57 |
+
"extra_special_tokens": {},
|
| 58 |
+
"mask_token": "<mask>",
|
| 59 |
+
"model_max_length": 512,
|
| 60 |
+
"only_label_first_subword": true,
|
| 61 |
+
"pad_token": "<pad>",
|
| 62 |
+
"pad_token_box": [
|
| 63 |
+
0,
|
| 64 |
+
0,
|
| 65 |
+
0,
|
| 66 |
+
0
|
| 67 |
+
],
|
| 68 |
+
"pad_token_label": -100,
|
| 69 |
+
"processor_class": "LayoutLMv3Processor",
|
| 70 |
+
"sep_token": "</s>",
|
| 71 |
+
"sep_token_box": [
|
| 72 |
+
0,
|
| 73 |
+
0,
|
| 74 |
+
0,
|
| 75 |
+
0
|
| 76 |
+
],
|
| 77 |
+
"tokenizer_class": "LayoutLMv3Tokenizer",
|
| 78 |
+
"trim_offsets": true,
|
| 79 |
+
"unk_token": "<unk>"
|
| 80 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,913 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 1.0,
|
| 3 |
+
"best_model_checkpoint": "test_long_tokens/checkpoint-70",
|
| 4 |
+
"epoch": 14.285714285714286,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 100,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.14285714285714285,
|
| 13 |
+
"grad_norm": 18.59529685974121,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 1.637,
|
| 16 |
+
"step": 1
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.2857142857142857,
|
| 20 |
+
"grad_norm": 20.817951202392578,
|
| 21 |
+
"learning_rate": 1e-05,
|
| 22 |
+
"loss": 1.6372,
|
| 23 |
+
"step": 2
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.42857142857142855,
|
| 27 |
+
"grad_norm": 19.524600982666016,
|
| 28 |
+
"learning_rate": 1.5e-05,
|
| 29 |
+
"loss": 1.4306,
|
| 30 |
+
"step": 3
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.5714285714285714,
|
| 34 |
+
"grad_norm": 15.0996675491333,
|
| 35 |
+
"learning_rate": 2e-05,
|
| 36 |
+
"loss": 1.2657,
|
| 37 |
+
"step": 4
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.7142857142857143,
|
| 41 |
+
"grad_norm": 12.507349967956543,
|
| 42 |
+
"learning_rate": 2.5e-05,
|
| 43 |
+
"loss": 0.8948,
|
| 44 |
+
"step": 5
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.8571428571428571,
|
| 48 |
+
"grad_norm": 8.167460441589355,
|
| 49 |
+
"learning_rate": 3e-05,
|
| 50 |
+
"loss": 0.5404,
|
| 51 |
+
"step": 6
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.0,
|
| 55 |
+
"grad_norm": 5.33146858215332,
|
| 56 |
+
"learning_rate": 3.5e-05,
|
| 57 |
+
"loss": 0.5374,
|
| 58 |
+
"step": 7
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 1.0,
|
| 62 |
+
"eval_accuracy": 0.8645276292335116,
|
| 63 |
+
"eval_f1": 0.0,
|
| 64 |
+
"eval_loss": 0.7161440253257751,
|
| 65 |
+
"eval_precision": 0.0,
|
| 66 |
+
"eval_recall": 0.0,
|
| 67 |
+
"eval_runtime": 0.2378,
|
| 68 |
+
"eval_samples_per_second": 12.618,
|
| 69 |
+
"eval_steps_per_second": 12.618,
|
| 70 |
+
"step": 7
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 1.1428571428571428,
|
| 74 |
+
"grad_norm": 2.557964324951172,
|
| 75 |
+
"learning_rate": 4e-05,
|
| 76 |
+
"loss": 0.2147,
|
| 77 |
+
"step": 8
|
| 78 |
+
},
|
| 79 |
+
{
|
| 80 |
+
"epoch": 1.2857142857142856,
|
| 81 |
+
"grad_norm": 4.4479289054870605,
|
| 82 |
+
"learning_rate": 4.5e-05,
|
| 83 |
+
"loss": 0.5833,
|
| 84 |
+
"step": 9
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 1.4285714285714286,
|
| 88 |
+
"grad_norm": 5.119785308837891,
|
| 89 |
+
"learning_rate": 5e-05,
|
| 90 |
+
"loss": 0.6062,
|
| 91 |
+
"step": 10
|
| 92 |
+
},
|
| 93 |
+
{
|
| 94 |
+
"epoch": 1.5714285714285714,
|
| 95 |
+
"grad_norm": 3.064371347427368,
|
| 96 |
+
"learning_rate": 4.9444444444444446e-05,
|
| 97 |
+
"loss": 0.451,
|
| 98 |
+
"step": 11
|
| 99 |
+
},
|
| 100 |
+
{
|
| 101 |
+
"epoch": 1.7142857142857144,
|
| 102 |
+
"grad_norm": 1.8660037517547607,
|
| 103 |
+
"learning_rate": 4.888888888888889e-05,
|
| 104 |
+
"loss": 0.3188,
|
| 105 |
+
"step": 12
