michaeljcliao commited on
Commit
429eef1
1 Parent(s): a288e93

Upload folder using huggingface_hub

Browse files
added_tokens.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</s_invoice_date>": 57534,
3
+ "</s_invoice_num>": 57532,
4
+ "</s_tax>": 57530,
5
+ "</s_total_price>": 57528,
6
+ "</s_untaxed_price>": 57526,
7
+ "<s_iitcdip>": 57523,
8
+ "<s_invoice_date>": 57533,
9
+ "<s_invoice_num>": 57531,
10
+ "<s_synthdog>": 57524,
11
+ "<s_tax>": 57529,
12
+ "<s_total_price>": 57527,
13
+ "<s_untaxed_price>": 57525,
14
+ "<sep/>": 57522
15
+ }
checkpoint-5058/config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "naver-clova-ix/donut-base",
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "",
8
+ "activation_dropout": 0.0,
9
+ "activation_function": "gelu",
10
+ "add_cross_attention": true,
11
+ "add_final_layer_norm": 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": null,
20
+ "d_model": 1024,
21
+ "decoder_attention_heads": 16,
22
+ "decoder_ffn_dim": 4096,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 4,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "dropout": 0.1,
29
+ "early_stopping": false,
30
+ "encoder_attention_heads": 16,
31
+ "encoder_ffn_dim": 4096,
32
+ "encoder_layerdrop": 0.0,
33
+ "encoder_layers": 12,
34
+ "encoder_no_repeat_ngram_size": 0,
35
+ "eos_token_id": 2,
36
+ "exponential_decay_length_penalty": null,
37
+ "finetuning_task": null,
38
+ "forced_bos_token_id": null,
39
+ "forced_eos_token_id": 2,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1"
43
+ },
44
+ "init_std": 0.02,
45
+ "is_decoder": true,
46
+ "is_encoder_decoder": false,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
+ "length_penalty": 1.0,
52
+ "max_length": 512,
53
+ "max_position_embeddings": 1536,
54
+ "min_length": 0,
55
+ "model_type": "mbart",
56
+ "no_repeat_ngram_size": 0,
57
+ "num_beam_groups": 1,
58
+ "num_beams": 1,
59
+ "num_hidden_layers": 12,
60
+ "num_return_sequences": 1,
61
+ "output_attentions": false,
62
+ "output_hidden_states": false,
63
+ "output_scores": false,
64
+ "pad_token_id": 1,
65
+ "prefix": null,
66
+ "problem_type": null,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "scale_embedding": true,
73
+ "sep_token_id": null,
74
+ "suppress_tokens": null,
75
+ "task_specific_params": null,
76
+ "temperature": 1.0,
77
+ "tf_legacy_loss": false,
78
+ "tie_encoder_decoder": false,
79
+ "tie_word_embeddings": true,
80
+ "tokenizer_class": null,
81
+ "top_k": 50,
82
+ "top_p": 1.0,
83
+ "torch_dtype": null,
84
+ "torchscript": false,
85
+ "typical_p": 1.0,
86
+ "use_bfloat16": false,
87
+ "use_cache": true,
88
+ "vocab_size": 57535
89
+ },
90
+ "decoder_start_token_id": 0,
91
+ "encoder": {
92
+ "_name_or_path": "",
93
+ "add_cross_attention": false,
94
+ "architectures": null,
95
+ "attention_probs_dropout_prob": 0.0,
96
+ "bad_words_ids": null,
97
+ "begin_suppress_tokens": null,
98
+ "bos_token_id": null,
99
+ "chunk_size_feed_forward": 0,
100
+ "cross_attention_hidden_size": null,
101
+ "decoder_start_token_id": null,
102
+ "depths": [
103
+ 2,
104
+ 2,
105
+ 14,
106
+ 2
107
+ ],
108
+ "diversity_penalty": 0.0,
109
+ "do_sample": false,
110
+ "drop_path_rate": 0.1,
111
+ "early_stopping": false,
112
+ "embed_dim": 128,
113
+ "encoder_no_repeat_ngram_size": 0,
114
+ "eos_token_id": null,
115
+ "exponential_decay_length_penalty": null,
116
+ "finetuning_task": null,
117
+ "forced_bos_token_id": null,
118
+ "forced_eos_token_id": null,
119
+ "hidden_act": "gelu",
120
+ "hidden_dropout_prob": 0.0,
121
+ "hidden_size": 1024,
122
+ "id2label": {
123
+ "0": "LABEL_0",
124
+ "1": "LABEL_1"
125
+ },
126
+ "image_size": [
127
+ 550,
128
+ 960
129
+ ],
130
+ "initializer_range": 0.02,
131
+ "is_decoder": false,
132
+ "is_encoder_decoder": false,
133
+ "label2id": {
134
+ "LABEL_0": 0,
135
+ "LABEL_1": 1
136
+ },
137
+ "layer_norm_eps": 1e-05,
138
+ "length_penalty": 1.0,
139
+ "max_length": 20,
140
+ "min_length": 0,
141
+ "mlp_ratio": 4.0,
142
+ "model_type": "donut-swin",
143
+ "no_repeat_ngram_size": 0,
144
+ "num_beam_groups": 1,
145
+ "num_beams": 1,
146
+ "num_channels": 3,
147
+ "num_heads": [
148
+ 4,
149
+ 8,
150
+ 16,
151
+ 32
152
+ ],
153
+ "num_layers": 4,
154
+ "num_return_sequences": 1,
155
