anjikya07 commited on
Commit
b04e243
·
verified ·
1 Parent(s): 1e4a67a

Upload folder using huggingface_hub

Browse files
config.json ADDED
@@ -0,0 +1,173 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "microsoft/trocr-base-handwritten",
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_attn_implementation_autoset": false,
8
+ "_name_or_path": "",
9
+ "activation_dropout": 0.0,
10
+ "activation_function": "gelu",
11
+ "add_cross_attention": true,
12
+ "architectures": null,
13
+ "attention_dropout": 0.0,
14
+ "bad_words_ids": null,
15
+ "begin_suppress_tokens": null,
16
+ "bos_token_id": 0,
17
+ "chunk_size_feed_forward": 0,
18
+ "classifier_dropout": 0.0,
19
+ "cross_attention_hidden_size": 768,
20
+ "d_model": 1024,
21
+ "decoder_attention_heads": 16,
22
+ "decoder_ffn_dim": 4096,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 12,
25
+ "decoder_start_token_id": 2,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "dropout": 0.1,
29
+ "early_stopping": false,
30
+ "encoder_no_repeat_ngram_size": 0,
31
+ "eos_token_id": 2,
32
+ "exponential_decay_length_penalty": null,
33
+ "finetuning_task": null,
34
+ "forced_bos_token_id": null,
35
+ "forced_eos_token_id": null,
36
+ "id2label": {
37
+ "0": "LABEL_0",
38
+ "1": "LABEL_1"
39
+ },
40
+ "init_std": 0.02,
41
+ "is_decoder": true,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "layernorm_embedding": true,
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 512,
51
+ "min_length": 0,
52
+ "model_type": "trocr",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_beam_groups": 1,
55
+ "num_beams": 1,
56
+ "num_return_sequences": 1,
57
+ "output_attentions": false,
58
+ "output_hidden_states": false,
59
+ "output_scores": false,
60
+ "pad_token_id": 1,
61
+ "prefix": null,
62
+ "problem_type": null,
63
+ "pruned_heads": {},
64
+ "remove_invalid_values": false,
65
+ "repetition_penalty": 1.0,
66
+ "return_dict": true,
67
+ "return_dict_in_generate": false,
68
+ "scale_embedding": false,
69
+ "sep_token_id": null,
70
+ "suppress_tokens": null,
71
+ "task_specific_params": null,
72
+ "temperature": 1.0,
73
+ "tf_legacy_loss": false,
74
+ "tie_encoder_decoder": false,
75
+ "tie_word_embeddings": true,
76
+ "tokenizer_class": null,
77
+ "top_k": 50,
78
+ "top_p": 1.0,
79
+ "torch_dtype": null,
80
+ "torchscript": false,
81
+ "typical_p": 1.0,
82
+ "use_bfloat16": false,
83
+ "use_cache": false,
84
+ "use_learned_position_embeddings": true,
85
+ "vocab_size": 50265
86
+ },
87
+ "decoder_start_token_id": 0,
88
+ "encoder": {
89
+ "_attn_implementation_autoset": false,
90
+ "_name_or_path": "",
91
+ "add_cross_attention": false,
92
+ "architectures": null,
93
+ "attention_probs_dropout_prob": 0.0,
94
+ "bad_words_ids": null,
95
+ "begin_suppress_tokens": null,
96
+ "bos_token_id": null,
97
+ "chunk_size_feed_forward": 0,
98
+ "cross_attention_hidden_size": null,
99
+ "decoder_start_token_id": null,
100
+ "diversity_penalty": 0.0,
101
+ "do_sample": false,
102
+ "early_stopping": false,
103
+ "encoder_no_repeat_ngram_size": 0,
104
+ "encoder_stride": 16,
105
+ "eos_token_id": null,
106
+ "exponential_decay_length_penalty": null,
107
+ "finetuning_task": null,
108
+ "forced_bos_token_id": null,
109
+ "forced_eos_token_id": null,
110
+ "hidden_act": "gelu",
111
+ "hidden_dropout_prob": 0.0,
112