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 1.8571428571428572,
|
| 109 |
+
"grad_norm": 2.083087205886841,
|
| 110 |
+
"learning_rate": 4.8333333333333334e-05,
|
| 111 |
+
"loss": 0.2287,
|
| 112 |
+
"step": 13
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 2.0,
|
| 116 |
+
"grad_norm": 2.0547335147857666,
|
| 117 |
+
"learning_rate": 4.7777777777777784e-05,
|
| 118 |
+
"loss": 0.3423,
|
| 119 |
+
"step": 14
|
| 120 |
+
},
|
| 121 |
+
{
|
| 122 |
+
"epoch": 2.0,
|
| 123 |
+
"eval_accuracy": 0.8645276292335116,
|
| 124 |
+
"eval_f1": 0.0,
|
| 125 |
+
"eval_loss": 0.459845632314682,
|
| 126 |
+
"eval_precision": 0.0,
|
| 127 |
+
"eval_recall": 0.0,
|
| 128 |
+
"eval_runtime": 0.2226,
|
| 129 |
+
"eval_samples_per_second": 13.474,
|
| 130 |
+
"eval_steps_per_second": 13.474,
|
| 131 |
+
"step": 14
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 2.142857142857143,
|
| 135 |
+
"grad_norm": 2.206693410873413,
|
| 136 |
+
"learning_rate": 4.722222222222222e-05,
|
| 137 |
+
"loss": 0.2449,
|
| 138 |
+
"step": 15
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 2.2857142857142856,
|
| 142 |
+
"grad_norm": 0.9722664952278137,
|
| 143 |
+
"learning_rate": 4.666666666666667e-05,
|
| 144 |
+
"loss": 0.1875,
|
| 145 |
+
"step": 16
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 2.4285714285714284,
|
| 149 |
+
"grad_norm": 1.500380039215088,
|
| 150 |
+
"learning_rate": 4.6111111111111115e-05,
|
| 151 |
+
"loss": 0.1429,
|
| 152 |
+
"step": 17
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 2.571428571428571,
|
| 156 |
+
"grad_norm": 1.9801063537597656,
|
| 157 |
+
"learning_rate": 4.555555555555556e-05,
|
| 158 |
+
"loss": 0.1752,
|
| 159 |
+
"step": 18
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 2.7142857142857144,
|
| 163 |
+
"grad_norm": 2.65030837059021,
|
| 164 |
+
"learning_rate": 4.5e-05,
|
| 165 |
+
"loss": 0.0763,
|
| 166 |
+
"step": 19
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 2.857142857142857,
|
| 170 |
+
"grad_norm": 3.4686992168426514,
|
| 171 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 172 |
+
"loss": 0.168,
|
| 173 |
+
"step": 20
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 3.0,
|
| 177 |
+
"grad_norm": 6.0364298820495605,
|
| 178 |
+
"learning_rate": 4.388888888888889e-05,
|
| 179 |
+
"loss": 0.1813,
|
| 180 |
+
"step": 21
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 3.0,
|
| 184 |
+
"eval_accuracy": 0.966131907308378,
|
| 185 |
+
"eval_f1": 0.9019607843137256,
|
| 186 |
+
"eval_loss": 0.14405852556228638,
|
| 187 |
+
"eval_precision": 0.8846153846153846,
|
| 188 |
+
"eval_recall": 0.92,
|
| 189 |
+
"eval_runtime": 0.2168,
|
| 190 |
+
"eval_samples_per_second": 13.839,
|
| 191 |
+
"eval_steps_per_second": 13.839,
|
| 192 |
+
"step": 21
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 3.142857142857143,
|
| 196 |
+
"grad_norm": 0.7663143873214722,
|
| 197 |
+
"learning_rate": 4.3333333333333334e-05,
|
| 198 |
+
"loss": 0.0552,
|
| 199 |
+
"step": 22
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 3.2857142857142856,
|
| 203 |
+
"grad_norm": 1.2191542387008667,
|
| 204 |
+
"learning_rate": 4.277777777777778e-05,
|
| 205 |
+
"loss": 0.1005,
|
| 206 |
+
"step": 23
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 3.4285714285714284,
|
| 210 |
+
"grad_norm": 7.446482181549072,
|
| 211 |
+
"learning_rate": 4.222222222222222e-05,
|
| 212 |
+
"loss": 0.0559,
|
| 213 |
+
"step": 24
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 3.571428571428571,
|
| 217 |
+
"grad_norm": 1.18604576587677,
|
| 218 |
+
"learning_rate": 4.166666666666667e-05,
|
| 219 |
+
"loss": 0.0494,
|
| 220 |
+
"step": 25
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 3.7142857142857144,