+ "output_attentions": false,
156
+ "output_hidden_states": false,
157
+ "output_scores": false,
158
+ "pad_token_id": null,
159
+ "patch_size": 4,
160
+ "path_norm": true,
161
+ "prefix": null,
162
+ "problem_type": null,
163
+ "pruned_heads": {},
164
+ "qkv_bias": true,
165
+ "remove_invalid_values": false,
166
+ "repetition_penalty": 1.0,
167
+ "return_dict": true,
168
+ "return_dict_in_generate": false,
169
+ "sep_token_id": null,
170
+ "suppress_tokens": null,
171
+ "task_specific_params": null,
172
+ "temperature": 1.0,
173
+ "tf_legacy_loss": false,
174
+ "tie_encoder_decoder": false,
175
+ "tie_word_embeddings": true,
176
+ "tokenizer_class": null,
177
+ "top_k": 50,
178
+ "top_p": 1.0,
179
+ "torch_dtype": null,
180
+ "torchscript": false,
181
+ "typical_p": 1.0,
182
+ "use_absolute_embeddings": false,
183
+ "use_bfloat16": false,
184
+ "window_size": 10
185
+ },
186
+ "is_encoder_decoder": true,
187
+ "model_type": "vision-encoder-decoder",
188
+ "pad_token_id": 1,
189
+ "tie_word_embeddings": false,
190
+ "torch_dtype": "float32",
191
+ "transformers_version": "4.38.2"
192
+ }
checkpoint-5058/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.38.2"
8
+ }
checkpoint-5058/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46b171d7cab588ece0a814338122fb1c918694d18072991302fd6de0f90449e0
3
+ size 809111704
checkpoint-5058/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e95d868dfb0cec36a090521265ac94d4aabfee385739ecba935eaa21d613456c
3
+ size 1615285631
checkpoint-5058/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fba72cade8cffe76dc5cc12c2513692607d92f3196acbfe04e32eb2beb048d2
3
+ size 14244
checkpoint-5058/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d8c541e22e3f3813ec817b1732330cb9158ed3827913f5d904ac5f52f593afe
3
+ size 1064
checkpoint-5058/trainer_state.json ADDED
@@ -0,0 +1,371 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5058,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.18,
13
+ "grad_norm": 48.51668930053711,
14
+ "learning_rate": 1.98220640569395e-06,
15
+ "loss": 10.5512,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.36,
20
+ "grad_norm": 33.89441680908203,
21
+ "learning_rate": 1.9644128113879e-06,
22
+ "loss": 6.656,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.53,
27
+ "grad_norm": 54.47207260131836,
28
+ "learning_rate": 1.9466192170818503e-06,
29
+ "loss": 4.8936,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.71,
34
+ "grad_norm": 37.983856201171875,
35
+ "learning_rate": 1.9288256227758005e-06,
36
+ "loss": 3.5277,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.89,
41
+ "grad_norm": 23.24921417236328,
42
+ "learning_rate": 1.9110320284697506e-06,
43
+ "loss": 2.8756,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 1.07,
48
+ "grad_norm": 26.32309913635254,
49
+ "learning_rate": 1.8932384341637008e-06,
50
+ "loss": 2.4437,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 1.25,
55
+ "grad_norm": 154.72117614746094,
56
+ "learning_rate": 1.8754448398576511e-06,
57
+ "loss": 2.2582,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 1.42,
62
+ "grad_norm": 16.39977264404297,
63
+ "learning_rate": 1.8576512455516013e-06,
64
+ "loss": 2.2289,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 1.6,
69
+ "grad_norm": 22.533836364746094,
70
+ "learning_rate": 1.8398576512455514e-06,
71
+ "loss": 2.091,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 1.78,
76
+ "grad_norm": 16.523881912231445,
77
+ "learning_rate": 1.8220640569395016e-06,
78
+ "loss": 2.0129,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 1.96,
83
+ "grad_norm": 69.78620147705078,
84
+ "learning_rate": 1.804270462633452e-06,
85
+ "loss": 1.926,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 2.14,
90
+ "grad_norm": 21.385257720947266,
91
+ "learning_rate": 1.786476868327402e-06,
92
+ "loss": 1.8193,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 2.31,
97
+ "grad_norm": 23.061298370361328,
98
+ "learning_rate": 1.7686832740213522e-06,
99
+ "loss": 1.804,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 2.49,
104
+ "grad_norm": 21.625669479370117,
105
+ "learning_rate": 1.7508896797153024e-06,
106
+ "loss": 1.7568,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 2.67,
111
+ "grad_norm": 13.98591136932373,