+ "hidden_size": 768,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "image_size": 384,
118
+ "initializer_range": 0.02,
119
+ "intermediate_size": 3072,
120
+ "is_decoder": false,
121
+ "is_encoder_decoder": false,
122
+ "label2id": {
123
+ "LABEL_0": 0,
124
+ "LABEL_1": 1
125
+ },
126
+ "layer_norm_eps": 1e-12,
127
+ "length_penalty": 1.0,
128
+ "max_length": 20,
129
+ "min_length": 0,
130
+ "model_type": "vit",
131
+ "no_repeat_ngram_size": 0,
132
+ "num_attention_heads": 12,
133
+ "num_beam_groups": 1,
134
+ "num_beams": 1,
135
+ "num_channels": 3,
136
+ "num_hidden_layers": 12,
137
+ "num_return_sequences": 1,
138
+ "output_attentions": false,
139
+ "output_hidden_states": false,
140
+ "output_scores": false,
141
+ "pad_token_id": null,
142
+ "patch_size": 16,
143
+ "prefix": null,
144
+ "problem_type": null,
145
+ "pruned_heads": {},
146
+ "qkv_bias": false,
147
+ "remove_invalid_values": false,
148
+ "repetition_penalty": 1.0,
149
+ "return_dict": true,
150
+ "return_dict_in_generate": false,
151
+ "sep_token_id": null,
152
+ "suppress_tokens": null,
153
+ "task_specific_params": null,
154
+ "temperature": 1.0,
155
+ "tf_legacy_loss": false,
156
+ "tie_encoder_decoder": false,
157
+ "tie_word_embeddings": true,
158
+ "tokenizer_class": null,
159
+ "top_k": 50,
160
+ "top_p": 1.0,
161
+ "torch_dtype": null,
162
+ "torchscript": false,
163
+ "typical_p": 1.0,
164
+ "use_bfloat16": false
165
+ },
166
+ "is_encoder_decoder": true,
167
+ "model_type": "vision-encoder-decoder",
168
+ "pad_token_id": 1,
169
+ "processor_class": "TrOCRProcessor",
170
+ "tie_word_embeddings": false,
171
+ "torch_dtype": "float32",
172
+ "transformers_version": "4.46.3"
173
+ }
generation_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "decoder_start_token_id": 2,
5
+ "eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.46.3",
8
+ "use_cache": false
9
+ }
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 sha256:9d0864b5cf3951805142afc7e4bd12aa596343c1c0f2e0ba9bab7f4488024797
3
+ size 1335747032
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6f539a989eff32b0042a7125b35451e93cefdcff01b5b4b5b6d9fc0e8f849d1
3
+ size 2666915017
preprocessor_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "do_rescale": true,
4
+ "do_resize": true,
5
+ "image_mean": [
6
+ 0.5,
7
+ 0.5,
8
+ 0.5
9
+ ],
10
+ "image_processor_type": "ViTImageProcessor",
11
+ "image_std": [
12
+ 0.5,
13
+ 0.5,
14
+ 0.5
15
+ ],
16
+ "processor_class": "TrOCRProcessor",
17
+ "resample": 2,
18
+ "rescale_factor": 0.00392156862745098,
19
+ "size": {
20
+ "height": 384,
21
+ "width": 384
22
+ }
23
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0de23271066ca64748bcdffdff0925f8c4f7312284e7a166681ab5394cd92665
3
+ size 13547
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d31953a7317079e12954d04c4974cd6b9586e0ed412382f3df798c0960b96d72
3
+ size 623
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 +1,58 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": true,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ }
44
+ },
45
+ "bos_token": "<s>",
46
+ "clean_up_tokenization_spaces": false,
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
+ "processor_class": "TrOCRProcessor",
54
+ "sep_token": "</s>",
55
+ "tokenizer_class": "RobertaTokenizer",
56
+ "trim_offsets": true,
57
+ "unk_token": "<unk>"
58
+ }
trainer_state.json ADDED