|
| 224 |
+
"grad_norm": 0.6873874664306641,
|
| 225 |
+
"learning_rate": 4.111111111111111e-05,
|
| 226 |
+
"loss": 0.0533,
|
| 227 |
+
"step": 26
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 3.857142857142857,
|
| 231 |
+
"grad_norm": 2.966907024383545,
|
| 232 |
+
"learning_rate": 4.055555555555556e-05,
|
| 233 |
+
"loss": 0.0625,
|
| 234 |
+
"step": 27
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 4.0,
|
| 238 |
+
"grad_norm": 3.066542863845825,
|
| 239 |
+
"learning_rate": 4e-05,
|
| 240 |
+
"loss": 0.0734,
|
| 241 |
+
"step": 28
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 4.0,
|
| 245 |
+
"eval_accuracy": 0.9732620320855615,
|
| 246 |
+
"eval_f1": 0.8000000000000002,
|
| 247 |
+
"eval_loss": 0.13226450979709625,
|
| 248 |
+
"eval_precision": 0.8,
|
| 249 |
+
"eval_recall": 0.8,
|
| 250 |
+
"eval_runtime": 0.2294,
|
| 251 |
+
"eval_samples_per_second": 13.077,
|
| 252 |
+
"eval_steps_per_second": 13.077,
|
| 253 |
+
"step": 28
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 4.142857142857143,
|
| 257 |
+
"grad_norm": 0.8713329434394836,
|
| 258 |
+
"learning_rate": 3.944444444444445e-05,
|
| 259 |
+
"loss": 0.0673,
|
| 260 |
+
"step": 29
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 4.285714285714286,
|
| 264 |
+
"grad_norm": 0.306024968624115,
|
| 265 |
+
"learning_rate": 3.888888888888889e-05,
|
| 266 |
+
"loss": 0.0146,
|
| 267 |
+
"step": 30
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 4.428571428571429,
|
| 271 |
+
"grad_norm": 0.3102547526359558,
|
| 272 |
+
"learning_rate": 3.8333333333333334e-05,
|
| 273 |
+
"loss": 0.0169,
|
| 274 |
+
"step": 31
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 4.571428571428571,
|
| 278 |
+
"grad_norm": 5.933145046234131,
|
| 279 |
+
"learning_rate": 3.777777777777778e-05,
|
| 280 |
+
"loss": 0.0753,
|
| 281 |
+
"step": 32
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 4.714285714285714,
|
| 285 |
+
"grad_norm": 1.7290794849395752,
|
| 286 |
+
"learning_rate": 3.722222222222222e-05,
|
| 287 |
+
"loss": 0.0668,
|
| 288 |
+
"step": 33
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 4.857142857142857,
|
| 292 |
+
"grad_norm": 8.295025825500488,
|
| 293 |
+
"learning_rate": 3.6666666666666666e-05,
|
| 294 |
+
"loss": 0.0786,
|
| 295 |
+
"step": 34
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 5.0,
|
| 299 |
+
"grad_norm": 0.47509345412254333,
|
| 300 |
+
"learning_rate": 3.611111111111111e-05,
|
| 301 |
+
"loss": 0.0124,
|
| 302 |
+
"step": 35
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 5.0,
|
| 306 |
+
"eval_accuracy": 0.9928698752228164,
|
| 307 |
+
"eval_f1": 0.8235294117647058,
|
| 308 |
+
"eval_loss": 0.0685623362660408,
|
| 309 |
+
"eval_precision": 0.8076923076923077,
|
| 310 |
+
"eval_recall": 0.84,
|
| 311 |
+
"eval_runtime": 0.2188,
|
| 312 |
+
"eval_samples_per_second": 13.709,
|
| 313 |
+
"eval_steps_per_second": 13.709,
|
| 314 |
+
"step": 35
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 5.142857142857143,
|
| 318 |
+
"grad_norm": 1.3178348541259766,
|
| 319 |
+
"learning_rate": 3.555555555555556e-05,
|
| 320 |
+
"loss": 0.0303,
|
| 321 |
+
"step": 36
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 5.285714285714286,
|
| 325 |
+
"grad_norm": 2.2010915279388428,
|
| 326 |
+
"learning_rate": 3.5e-05,
|
| 327 |
+
"loss": 0.045,
|
| 328 |
+
"step": 37
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 5.428571428571429,
|
| 332 |
+
"grad_norm": 1.1045790910720825,
|
| 333 |
+
"learning_rate": 3.444444444444445e-05,
|
| 334 |
+
"loss": 0.0145,
|
| 335 |
+
"step": 38
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 5.571428571428571,
|
| 339 |
+
"grad_norm": 1.0724176168441772,
|