112
+ "learning_rate": 1.7330960854092527e-06,
113
+ "loss": 1.7313,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 2.85,
118
+ "grad_norm": 18.47169303894043,
119
+ "learning_rate": 1.7153024911032029e-06,
120
+ "loss": 1.733,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 3.02,
125
+ "grad_norm": 20.671327590942383,
126
+ "learning_rate": 1.697508896797153e-06,
127
+ "loss": 1.698,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 3.2,
132
+ "grad_norm": 20.78021812438965,
133
+ "learning_rate": 1.6797153024911032e-06,
134
+ "loss": 1.6192,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 3.38,
139
+ "grad_norm": 35.38755416870117,
140
+ "learning_rate": 1.6619217081850533e-06,
141
+ "loss": 1.5752,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 3.56,
146
+ "grad_norm": 24.105249404907227,
147
+ "learning_rate": 1.6441281138790034e-06,
148
+ "loss": 1.5921,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 3.74,
153
+ "grad_norm": 11.530924797058105,
154
+ "learning_rate": 1.6263345195729536e-06,
155
+ "loss": 1.5497,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 3.91,
160
+ "grad_norm": 17.551040649414062,
161
+ "learning_rate": 1.6085409252669037e-06,
162
+ "loss": 1.5751,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 4.09,
167
+ "grad_norm": 22.44804573059082,
168
+ "learning_rate": 1.590747330960854e-06,
169
+ "loss": 1.6072,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 4.27,
174
+ "grad_norm": 14.482297897338867,
175
+ "learning_rate": 1.5729537366548042e-06,
176
+ "loss": 1.552,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 4.45,
181
+ "grad_norm": 17.7537899017334,
182
+ "learning_rate": 1.5551601423487544e-06,
183
+ "loss": 1.4403,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 4.63,
188
+ "grad_norm": 23.001920700073242,
189
+ "learning_rate": 1.5373665480427045e-06,
190
+ "loss": 1.4955,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 4.8,
195
+ "grad_norm": 14.721695899963379,
196
+ "learning_rate": 1.5195729537366549e-06,
197
+ "loss": 1.4456,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 4.98,
202
+ "grad_norm": 15.371649742126465,
203
+ "learning_rate": 1.501779359430605e-06,
204
+ "loss": 1.4303,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 5.16,
209
+ "grad_norm": 14.734794616699219,
210
+ "learning_rate": 1.4839857651245552e-06,
211
+ "loss": 1.4544,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 5.34,
216
+ "grad_norm": 13.686590194702148,
217
+ "learning_rate": 1.4661921708185053e-06,
218
+ "loss": 1.401,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 5.52,
223
+ "grad_norm": 18.93415641784668,
224
+ "learning_rate": 1.4483985765124555e-06,
225
+ "loss": 1.4612,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 5.69,
230
+ "grad_norm": 9.70661735534668,
231
+ "learning_rate": 1.4306049822064056e-06,
232
+ "loss": 1.3558,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 5.87,
237
+ "grad_norm": 16.12574577331543,
238
+ "learning_rate": 1.4128113879003557e-06,
239
+ "loss": 1.3686,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 6.05,
244
+ "grad_norm": 29.739870071411133,
245
+ "learning_rate": 1.3950177935943059e-06,
246
+ "loss": 1.3703,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 6.23,
251
+ "grad_norm": 22.152677536010742,
252
+ "learning_rate": 1.377224199288256e-06,
253
+ "loss": 1.2662,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 6.41,
258
+ "grad_norm": 24.051326751708984,
259
+ "learning_rate": 1.3594306049822064e-06,
260
+ "loss": 1.35,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 6.58,
265
+ "grad_norm": 11.552955627441406,
266
+ "learning_rate": 1.3416370106761565e-06,
267
+ "loss": 1.3592,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 6.76,
272
+ "grad_norm": 16.08234977722168,
273
+ "learning_rate": 1.3238434163701067e-06,
274
+ "loss": 1.3566,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 6.94,
279
+ "grad_norm": 14.58088493347168,
280
+ "learning_rate": 1.3060498220640568e-06,
281
+ "loss": 1.3257,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 7.12,
286
+ "grad_norm": 12.278518676757812,
287
+ "learning_rate": 1.2882562277580072e-06,
288