@@ -0,0 +1,663 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.272984441301273,
5
+ "eval_steps": 500,
6
+ "global_step": 900,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.014144271570014143,
13
+ "grad_norm": 85.7519302368164,
14
+ "learning_rate": 4.976426214049977e-05,
15
+ "loss": 9.3898,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.028288543140028287,
20
+ "grad_norm": 33.235904693603516,
21
+ "learning_rate": 4.952852428099953e-05,
22
+ "loss": 5.3413,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.042432814710042434,
27
+ "grad_norm": 5.113602161407471,
28
+ "learning_rate": 4.9292786421499294e-05,
29
+ "loss": 4.854,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.056577086280056574,
34
+ "grad_norm": 36.069705963134766,
35
+ "learning_rate": 4.9057048561999055e-05,
36
+ "loss": 5.0425,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.07072135785007072,
41
+ "grad_norm": 33.71372604370117,
42
+ "learning_rate": 4.882131070249882e-05,
43
+ "loss": 5.04,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.08486562942008487,
48
+ "grad_norm": 10.95967960357666,
49
+ "learning_rate": 4.858557284299859e-05,
50
+ "loss": 4.5402,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.09900990099009901,
55
+ "grad_norm": 57.9084358215332,
56
+ "learning_rate": 4.834983498349835e-05,
57
+ "loss": 4.8505,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.11315417256011315,
62
+ "grad_norm": 34.007869720458984,
63
+ "learning_rate": 4.8114097123998114e-05,
64
+ "loss": 4.3305,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.1272984441301273,
69
+ "grad_norm": 15.245634078979492,
70
+ "learning_rate": 4.787835926449788e-05,
71
+ "loss": 4.4707,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.14144271570014144,
76
+ "grad_norm": 24.47016143798828,
77
+ "learning_rate": 4.7642621404997644e-05,
78
+ "loss": 4.5379,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.15558698727015557,
83
+ "grad_norm": 14.591358184814453,
84
+ "learning_rate": 4.740688354549741e-05,
85
+ "loss": 4.5205,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.16973125884016974,
90
+ "grad_norm": 18.776493072509766,
91
+ "learning_rate": 4.7171145685997174e-05,
92
+ "loss": 4.6578,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.18387553041018387,
97
+ "grad_norm": 4.018069267272949,
98
+ "learning_rate": 4.6935407826496935e-05,
99
+ "loss": 4.1864,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.19801980198019803,
104
+ "grad_norm": 8.038480758666992,
105
+ "learning_rate": 4.6699669966996704e-05,
106
+ "loss": 4.5046,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.21216407355021216,
111
+ "grad_norm": 2.9573426246643066,
112
+ "learning_rate": 4.6463932107496465e-05,
113
+ "loss": 4.2317,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.2263083451202263,
118
+ "grad_norm": 3.0037927627563477,
119
+ "learning_rate": 4.622819424799623e-05,
120
+ "loss": 4.0951,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.24045261669024046,
125
+ "grad_norm": 9.886232376098633,
126
+ "learning_rate": 4.5992456388495995e-05,
127
+ "loss": 4.0168,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.2545968882602546,
132
+ "grad_norm": 2.463179588317871,
133
+ "learning_rate": 4.5756718528995756e-05,
134
+ "loss": 4.0372,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.26874115983026875,
139