| 340 |
+
"learning_rate": 3.388888888888889e-05,
|
| 341 |
+
"loss": 0.0063,
|
| 342 |
+
"step": 39
|
| 343 |
+
},
|
| 344 |
+
{
|
| 345 |
+
"epoch": 5.714285714285714,
|
| 346 |
+
"grad_norm": 0.7634330987930298,
|
| 347 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 348 |
+
"loss": 0.0176,
|
| 349 |
+
"step": 40
|
| 350 |
+
},
|
| 351 |
+
{
|
| 352 |
+
"epoch": 5.857142857142857,
|
| 353 |
+
"grad_norm": 0.48025190830230713,
|
| 354 |
+
"learning_rate": 3.277777777777778e-05,
|
| 355 |
+
"loss": 0.0228,
|
| 356 |
+
"step": 41
|
| 357 |
+
},
|
| 358 |
+
{
|
| 359 |
+
"epoch": 6.0,
|
| 360 |
+
"grad_norm": 0.21735815703868866,
|
| 361 |
+
"learning_rate": 3.222222222222223e-05,
|
| 362 |
+
"loss": 0.0034,
|
| 363 |
+
"step": 42
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 6.0,
|
| 367 |
+
"eval_accuracy": 0.983957219251337,
|
| 368 |
+
"eval_f1": 0.7058823529411765,
|
| 369 |
+
"eval_loss": 0.16237980127334595,
|
| 370 |
+
"eval_precision": 0.6923076923076923,
|
| 371 |
+
"eval_recall": 0.72,
|
| 372 |
+
"eval_runtime": 0.2281,
|
| 373 |
+
"eval_samples_per_second": 13.15,
|
| 374 |
+
"eval_steps_per_second": 13.15,
|
| 375 |
+
"step": 42
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 6.142857142857143,
|
| 379 |
+
"grad_norm": 1.1637978553771973,
|
| 380 |
+
"learning_rate": 3.1666666666666666e-05,
|
| 381 |
+
"loss": 0.0137,
|
| 382 |
+
"step": 43
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 6.285714285714286,
|
| 386 |
+
"grad_norm": 0.21785947680473328,
|
| 387 |
+
"learning_rate": 3.111111111111111e-05,
|
| 388 |
+
"loss": 0.0039,
|
| 389 |
+
"step": 44
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 6.428571428571429,
|
| 393 |
+
"grad_norm": 20.79886245727539,
|
| 394 |
+
"learning_rate": 3.055555555555556e-05,
|
| 395 |
+
"loss": 0.1387,
|
| 396 |
+
"step": 45
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 6.571428571428571,
|
| 400 |
+
"grad_norm": 7.047394752502441,
|
| 401 |
+
"learning_rate": 3e-05,
|
| 402 |
+
"loss": 0.019,
|
| 403 |
+
"step": 46
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 6.714285714285714,
|
| 407 |
+
"grad_norm": 0.3814934194087982,
|
| 408 |
+
"learning_rate": 2.9444444444444448e-05,
|
| 409 |
+
"loss": 0.0059,
|
| 410 |
+
"step": 47
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 6.857142857142857,
|
| 414 |
+
"grad_norm": 0.4642070233821869,
|
| 415 |
+
"learning_rate": 2.8888888888888888e-05,
|
| 416 |
+
"loss": 0.005,
|
| 417 |
+
"step": 48
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 7.0,
|
| 421 |
+
"grad_norm": 0.06280206888914108,
|
| 422 |
+
"learning_rate": 2.8333333333333335e-05,
|
| 423 |
+
"loss": 0.0023,
|
| 424 |
+
"step": 49
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 7.0,
|
| 428 |
+
"eval_accuracy": 0.9946524064171123,
|
| 429 |
+
"eval_f1": 0.830188679245283,
|
| 430 |
+
"eval_loss": 0.018056461587548256,
|
| 431 |
+
"eval_precision": 0.7857142857142857,
|
| 432 |
+
"eval_recall": 0.88,
|
| 433 |
+
"eval_runtime": 0.2418,
|
| 434 |
+
"eval_samples_per_second": 12.409,
|
| 435 |
+
"eval_steps_per_second": 12.409,
|
| 436 |
+
"step": 49
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 7.142857142857143,
|
| 440 |
+
"grad_norm": 0.042585261166095734,
|
| 441 |
+
"learning_rate": 2.777777777777778e-05,
|
| 442 |
+
"loss": 0.002,
|
| 443 |
+
"step": 50
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 7.285714285714286,
|
| 447 |
+
"grad_norm": 3.1652538776397705,
|
| 448 |
+
"learning_rate": 2.7222222222222223e-05,
|
| 449 |
+
"loss": 0.0085,
|
| 450 |
+
"step": 51
|
| 451 |
+
},
|
| 452 |
+
{
|
| 453 |
+
"epoch": 7.428571428571429,
|
| 454 |
+
"grad_norm": 0.997791051864624,
|
| 455 |
+