+ "loss": 1.3254,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 7.3,
293
+ "grad_norm": 17.330495834350586,
294
+ "learning_rate": 1.2704626334519573e-06,
295
+ "loss": 1.2095,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 7.47,
300
+ "grad_norm": 13.842063903808594,
301
+ "learning_rate": 1.2526690391459075e-06,
302
+ "loss": 1.3475,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 7.65,
307
+ "grad_norm": 13.967167854309082,
308
+ "learning_rate": 1.2348754448398574e-06,
309
+ "loss": 1.2757,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 7.83,
314
+ "grad_norm": 18.25010871887207,
315
+ "learning_rate": 1.2170818505338078e-06,
316
+ "loss": 1.2795,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 8.01,
321
+ "grad_norm": 11.46198558807373,
322
+ "learning_rate": 1.199288256227758e-06,
323
+ "loss": 1.2648,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 8.19,
328
+ "grad_norm": 18.330867767333984,
329
+ "learning_rate": 1.181494661921708e-06,
330
+ "loss": 1.2345,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 8.36,
335
+ "grad_norm": 27.236454010009766,
336
+ "learning_rate": 1.1637010676156582e-06,
337
+ "loss": 1.2998,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 8.54,
342
+ "grad_norm": 15.08573055267334,
343
+ "learning_rate": 1.1459074733096086e-06,
344
+ "loss": 1.2578,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 8.72,
349
+ "grad_norm": 15.639131546020508,
350
+ "learning_rate": 1.1281138790035587e-06,
351
+ "loss": 1.2062,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 8.9,
356
+ "grad_norm": 22.758560180664062,
357
+ "learning_rate": 1.1103202846975088e-06,
358
+ "loss": 1.2305,
359
+ "step": 5000
360
+ }
361
+ ],
362
+ "logging_steps": 100,
363
+ "max_steps": 11240,
364
+ "num_input_tokens_seen": 0,
365
+ "num_train_epochs": 20,
366
+ "save_steps": 500,
367
+ "total_flos": 1.3591805503085568e+19,
368
+ "train_batch_size": 2,
369
+ "trial_name": null,
370
+ "trial_params": null
371
+ }
checkpoint-5058/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22da3339874e661b72481662e90c368b4085b9b260c4cb2ef0544e160b44b549
3
+ size 5048
checkpoint-5620/config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "naver-clova-ix/donut-base",
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "",
8
+ "activation_dropout": 0.0,
9
+ "activation_function": "gelu",
10
+ "add_cross_attention": true,
11
+ "add_final_layer_norm": 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": null,
20
+ "d_model": 1024,
21
+ "decoder_attention_heads": 16,
22
+ "decoder_ffn_dim": 4096,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 4,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "dropout": 0.1,
29
+ "early_stopping": false,
30
+ "encoder_attention_heads": 16,
31
+ "encoder_ffn_dim": 4096,
32
+ "encoder_layerdrop": 0.0,
33
+ "encoder_layers": 12,
34
+ "encoder_no_repeat_ngram_size": 0,
35
+ "eos_token_id": 2,
36
+ "exponential_decay_length_penalty": null,
37
+ "finetuning_task": null,
38
+ "forced_bos_token_id": null,
39
+ "forced_eos_token_id": 2,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1"
43
+ },
44
+ "init_std": 0.02,
45
+ "is_decoder": true,
46
+ "is_encoder_decoder": false,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
+ "length_penalty": 1.0,
52
+ "max_length": 512,
53
+ "max_position_embeddings": 1536,
54
+ "min_length": 0,
55
+ "model_type": "mbart",
56
+ "no_repeat_ngram_size": 0,
57
+ "num_beam_groups": 1,
58
+ "num_beams": 1,
59
+ "num_hidden_layers": 12,
60
+ "num_return_sequences": 1,
61
+ "output_attentions": false,
62
+ "output_hidden_states": false,
63
+ "output_scores": false,
64
+ "pad_token_id": 1,
65
+ "prefix": null,
66
+ "problem_type": null,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "scale_embedding": true,
73
+ "sep_token_id": null,
74
+ "suppress_tokens": null,
75
+ "task_specific_params": null,
76
+ "temperature": 1.0,
77
+ "tf_legacy_loss": false,
78
+ "tie_encoder_decoder": false,
79
+ "tie_word_embeddings": true,
80
+ "tokenizer_class": null,
81
+ "top_k": 50,
82
+ "top_p": 1.0,
83
+ "torch_dtype": null,
84
+ "torchscript": false,
85
+ "typical_p": 1.0,
86
+ "use_bfloat16": false,
87
+ "use_cache": true,
88
+ "vocab_size": 57535
89
+ },
90
+ "decoder_start_token_id": 0,
91
+ "encoder": {