+ "grad_norm": 13.546555519104004,
140
+ "learning_rate": 4.5520980669495525e-05,
141
+ "loss": 4.1929,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.2828854314002829,
146
+ "grad_norm": 2.4467103481292725,
147
+ "learning_rate": 4.5285242809995286e-05,
148
+ "loss": 4.2146,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.297029702970297,
153
+ "grad_norm": 5.936313152313232,
154
+ "learning_rate": 4.5049504950495054e-05,
155
+ "loss": 4.6069,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.31117397454031115,
160
+ "grad_norm": 6.5272536277771,
161
+ "learning_rate": 4.4813767090994816e-05,
162
+ "loss": 4.3263,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.32531824611032534,
167
+ "grad_norm": 4.2881598472595215,
168
+ "learning_rate": 4.457802923149458e-05,
169
+ "loss": 3.8218,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.33946251768033947,
174
+ "grad_norm": 3.9945058822631836,
175
+ "learning_rate": 4.4342291371994345e-05,
176
+ "loss": 4.1532,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.3536067892503536,
181
+ "grad_norm": 4.577730655670166,
182
+ "learning_rate": 4.410655351249411e-05,
183
+ "loss": 4.0727,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.36775106082036774,
188
+ "grad_norm": 2.6052353382110596,
189
+ "learning_rate": 4.3870815652993875e-05,
190
+ "loss": 3.9074,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.38189533239038187,
195
+ "grad_norm": 15.787618637084961,
196
+ "learning_rate": 4.363507779349364e-05,
197
+ "loss": 4.2402,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.39603960396039606,
202
+ "grad_norm": 23.970670700073242,
203
+ "learning_rate": 4.33993399339934e-05,
204
+ "loss": 4.3765,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.4101838755304102,
209
+ "grad_norm": 2.5313973426818848,
210
+ "learning_rate": 4.3163602074493166e-05,
211
+ "loss": 3.9863,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.4243281471004243,
216
+ "grad_norm": 21.020267486572266,
217
+ "learning_rate": 4.292786421499293e-05,
218
+ "loss": 4.0341,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.43847241867043846,
223
+ "grad_norm": 9.731268882751465,
224
+ "learning_rate": 4.2692126355492696e-05,
225
+ "loss": 4.1089,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.4526166902404526,
230
+ "grad_norm": 4.240326881408691,
231
+ "learning_rate": 4.245638849599246e-05,
232
+ "loss": 3.9737,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.4667609618104668,
237
+ "grad_norm": 15.72867202758789,
238
+ "learning_rate": 4.222065063649222e-05,
239
+ "loss": 4.454,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.4809052333804809,
244
+ "grad_norm": 10.669405937194824,
245
+ "learning_rate": 4.198491277699199e-05,
246
+ "loss": 4.1596,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.49504950495049505,
251
+ "grad_norm": 11.927492141723633,
252
+ "learning_rate": 4.174917491749175e-05,
253
+ "loss": 4.0485,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.5091937765205092,
258
+ "grad_norm": 7.629958629608154,
259
+ "learning_rate": 4.151343705799152e-05,
260
+ "loss": 4.1567,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.5233380480905233,
265
+ "grad_norm": 32.22209930419922,
266
+ "learning_rate": 4.1277699198491285e-05,
267
+ "loss": 4.9187,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.5374823196605375,