"learning_rate": 2.6666666666666667e-05,
|
| 456 |
+
"loss": 0.0154,
|
| 457 |
+
"step": 52
|
| 458 |
+
},
|
| 459 |
+
{
|
| 460 |
+
"epoch": 7.571428571428571,
|
| 461 |
+
"grad_norm": 0.2884855568408966,
|
| 462 |
+
"learning_rate": 2.6111111111111114e-05,
|
| 463 |
+
"loss": 0.0021,
|
| 464 |
+
"step": 53
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"epoch": 7.714285714285714,
|
| 468 |
+
"grad_norm": 0.39060717821121216,
|
| 469 |
+
"learning_rate": 2.5555555555555554e-05,
|
| 470 |
+
"loss": 0.0026,
|
| 471 |
+
"step": 54
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 7.857142857142857,
|
| 475 |
+
"grad_norm": 15.578678131103516,
|
| 476 |
+
"learning_rate": 2.5e-05,
|
| 477 |
+
"loss": 0.031,
|
| 478 |
+
"step": 55
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 8.0,
|
| 482 |
+
"grad_norm": 0.1004723384976387,
|
| 483 |
+
"learning_rate": 2.4444444444444445e-05,
|
| 484 |
+
"loss": 0.0023,
|
| 485 |
+
"step": 56
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 8.0,
|
| 489 |
+
"eval_accuracy": 0.9946524064171123,
|
| 490 |
+
"eval_f1": 0.8627450980392156,
|
| 491 |
+
"eval_loss": 0.054031386971473694,
|
| 492 |
+
"eval_precision": 0.8461538461538461,
|
| 493 |
+
"eval_recall": 0.88,
|
| 494 |
+
"eval_runtime": 0.3115,
|
| 495 |
+
"eval_samples_per_second": 9.631,
|
| 496 |
+
"eval_steps_per_second": 9.631,
|
| 497 |
+
"step": 56
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 8.142857142857142,
|
| 501 |
+
"grad_norm": 0.5730704665184021,
|
| 502 |
+
"learning_rate": 2.3888888888888892e-05,
|
| 503 |
+
"loss": 0.005,
|
| 504 |
+
"step": 57
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 8.285714285714286,
|
| 508 |
+
"grad_norm": 0.08043497800827026,
|
| 509 |
+
"learning_rate": 2.3333333333333336e-05,
|
| 510 |
+
"loss": 0.0023,
|
| 511 |
+
"step": 58
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 8.428571428571429,
|
| 515 |
+
"grad_norm": 0.03008083440363407,
|
| 516 |
+
"learning_rate": 2.277777777777778e-05,
|
| 517 |
+
"loss": 0.0012,
|
| 518 |
+
"step": 59
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 8.571428571428571,
|
| 522 |
+
"grad_norm": 0.03248002007603645,
|
| 523 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 524 |
+
"loss": 0.0008,
|
| 525 |
+
"step": 60
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 8.714285714285714,
|
| 529 |
+
"grad_norm": 0.04838703200221062,
|
| 530 |
+
"learning_rate": 2.1666666666666667e-05,
|
| 531 |
+
"loss": 0.0013,
|
| 532 |
+
"step": 61
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 8.857142857142858,
|
| 536 |
+
"grad_norm": 0.33141571283340454,
|
| 537 |
+
"learning_rate": 2.111111111111111e-05,
|
| 538 |
+
"loss": 0.0022,
|
| 539 |
+
"step": 62
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 9.0,
|
| 543 |
+
"grad_norm": 1.7117937803268433,
|
| 544 |
+
"learning_rate": 2.0555555555555555e-05,
|
| 545 |
+
"loss": 0.0069,
|
| 546 |
+
"step": 63
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 9.0,
|
| 550 |
+
"eval_accuracy": 0.9269162210338681,
|
| 551 |
+
"eval_f1": 0.5,
|
| 552 |
+
"eval_loss": 0.5584124326705933,
|
| 553 |
+
"eval_precision": 0.5789473684210527,
|
| 554 |
+
"eval_recall": 0.44,
|
| 555 |
+
"eval_runtime": 0.2368,
|
| 556 |
+
"eval_samples_per_second": 12.67,
|
| 557 |
+
"eval_steps_per_second": 12.67,
|
| 558 |
+
"step": 63
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 9.142857142857142,
|
| 562 |
+
"grad_norm": 0.3541106581687927,
|
| 563 |
+
"learning_rate": 2e-05,
|
| 564 |
+
"loss": 0.003,
|
| 565 |
+
"step": 64
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"epoch": 9.285714285714286,
|
| 569 |
+
"grad_norm": 6.2997145652771,
|
| 570 |
+
"learning_rate": 1.9444444444444445e-05,
|
| 571 |