92
+ "_name_or_path": "",
93
+ "add_cross_attention": false,
94
+ "architectures": null,
95
+ "attention_probs_dropout_prob": 0.0,
96
+ "bad_words_ids": null,
97
+ "begin_suppress_tokens": null,
98
+ "bos_token_id": null,
99
+ "chunk_size_feed_forward": 0,
100
+ "cross_attention_hidden_size": null,
101
+ "decoder_start_token_id": null,
102
+ "depths": [
103
+ 2,
104
+ 2,
105
+ 14,
106
+ 2
107
+ ],
108
+ "diversity_penalty": 0.0,
109
+ "do_sample": false,
110
+ "drop_path_rate": 0.1,
111
+ "early_stopping": false,
112
+ "embed_dim": 128,
113
+ "encoder_no_repeat_ngram_size": 0,
114
+ "eos_token_id": null,
115
+ "exponential_decay_length_penalty": null,
116
+ "finetuning_task": null,
117
+ "forced_bos_token_id": null,
118
+ "forced_eos_token_id": null,
119
+ "hidden_act": "gelu",
120
+ "hidden_dropout_prob": 0.0,
121
+ "hidden_size": 1024,
122
+ "id2label": {
123
+ "0": "LABEL_0",
124
+ "1": "LABEL_1"
125
+ },
126
+ "image_size": [
127
+ 550,
128
+ 960
129
+ ],
130
+ "initializer_range": 0.02,
131
+ "is_decoder": false,
132
+ "is_encoder_decoder": false,
133
+ "label2id": {
134
+ "LABEL_0": 0,
135
+ "LABEL_1": 1
136
+ },
137
+ "layer_norm_eps": 1e-05,
138
+ "length_penalty": 1.0,
139
+ "max_length": 20,
140
+ "min_length": 0,
141
+ "mlp_ratio": 4.0,
142
+ "model_type": "donut-swin",
143
+ "no_repeat_ngram_size": 0,
144
+ "num_beam_groups": 1,
145
+ "num_beams": 1,
146
+ "num_channels": 3,
147
+ "num_heads": [
148
+ 4,
149
+ 8,
150
+ 16,
151
+ 32
152
+ ],
153
+ "num_layers": 4,
154
+ "num_return_sequences": 1,
155
+ "output_attentions": false,
156
+ "output_hidden_states": false,
157
+ "output_scores": false,
158
+ "pad_token_id": null,
159
+ "patch_size": 4,
160
+ "path_norm": true,
161
+ "prefix": null,
162
+ "problem_type": null,
163
+ "pruned_heads": {},
164
+ "qkv_bias": true,
165
+ "remove_invalid_values": false,
166
+ "repetition_penalty": 1.0,
167
+ "return_dict": true,
168
+ "return_dict_in_generate": false,
169
+ "sep_token_id": null,
170
+ "suppress_tokens": null,
171
+ "task_specific_params": null,
172
+ "temperature": 1.0,
173
+ "tf_legacy_loss": false,
174
+ "tie_encoder_decoder": false,
175
+ "tie_word_embeddings": true,
176
+ "tokenizer_class": null,
177
+ "top_k": 50,
178
+ "top_p": 1.0,
179
+ "torch_dtype": null,
180
+ "torchscript": false,
181
+ "typical_p": 1.0,
182
+ "use_absolute_embeddings": false,
183
+ "use_bfloat16": false,
184
+ "window_size": 10
185
+ },
186
+ "is_encoder_decoder": true,
187
+ "model_type": "vision-encoder-decoder",
188
+ "pad_token_id": 1,
189
+ "tie_word_embeddings": false,
190
+ "torch_dtype": "float32",
191
+ "transformers_version": "4.38.2"
192
+ }
checkpoint-5620/generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.38.2"
8
+ }
checkpoint-5620/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c53d94c63a7306a429aa181421e8eedf075a047f585561bd25dbf9b5bc5bc88
3
+ size 809111704
checkpoint-5620/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65debd166f8685e1a8bc5ff1e3862653f2d56190eb653faf2c04f881eb1489d
3
+ size 1615285631
checkpoint-5620/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b15614d912a2b89c617584e8ec932228eb5c10c981726a18e255e380282d2f6
3
+ size 14244
checkpoint-5620/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6323a4a11036359a80107f6079ec08f6fd864b58d3a71938d832f444b4f7ac00
3
+ size 1064
checkpoint-5620/trainer_state.json ADDED
@@ -0,0 +1,413 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5620,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.18,
13
+ "grad_norm": 48.51668930053711,
14
+ "learning_rate": 1.98220640569395e-06,
15
+ "loss": 10.5512,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.36,
20
+ "grad_norm": 33.89441680908203,
21
+ "learning_rate": 1.9644128113879e-06,
22
+ "loss": 6.656,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.53,
27
+ "grad_norm": 54.47207260131836,
28
+ "learning_rate": 1.9466192170818503e-06,
29
+ "loss": 4.8936,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.71,
34
+ "grad_norm": 37.983856201171875,
35
+ "learning_rate": 1.9288256227758005e-06,
36
+ "loss": 3.5277,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.89,
41
+ "grad_norm": 23.24921417236328,
42
+ "learning_rate": 1.9110320284697506e-06,
43