272
+ "grad_norm": 7.841526985168457,
273
+ "learning_rate": 4.104196133899104e-05,
274
+ "loss": 4.0989,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.5516265912305516,
279
+ "grad_norm": 3.8099868297576904,
280
+ "learning_rate": 4.080622347949081e-05,
281
+ "loss": 4.4586,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.5657708628005658,
286
+ "grad_norm": 11.720135688781738,
287
+ "learning_rate": 4.057048561999057e-05,
288
+ "loss": 4.1915,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.57991513437058,
293
+ "grad_norm": 5.8960280418396,
294
+ "learning_rate": 4.033474776049034e-05,
295
+ "loss": 4.3458,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.594059405940594,
300
+ "grad_norm": 3.532780885696411,
301
+ "learning_rate": 4.0099009900990106e-05,
302
+ "loss": 4.2094,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.6082036775106082,
307
+ "grad_norm": 6.77498722076416,
308
+ "learning_rate": 3.986327204148986e-05,
309
+ "loss": 4.3139,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.6223479490806223,
314
+ "grad_norm": 23.035005569458008,
315
+ "learning_rate": 3.962753418198963e-05,
316
+ "loss": 4.0213,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.6364922206506365,
321
+ "grad_norm": 3.033621311187744,
322
+ "learning_rate": 3.939179632248939e-05,
323
+ "loss": 4.0612,
324
+ "step": 450
325
+ },
326
+ {
327
+ "epoch": 0.6506364922206507,
328
+ "grad_norm": 32.6967887878418,
329
+ "learning_rate": 3.915605846298916e-05,
330
+ "loss": 4.1847,
331
+ "step": 460
332
+ },
333
+ {
334
+ "epoch": 0.6647807637906648,
335
+ "grad_norm": 9.779464721679688,
336
+ "learning_rate": 3.892032060348893e-05,
337
+ "loss": 4.1741,
338
+ "step": 470
339
+ },
340
+ {
341
+ "epoch": 0.6789250353606789,
342
+ "grad_norm": 14.904414176940918,
343
+ "learning_rate": 3.868458274398868e-05,
344
+ "loss": 4.1909,
345
+ "step": 480
346
+ },
347
+ {
348
+ "epoch": 0.693069306930693,
349
+ "grad_norm": 34.94367218017578,
350
+ "learning_rate": 3.844884488448845e-05,
351
+ "loss": 4.9592,
352
+ "step": 490
353
+ },
354
+ {
355
+ "epoch": 0.7072135785007072,
356
+ "grad_norm": 6.339000701904297,
357
+ "learning_rate": 3.821310702498822e-05,
358
+ "loss": 3.7726,
359
+ "step": 500
360
+ },
361
+ {
362
+ "epoch": 0.7213578500707214,
363
+ "grad_norm": 17.672000885009766,
364
+ "learning_rate": 3.797736916548798e-05,
365
+ "loss": 3.9599,
366
+ "step": 510
367
+ },
368
+ {
369
+ "epoch": 0.7355021216407355,
370
+ "grad_norm": 13.348356246948242,
371
+ "learning_rate": 3.774163130598775e-05,
372
+ "loss": 3.8342,
373
+ "step": 520
374
+ },
375
+ {
376
+ "epoch": 0.7496463932107497,
377
+ "grad_norm": 1.8930085897445679,
378
+ "learning_rate": 3.75058934464875e-05,
379
+ "loss": 4.0049,
380
+ "step": 530
381
+ },
382
+ {
383
+ "epoch": 0.7637906647807637,
384
+ "grad_norm": 35.62409210205078,
385
+ "learning_rate": 3.727015558698727e-05,
386
+ "loss": 3.9412,
387
+ "step": 540
388
+ },
389
+ {
390
+ "epoch": 0.7779349363507779,
391
+ "grad_norm": 2.246541738510132,
392
+ "learning_rate": 3.703441772748704e-05,
393
+ "loss": 3.893,
394
+ "step": 550
395
+ },
396
+ {
397
+ "epoch": 0.7920792079207921,
398
+ "grad_norm": 57.89748001098633,
399
+ "learning_rate": 3.67986798679868e-05,
400
+ "loss": 4.2004,
401
+ "step": 560
402
+ },
403
+ {
404
+ "epoch": 0.8062234794908062,