+
"loss": 0.0145,
|
| 572 |
+
"step": 65
|
| 573 |
+
},
|
| 574 |
+
{
|
| 575 |
+
"epoch": 9.428571428571429,
|
| 576 |
+
"grad_norm": 3.1364083290100098,
|
| 577 |
+
"learning_rate": 1.888888888888889e-05,
|
| 578 |
+
"loss": 0.0043,
|
| 579 |
+
"step": 66
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 9.571428571428571,
|
| 583 |
+
"grad_norm": 0.018303165212273598,
|
| 584 |
+
"learning_rate": 1.8333333333333333e-05,
|
| 585 |
+
"loss": 0.0007,
|
| 586 |
+
"step": 67
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 9.714285714285714,
|
| 590 |
+
"grad_norm": 0.06226564571261406,
|
| 591 |
+
"learning_rate": 1.777777777777778e-05,
|
| 592 |
+
"loss": 0.0011,
|
| 593 |
+
"step": 68
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 9.857142857142858,
|
| 597 |
+
"grad_norm": 0.18134748935699463,
|
| 598 |
+
"learning_rate": 1.7222222222222224e-05,
|
| 599 |
+
"loss": 0.0014,
|
| 600 |
+
"step": 69
|
| 601 |
+
},
|
| 602 |
+
{
|
| 603 |
+
"epoch": 10.0,
|
| 604 |
+
"grad_norm": 0.013242754153907299,
|
| 605 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 606 |
+
"loss": 0.0006,
|
| 607 |
+
"step": 70
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"epoch": 10.0,
|
| 611 |
+
"eval_accuracy": 1.0,
|
| 612 |
+
"eval_f1": 1.0,
|
| 613 |
+
"eval_loss": 0.004223768133670092,
|
| 614 |
+
"eval_precision": 1.0,
|
| 615 |
+
"eval_recall": 1.0,
|
| 616 |
+
"eval_runtime": 0.2664,
|
| 617 |
+
"eval_samples_per_second": 11.263,
|
| 618 |
+
"eval_steps_per_second": 11.263,
|
| 619 |
+
"step": 70
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 10.142857142857142,
|
| 623 |
+
"grad_norm": 0.5124610662460327,
|
| 624 |
+
"learning_rate": 1.6111111111111115e-05,
|
| 625 |
+
"loss": 0.0017,
|
| 626 |
+
"step": 71
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 10.285714285714286,
|
| 630 |
+
"grad_norm": 0.014037979766726494,
|
| 631 |
+
"learning_rate": 1.5555555555555555e-05,
|
| 632 |
+
"loss": 0.0008,
|
| 633 |
+
"step": 72
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 10.428571428571429,
|
| 637 |
+
"grad_norm": 0.020040445029735565,
|
| 638 |
+
"learning_rate": 1.5e-05,
|
| 639 |
+
"loss": 0.001,
|
| 640 |
+
"step": 73
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 10.571428571428571,
|
| 644 |
+
"grad_norm": 0.0177422147244215,
|
| 645 |
+
"learning_rate": 1.4444444444444444e-05,
|
| 646 |
+
"loss": 0.0007,
|
| 647 |
+
"step": 74
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 10.714285714285714,
|
| 651 |
+
"grad_norm": 0.02175714634358883,
|
| 652 |
+
"learning_rate": 1.388888888888889e-05,
|
| 653 |
+
"loss": 0.0011,
|
| 654 |
+
"step": 75
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 10.857142857142858,
|
| 658 |
+
"grad_norm": 0.016904808580875397,
|
| 659 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 660 |
+
"loss": 0.0009,
|
| 661 |
+
"step": 76
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 11.0,
|
| 665 |
+
"grad_norm": 0.7300955653190613,
|
| 666 |
+
"learning_rate": 1.2777777777777777e-05,
|
| 667 |
+
"loss": 0.0026,
|
| 668 |
+
"step": 77
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 11.0,
|
| 672 |
+
"eval_accuracy": 1.0,
|
| 673 |
+
"eval_f1": 1.0,
|
| 674 |
+
"eval_loss": 0.0016724281013011932,
|
| 675 |
+
"eval_precision": 1.0,
|
| 676 |
+
"eval_recall": 1.0,
|
| 677 |
+
"eval_runtime": 0.2244,
|
| 678 |
+
"eval_samples_per_second": 13.369,
|
| 679 |
+
"eval_steps_per_second": 13.369,
|
| 680 |
+
"step": 77
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 11.142857142857142,
|
| 684 |
+
"grad_norm": 0.01708046905696392,
|
| 685 |
+
"learning_rate": 1.2222222222222222e-05,
|
| 686 |
+
"loss": 0.001,
|
| 687 |
+
"step": 78