+ "loss": 2.8756,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 1.07,
48
+ "grad_norm": 26.32309913635254,
49
+ "learning_rate": 1.8932384341637008e-06,
50
+ "loss": 2.4437,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 1.25,
55
+ "grad_norm": 154.72117614746094,
56
+ "learning_rate": 1.8754448398576511e-06,
57
+ "loss": 2.2582,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 1.42,
62
+ "grad_norm": 16.39977264404297,
63
+ "learning_rate": 1.8576512455516013e-06,
64
+ "loss": 2.2289,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 1.6,
69
+ "grad_norm": 22.533836364746094,
70
+ "learning_rate": 1.8398576512455514e-06,
71
+ "loss": 2.091,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 1.78,
76
+ "grad_norm": 16.523881912231445,
77
+ "learning_rate": 1.8220640569395016e-06,
78
+ "loss": 2.0129,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 1.96,
83
+ "grad_norm": 69.78620147705078,
84
+ "learning_rate": 1.804270462633452e-06,
85
+ "loss": 1.926,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 2.14,
90
+ "grad_norm": 21.385257720947266,
91
+ "learning_rate": 1.786476868327402e-06,
92
+ "loss": 1.8193,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 2.31,
97
+ "grad_norm": 23.061298370361328,
98
+ "learning_rate": 1.7686832740213522e-06,
99
+ "loss": 1.804,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 2.49,
104
+ "grad_norm": 21.625669479370117,
105
+ "learning_rate": 1.7508896797153024e-06,
106
+ "loss": 1.7568,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 2.67,
111
+ "grad_norm": 13.98591136932373,
112
+ "learning_rate": 1.7330960854092527e-06,
113
+ "loss": 1.7313,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 2.85,
118
+ "grad_norm": 18.47169303894043,
119
+ "learning_rate": 1.7153024911032029e-06,
120
+ "loss": 1.733,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 3.02,
125
+ "grad_norm": 20.671327590942383,
126
+ "learning_rate": 1.697508896797153e-06,
127
+ "loss": 1.698,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 3.2,
132
+ "grad_norm": 20.78021812438965,
133
+ "learning_rate": 1.6797153024911032e-06,
134
+ "loss": 1.6192,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 3.38,
139
+ "grad_norm": 35.38755416870117,
140
+ "learning_rate": 1.6619217081850533e-06,
141
+ "loss": 1.5752,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 3.56,
146
+ "grad_norm": 24.105249404907227,
147
+ "learning_rate": 1.6441281138790034e-06,
148
+ "loss": 1.5921,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 3.74,
153
+ "grad_norm": 11.530924797058105,
154
+ "learning_rate": 1.6263345195729536e-06,
155
+ "loss": 1.5497,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 3.91,
160
+ "grad_norm": 17.551040649414062,
161
+ "learning_rate": 1.6085409252669037e-06,
162
+ "loss": 1.5751,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 4.09,
167
+ "grad_norm": 22.44804573059082,
168
+ "learning_rate": 1.590747330960854e-06,
169
+ "loss": 1.6072,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 4.27,
174
+ "grad_norm": 14.482297897338867,
175
+ "learning_rate": 1.5729537366548042e-06,
176
+ "loss": 1.552,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 4.45,
181
+ "grad_norm": 17.7537899017334,
182
+ "learning_rate": 1.5551601423487544e-06,
183
+ "loss": 1.4403,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 4.63,
188
+ "grad_norm": 23.001920700073242,
189
+ "learning_rate": 1.5373665480427045e-06,
190
+ "loss": 1.4955,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 4.8,
195
+ "grad_norm": 14.721695899963379,
196
+ "learning_rate": 1.5195729537366549e-06,
197
+ "loss": 1.4456,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 4.98,
202
+ "grad_norm": 15.371649742126465,
203
+ "learning_rate": 1.501779359430605e-06,
204
+ "loss": 1.4303,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 5.16,
209
+ "grad_norm": 14.734794616699219,
210
+ "learning_rate": 1.4839857651245552e-06,
211
+ "loss": 1.4544,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 5.34,
216
+ "grad_norm": 13.686590194702148,
217
+ "learning_rate": 1.4661921708185053e-06,
218
+ "loss": 1.401,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 5.52,
223
+ "grad_norm": 18.93415641784668,
224