405
+ "grad_norm": 13.958605766296387,
406
+ "learning_rate": 3.656294200848657e-05,
407
+ "loss": 4.5987,
408
+ "step": 570
409
+ },
410
+ {
411
+ "epoch": 0.8203677510608204,
412
+ "grad_norm": 7.963130950927734,
413
+ "learning_rate": 3.6327204148986324e-05,
414
+ "loss": 3.8688,
415
+ "step": 580
416
+ },
417
+ {
418
+ "epoch": 0.8345120226308345,
419
+ "grad_norm": 12.124194145202637,
420
+ "learning_rate": 3.609146628948609e-05,
421
+ "loss": 3.8787,
422
+ "step": 590
423
+ },
424
+ {
425
+ "epoch": 0.8486562942008486,
426
+ "grad_norm": 19.39701271057129,
427
+ "learning_rate": 3.585572842998586e-05,
428
+ "loss": 3.8274,
429
+ "step": 600
430
+ },
431
+ {
432
+ "epoch": 0.8628005657708628,
433
+ "grad_norm": 7.561882495880127,
434
+ "learning_rate": 3.561999057048562e-05,
435
+ "loss": 3.917,
436
+ "step": 610
437
+ },
438
+ {
439
+ "epoch": 0.8769448373408769,
440
+ "grad_norm": 8.699311256408691,
441
+ "learning_rate": 3.538425271098539e-05,
442
+ "loss": 3.8819,
443
+ "step": 620
444
+ },
445
+ {
446
+ "epoch": 0.8910891089108911,
447
+ "grad_norm": 10.60632038116455,
448
+ "learning_rate": 3.514851485148515e-05,
449
+ "loss": 4.3288,
450
+ "step": 630
451
+ },
452
+ {
453
+ "epoch": 0.9052333804809052,
454
+ "grad_norm": 5.851240634918213,
455
+ "learning_rate": 3.491277699198491e-05,
456
+ "loss": 3.7157,
457
+ "step": 640
458
+ },
459
+ {
460
+ "epoch": 0.9193776520509194,
461
+ "grad_norm": 12.624049186706543,
462
+ "learning_rate": 3.467703913248468e-05,
463
+ "loss": 4.0151,
464
+ "step": 650
465
+ },
466
+ {
467
+ "epoch": 0.9335219236209336,
468
+ "grad_norm": 10.379075050354004,
469
+ "learning_rate": 3.444130127298444e-05,
470
+ "loss": 4.1419,
471
+ "step": 660
472
+ },
473
+ {
474
+ "epoch": 0.9476661951909476,
475
+ "grad_norm": 11.247940063476562,
476
+ "learning_rate": 3.420556341348421e-05,
477
+ "loss": 3.5958,
478
+ "step": 670
479
+ },
480
+ {
481
+ "epoch": 0.9618104667609618,
482
+ "grad_norm": 10.014704704284668,
483
+ "learning_rate": 3.396982555398397e-05,
484
+ "loss": 3.7822,
485
+ "step": 680
486
+ },
487
+ {
488
+ "epoch": 0.9759547383309759,
489
+ "grad_norm": 8.791955947875977,
490
+ "learning_rate": 3.3734087694483734e-05,
491
+ "loss": 3.9809,
492
+ "step": 690
493
+ },
494
+ {
495
+ "epoch": 0.9900990099009901,
496
+ "grad_norm": 30.620357513427734,
497
+ "learning_rate": 3.34983498349835e-05,
498
+ "loss": 3.9702,
499
+ "step": 700
500
+ },
501
+ {
502
+ "epoch": 1.0042432814710043,
503
+ "grad_norm": 23.29230499267578,
504
+ "learning_rate": 3.326261197548326e-05,
505
+ "loss": 3.8758,
506
+ "step": 710
507
+ },
508
+ {
509
+ "epoch": 1.0183875530410185,
510
+ "grad_norm": 6.364682674407959,
511
+ "learning_rate": 3.302687411598303e-05,
512
+ "loss": 3.6476,
513
+ "step": 720
514
+ },
515
+ {
516
+ "epoch": 1.0325318246110324,
517
+ "grad_norm": 22.594091415405273,
518
+ "learning_rate": 3.279113625648279e-05,
519
+ "loss": 4.2427,
520
+ "step": 730
521
+ },
522
+ {
523
+ "epoch": 1.0466760961810466,
524
+ "grad_norm": 31.865617752075195,
525
+ "learning_rate": 3.2555398396982555e-05,
526
+ "loss": 3.8927,
527
+ "step": 740
528
+ },
529
+ {
530
+ "epoch": 1.0608203677510608,
531
+ "grad_norm": 2.553858757019043,
532
+ "learning_rate": 3.231966053748232e-05,
533
+ "loss": 3.6406,
534
+ "step": 750
535
+ },
536
+ {
537
+ "epoch": 1.074964639321075,
538