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 11.285714285714286,
|
| 691 |
+
"grad_norm": 0.025557199493050575,
|
| 692 |
+
"learning_rate": 1.1666666666666668e-05,
|
| 693 |
+
"loss": 0.0011,
|
| 694 |
+
"step": 79
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 11.428571428571429,
|
| 698 |
+
"grad_norm": 0.015760347247123718,
|
| 699 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 700 |
+
"loss": 0.0008,
|
| 701 |
+
"step": 80
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 11.571428571428571,
|
| 705 |
+
"grad_norm": 0.4625304341316223,
|
| 706 |
+
"learning_rate": 1.0555555555555555e-05,
|
| 707 |
+
"loss": 0.002,
|
| 708 |
+
"step": 81
|
| 709 |
+
},
|
| 710 |
+
{
|
| 711 |
+
"epoch": 11.714285714285714,
|
| 712 |
+
"grad_norm": 0.02315388433635235,
|
| 713 |
+
"learning_rate": 1e-05,
|
| 714 |
+
"loss": 0.0009,
|
| 715 |
+
"step": 82
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"epoch": 11.857142857142858,
|
| 719 |
+
"grad_norm": 0.013032798655331135,
|
| 720 |
+
"learning_rate": 9.444444444444445e-06,
|
| 721 |
+
"loss": 0.0006,
|
| 722 |
+
"step": 83
|
| 723 |
+
},
|
| 724 |
+
{
|
| 725 |
+
"epoch": 12.0,
|
| 726 |
+
"grad_norm": 0.01681060716509819,
|
| 727 |
+
"learning_rate": 8.88888888888889e-06,
|
| 728 |
+
"loss": 0.0007,
|
| 729 |
+
"step": 84
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 12.0,
|
| 733 |
+
"eval_accuracy": 0.9982174688057041,
|
| 734 |
+
"eval_f1": 0.9411764705882353,
|
| 735 |
+
"eval_loss": 0.006076255813241005,
|
| 736 |
+
"eval_precision": 0.9230769230769231,
|
| 737 |
+
"eval_recall": 0.96,
|
| 738 |
+
"eval_runtime": 0.2313,
|
| 739 |
+
"eval_samples_per_second": 12.968,
|
| 740 |
+
"eval_steps_per_second": 12.968,
|
| 741 |
+
"step": 84
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 12.142857142857142,
|
| 745 |
+
"grad_norm": 0.021738462150096893,
|
| 746 |
+
"learning_rate": 8.333333333333334e-06,
|
| 747 |
+
"loss": 0.0012,
|
| 748 |
+
"step": 85
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 12.285714285714286,
|
| 752 |
+
"grad_norm": 0.07413913309574127,
|
| 753 |
+
"learning_rate": 7.777777777777777e-06,
|
| 754 |
+
"loss": 0.001,
|
| 755 |
+
"step": 86
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 12.428571428571429,
|
| 759 |
+
"grad_norm": 0.015694081783294678,
|
| 760 |
+
"learning_rate": 7.222222222222222e-06,
|
| 761 |
+
"loss": 0.0007,
|
| 762 |
+
"step": 87
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 12.571428571428571,
|
| 766 |
+
"grad_norm": 0.07455814629793167,
|
| 767 |
+
"learning_rate": 6.666666666666667e-06,
|
| 768 |
+
"loss": 0.0011,
|
| 769 |
+
"step": 88
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 12.714285714285714,
|
| 773 |
+
"grad_norm": 2.512777805328369,
|
| 774 |
+
"learning_rate": 6.111111111111111e-06,
|
| 775 |
+
"loss": 0.002,
|
| 776 |
+
"step": 89
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 12.857142857142858,
|
| 780 |
+
"grad_norm": 0.020945778116583824,
|
| 781 |
+
"learning_rate": 5.555555555555556e-06,
|
| 782 |
+
"loss": 0.0008,
|
| 783 |
+
"step": 90
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 13.0,
|
| 787 |
+
"grad_norm": 0.014726142399013042,
|
| 788 |
+
"learning_rate": 5e-06,
|
| 789 |
+
"loss": 0.0006,
|
| 790 |
+
"step": 91
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 13.0,
|
| 794 |
+
"eval_accuracy": 0.9982174688057041,
|
| 795 |
+
"eval_f1": 0.9411764705882353,
|
| 796 |
+
"eval_loss": 0.010821976698935032,
|
| 797 |
+
"eval_precision": 0.9230769230769231,
|
| 798 |
+
"eval_recall": 0.96,
|
| 799 |
+
"eval_runtime": 0.2328,
|
| 800 |
+
"eval_samples_per_second": 12.888,
|
| 801 |
+
"eval_steps_per_second": 12.888,
|
| 802 |
+
"step": 91