+ "learning_rate": 1.4483985765124555e-06,
225
+ "loss": 1.4612,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 5.69,
230
+ "grad_norm": 9.70661735534668,
231
+ "learning_rate": 1.4306049822064056e-06,
232
+ "loss": 1.3558,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 5.87,
237
+ "grad_norm": 16.12574577331543,
238
+ "learning_rate": 1.4128113879003557e-06,
239
+ "loss": 1.3686,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 6.05,
244
+ "grad_norm": 29.739870071411133,
245
+ "learning_rate": 1.3950177935943059e-06,
246
+ "loss": 1.3703,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 6.23,
251
+ "grad_norm": 22.152677536010742,
252
+ "learning_rate": 1.377224199288256e-06,
253
+ "loss": 1.2662,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 6.41,
258
+ "grad_norm": 24.051326751708984,
259
+ "learning_rate": 1.3594306049822064e-06,
260
+ "loss": 1.35,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 6.58,
265
+ "grad_norm": 11.552955627441406,
266
+ "learning_rate": 1.3416370106761565e-06,
267
+ "loss": 1.3592,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 6.76,
272
+ "grad_norm": 16.08234977722168,
273
+ "learning_rate": 1.3238434163701067e-06,
274
+ "loss": 1.3566,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 6.94,
279
+ "grad_norm": 14.58088493347168,
280
+ "learning_rate": 1.3060498220640568e-06,
281
+ "loss": 1.3257,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 7.12,
286
+ "grad_norm": 12.278518676757812,
287
+ "learning_rate": 1.2882562277580072e-06,
288
+ "loss": 1.3254,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 7.3,
293
+ "grad_norm": 17.330495834350586,
294
+ "learning_rate": 1.2704626334519573e-06,
295
+ "loss": 1.2095,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 7.47,
300
+ "grad_norm": 13.842063903808594,
301
+ "learning_rate": 1.2526690391459075e-06,
302
+ "loss": 1.3475,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 7.65,
307
+ "grad_norm": 13.967167854309082,
308
+ "learning_rate": 1.2348754448398574e-06,
309
+ "loss": 1.2757,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 7.83,
314
+ "grad_norm": 18.25010871887207,
315
+ "learning_rate": 1.2170818505338078e-06,
316
+ "loss": 1.2795,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 8.01,
321
+ "grad_norm": 11.46198558807373,
322
+ "learning_rate": 1.199288256227758e-06,
323
+ "loss": 1.2648,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 8.19,
328
+ "grad_norm": 18.330867767333984,
329
+ "learning_rate": 1.181494661921708e-06,
330
+ "loss": 1.2345,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 8.36,
335
+ "grad_norm": 27.236454010009766,
336
+ "learning_rate": 1.1637010676156582e-06,
337
+ "loss": 1.2998,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 8.54,
342
+ "grad_norm": 15.08573055267334,
343
+ "learning_rate": 1.1459074733096086e-06,
344
+ "loss": 1.2578,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 8.72,
349
+ "grad_norm": 15.639131546020508,
350
+ "learning_rate": 1.1281138790035587e-06,
351
+ "loss": 1.2062,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 8.9,
356
+ "grad_norm": 22.758560180664062,
357
+ "learning_rate": 1.1103202846975088e-06,
358
+ "loss": 1.2305,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 9.07,
363
+ "grad_norm": 11.382159233093262,
364
+ "learning_rate": 1.092526690391459e-06,
365
+ "loss": 1.2236,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 9.25,
370
+ "grad_norm": 14.228442192077637,
371
+ "learning_rate": 1.0747330960854093e-06,
372
+ "loss": 1.1871,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 9.43,
377
+ "grad_norm": 16.07115936279297,
378
+ "learning_rate": 1.0569395017793595e-06,
379
+ "loss": 1.2286,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 9.61,
384
+ "grad_norm": 12.73045539855957,
385
+ "learning_rate": 1.0391459074733096e-06,
386
+ "loss": 1.2837,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 9.79,
391
+ "grad_norm": 19.55732536315918,
392
+ "learning_rate": 1.0213523131672596e-06,
393
+ "loss": 1.1911,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 9.96,
398
+ "grad_norm": 13.422231674194336,
399
+ "learning_rate": 1.00355871886121e-06,
400
+ "loss": 1.1532,
401
+ "step": 5600
402
+ }
403
+ ],
404