+ "grad_norm": 24.558555603027344,
539
+ "learning_rate": 3.2083922677982084e-05,
540
+ "loss": 3.9391,
541
+ "step": 760
542
+ },
543
+ {
544
+ "epoch": 1.0891089108910892,
545
+ "grad_norm": 3.9098362922668457,
546
+ "learning_rate": 3.184818481848185e-05,
547
+ "loss": 4.2241,
548
+ "step": 770
549
+ },
550
+ {
551
+ "epoch": 1.1032531824611032,
552
+ "grad_norm": 14.435652732849121,
553
+ "learning_rate": 3.1612446958981614e-05,
554
+ "loss": 3.5212,
555
+ "step": 780
556
+ },
557
+ {
558
+ "epoch": 1.1173974540311173,
559
+ "grad_norm": 4.891509056091309,
560
+ "learning_rate": 3.1376709099481375e-05,
561
+ "loss": 3.3049,
562
+ "step": 790
563
+ },
564
+ {
565
+ "epoch": 1.1315417256011315,
566
+ "grad_norm": 10.893304824829102,
567
+ "learning_rate": 3.1140971239981144e-05,
568
+ "loss": 3.7428,
569
+ "step": 800
570
+ },
571
+ {
572
+ "epoch": 1.1456859971711457,
573
+ "grad_norm": 3.631542921066284,
574
+ "learning_rate": 3.0905233380480905e-05,
575
+ "loss": 3.7109,
576
+ "step": 810
577
+ },
578
+ {
579
+ "epoch": 1.15983026874116,
580
+ "grad_norm": 17.292734146118164,
581
+ "learning_rate": 3.0669495520980673e-05,
582
+ "loss": 3.748,
583
+ "step": 820
584
+ },
585
+ {
586
+ "epoch": 1.1739745403111739,
587
+ "grad_norm": 12.438305854797363,
588
+ "learning_rate": 3.043375766148043e-05,
589
+ "loss": 4.5263,
590
+ "step": 830
591
+ },
592
+ {
593
+ "epoch": 1.188118811881188,
594
+ "grad_norm": 7.694697380065918,
595
+ "learning_rate": 3.01980198019802e-05,
596
+ "loss": 3.9575,
597
+ "step": 840
598
+ },
599
+ {
600
+ "epoch": 1.2022630834512023,
601
+ "grad_norm": 9.88021469116211,
602
+ "learning_rate": 2.9962281942479965e-05,
603
+ "loss": 3.5793,
604
+ "step": 850
605
+ },
606
+ {
607
+ "epoch": 1.2164073550212164,
608
+ "grad_norm": 18.16057586669922,
609
+ "learning_rate": 2.972654408297973e-05,
610
+ "loss": 3.7951,
611
+ "step": 860
612
+ },
613
+ {
614
+ "epoch": 1.2305516265912306,
615
+ "grad_norm": 3.5214946269989014,
616
+ "learning_rate": 2.9490806223479494e-05,
617
+ "loss": 4.0263,
618
+ "step": 870
619
+ },
620
+ {
621
+ "epoch": 1.2446958981612446,
622
+ "grad_norm": 20.135046005249023,
623
+ "learning_rate": 2.9255068363979256e-05,
624
+ "loss": 3.678,
625
+ "step": 880
626
+ },
627
+ {
628
+ "epoch": 1.2588401697312588,
629
+ "grad_norm": 35.220733642578125,
630
+ "learning_rate": 2.901933050447902e-05,
631
+ "loss": 4.1981,
632
+ "step": 890
633
+ },
634
+ {
635
+ "epoch": 1.272984441301273,
636
+ "grad_norm": 39.2838134765625,
637
+ "learning_rate": 2.8783592644978786e-05,
638
+ "loss": 3.9173,
639
+ "step": 900
640
+ }
641
+ ],
642
+ "logging_steps": 10,
643
+ "max_steps": 2121,
644
+ "num_input_tokens_seen": 0,
645
+ "num_train_epochs": 3,
646
+ "save_steps": 100,
647
+ "stateful_callbacks": {
648
+ "TrainerControl": {
649
+ "args": {
650
+ "should_epoch_stop": false,
651
+ "should_evaluate": false,
652
+ "should_log": false,
653
+ "should_save": true,
654
+ "should_training_stop": false
655
+ },
656
+ "attributes": {}
657
+ }
658
+ },
659
+ "total_flos": 1.3469133437927424e+18,
660
+ "train_batch_size": 2,
661
+ "trial_name": null,
662
+ "trial_params": null
663
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b769e33f404ccffb79db1890a0a15a1d95b91ad4d06a151aebffd1ff7dca0621
3
+ size 4783
vocab.json ADDED
The diff for this file is too large to render. See raw diff