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 13.142857142857142,
|
| 806 |
+
"grad_norm": 0.022652102634310722,
|
| 807 |
+
"learning_rate": 4.444444444444445e-06,
|
| 808 |
+
"loss": 0.0007,
|
| 809 |
+
"step": 92
|
| 810 |
+
},
|
| 811 |
+
{
|
| 812 |
+
"epoch": 13.285714285714286,
|
| 813 |
+
"grad_norm": 0.0192624032497406,
|
| 814 |
+
"learning_rate": 3.888888888888889e-06,
|
| 815 |
+
"loss": 0.0009,
|
| 816 |
+
"step": 93
|
| 817 |
+
},
|
| 818 |
+
{
|
| 819 |
+
"epoch": 13.428571428571429,
|
| 820 |
+
"grad_norm": 0.03646668419241905,
|
| 821 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 822 |
+
"loss": 0.0009,
|
| 823 |
+
"step": 94
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"epoch": 13.571428571428571,
|
| 827 |
+
"grad_norm": 0.02297368273139,
|
| 828 |
+
"learning_rate": 2.777777777777778e-06,
|
| 829 |
+
"loss": 0.0006,
|
| 830 |
+
"step": 95
|
| 831 |
+
},
|
| 832 |
+
{
|
| 833 |
+
"epoch": 13.714285714285714,
|
| 834 |
+
"grad_norm": 0.013909080997109413,
|
| 835 |
+
"learning_rate": 2.2222222222222225e-06,
|
| 836 |
+
"loss": 0.0006,
|
| 837 |
+
"step": 96
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 13.857142857142858,
|
| 841 |
+
"grad_norm": 0.021894708275794983,
|
| 842 |
+
"learning_rate": 1.6666666666666667e-06,
|
| 843 |
+
"loss": 0.0008,
|
| 844 |
+
"step": 97
|
| 845 |
+
},
|
| 846 |
+
{
|
| 847 |
+
"epoch": 14.0,
|
| 848 |
+
"grad_norm": 0.019053662195801735,
|
| 849 |
+
"learning_rate": 1.1111111111111112e-06,
|
| 850 |
+
"loss": 0.0011,
|
| 851 |
+
"step": 98
|
| 852 |
+
},
|
| 853 |
+
{
|
| 854 |
+
"epoch": 14.0,
|
| 855 |
+
"eval_accuracy": 0.9982174688057041,
|
| 856 |
+
"eval_f1": 0.9411764705882353,
|
| 857 |
+
"eval_loss": 0.011927765794098377,
|
| 858 |
+
"eval_precision": 0.9230769230769231,
|
| 859 |
+
"eval_recall": 0.96,
|
| 860 |
+
"eval_runtime": 0.2367,
|
| 861 |
+
"eval_samples_per_second": 12.675,
|
| 862 |
+
"eval_steps_per_second": 12.675,
|
| 863 |
+
"step": 98
|
| 864 |
+
},
|
| 865 |
+
{
|
| 866 |
+
"epoch": 14.142857142857142,
|
| 867 |
+
"grad_norm": 0.015299996361136436,
|
| 868 |
+
"learning_rate": 5.555555555555556e-07,
|
| 869 |
+
"loss": 0.0007,
|
| 870 |
+
"step": 99
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 14.285714285714286,
|
| 874 |
+
"grad_norm": 0.06155708432197571,
|
| 875 |
+
"learning_rate": 0.0,
|
| 876 |
+
"loss": 0.0009,
|
| 877 |
+
"step": 100
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 14.285714285714286,
|
| 881 |
+
"eval_accuracy": 0.9982174688057041,
|
| 882 |
+
"eval_f1": 0.9411764705882353,
|
| 883 |
+
"eval_loss": 0.011938165873289108,
|
| 884 |
+
"eval_precision": 0.9230769230769231,
|
| 885 |
+
"eval_recall": 0.96,
|
| 886 |
+
"eval_runtime": 0.459,
|
| 887 |
+
"eval_samples_per_second": 6.535,
|
| 888 |
+
"eval_steps_per_second": 6.535,
|
| 889 |
+
"step": 100
|
| 890 |
+
}
|
| 891 |
+
],
|
| 892 |
+
"logging_steps": 1,
|
| 893 |
+
"max_steps": 100,
|
| 894 |
+
"num_input_tokens_seen": 0,
|
| 895 |
+
"num_train_epochs": 15,
|
| 896 |
+
"save_steps": 500,
|
| 897 |
+
"stateful_callbacks": {
|
| 898 |
+
"TrainerControl": {
|
| 899 |
+
"args": {
|
| 900 |
+
"should_epoch_stop": false,
|
| 901 |
+
"should_evaluate": false,
|
| 902 |
+
"should_log": false,
|
| 903 |
+
"should_save": true,
|
| 904 |
+
"should_training_stop": true
|
| 905 |
+
},
|
| 906 |
+
"attributes": {}
|
| 907 |
+
}
|
| 908 |
+
},
|
| 909 |
+
"total_flos": 52719651225600.0,
|
| 910 |
+
"train_batch_size": 1,
|
| 911 |
+
"trial_name": null,
|
| 912 |
+
"trial_params": null
|
| 913 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:81f1ef4de374f0e50f7535fc7aef0393aeb38851bfb2b5f2a7bad6c19b9a6811
|
| 3 |
+
size 5304
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|