+ "logging_steps": 100,
405
+ "max_steps": 11240,
406
+ "num_input_tokens_seen": 0,
407
+ "num_train_epochs": 20,
408
+ "save_steps": 500,
409
+ "total_flos": 1.510200611453952e+19,
410
+ "train_batch_size": 2,
411
+ "trial_name": null,
412
+ "trial_params": null
413
+ }
checkpoint-5620/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22da3339874e661b72481662e90c368b4085b9b260c4cb2ef0544e160b44b549
3
+ size 5048
config.json ADDED
@@ -0,0 +1,192 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "naver-clova-ix/donut-base",
3
+ "architectures": [
4
+ "VisionEncoderDecoderModel"
5
+ ],
6
+ "decoder": {
7
+ "_name_or_path": "",
8
+ "activation_dropout": 0.0,
9
+ "activation_function": "gelu",
10
+ "add_cross_attention": true,
11
+ "add_final_layer_norm": 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": null,
20
+ "d_model": 1024,
21
+ "decoder_attention_heads": 16,
22
+ "decoder_ffn_dim": 4096,
23
+ "decoder_layerdrop": 0.0,
24
+ "decoder_layers": 4,
25
+ "decoder_start_token_id": null,
26
+ "diversity_penalty": 0.0,
27
+ "do_sample": false,
28
+ "dropout": 0.1,
29
+ "early_stopping": false,
30
+ "encoder_attention_heads": 16,
31
+ "encoder_ffn_dim": 4096,
32
+ "encoder_layerdrop": 0.0,
33
+ "encoder_layers": 12,
34
+ "encoder_no_repeat_ngram_size": 0,
35
+ "eos_token_id": 2,
36
+ "exponential_decay_length_penalty": null,
37
+ "finetuning_task": null,
38
+ "forced_bos_token_id": null,
39
+ "forced_eos_token_id": 2,
40
+ "id2label": {
41
+ "0": "LABEL_0",
42
+ "1": "LABEL_1"
43
+ },
44
+ "init_std": 0.02,
45
+ "is_decoder": true,
46
+ "is_encoder_decoder": false,
47
+ "label2id": {
48
+ "LABEL_0": 0,
49
+ "LABEL_1": 1
50
+ },
51
+ "length_penalty": 1.0,
52
+ "max_length": 512,
53
+ "max_position_embeddings": 1536,
54
+ "min_length": 0,
55
+ "model_type": "mbart",
56
+ "no_repeat_ngram_size": 0,
57
+ "num_beam_groups": 1,
58
+ "num_beams": 1,
59
+ "num_hidden_layers": 12,
60
+ "num_return_sequences": 1,
61
+ "output_attentions": false,
62
+ "output_hidden_states": false,
63
+ "output_scores": false,
64
+ "pad_token_id": 1,
65
+ "prefix": null,
66
+ "problem_type": null,
67
+ "pruned_heads": {},
68
+ "remove_invalid_values": false,
69
+ "repetition_penalty": 1.0,
70
+ "return_dict": true,
71
+ "return_dict_in_generate": false,
72
+ "scale_embedding": true,
73
+ "sep_token_id": null,
74
+ "suppress_tokens": null,
75
+ "task_specific_params": null,
76
+ "temperature": 1.0,
77
+ "tf_legacy_loss": false,
78
+ "tie_encoder_decoder": false,
79
+ "tie_word_embeddings": true,
80
+ "tokenizer_class": null,
81
+ "top_k": 50,
82
+ "top_p": 1.0,
83
+ "torch_dtype": null,
84
+ "torchscript": false,
85
+ "typical_p": 1.0,
86
+ "use_bfloat16": false,
87
+ "use_cache": true,
88
+ "vocab_size": 57535
89
+ },
90
+ "decoder_start_token_id": 0,
91
+ "encoder": {
92
+ "_name_or_path": "",
93
+ "add_cross_attention": false,
94
+ "architectures": null,
95
+ "attention_probs_dropout_prob": 0.0,
96
+ "bad_words_ids": null,
97
+ "begin_suppress_tokens": null,
98
+ "bos_token_id": null,
99
+ "chunk_size_feed_forward": 0,
100
+ "cross_attention_hidden_size": null,
101
+ "decoder_start_token_id": null,
102
+ "depths": [
103
+ 2,
104
+ 2,
105
+ 14,
106
+ 2
107
+ ],
108
+ "diversity_penalty": 0.0,
109
+ "do_sample": false,
110
+ "drop_path_rate": 0.1,
111
+ "early_stopping": false,
112
+ "embed_dim": 128,
113
+ "encoder_no_repeat_ngram_size": 0,
114
+ "eos_token_id": null,
115
+ "exponential_decay_length_penalty": null,
116
+ "finetuning_task": null,
117
+ "forced_bos_token_id": null,
118
+ "forced_eos_token_id": null,
119
+ "hidden_act": "gelu",
120
+ "hidden_dropout_prob": 0.0,
121
+ "hidden_size": 1024,
122
+ "id2label": {
123
+ "0": "LABEL_0",
124
+ "1": "LABEL_1"
125
+ },
126
+ "image_size": [
127
+ 550,
128
+ 960
129
+ ],
130
+ "initializer_range": 0.02,
131
+ "is_decoder": false,
132
+ "is_encoder_decoder": false,
133
+ "label2id": {
134
+ "LABEL_0": 0,
135
+ "LABEL_1": 1
136
+ },
137
+ "layer_norm_eps": 1e-05,
138
+ "length_penalty": 1.0,
139
+ "max_length": 20,
140
+ "min_length": 0,
141
+ "mlp_ratio": 4.0,
142
+ "model_type": "donut-swin",
143
+ "no_repeat_ngram_size": 0,
144
+ "num_beam_groups": 1,
145
+ "num_beams": 1,
146
+ "num_channels": 3,
147
+ "num_heads": [
148
+ 4,
149
+ 8,
150
+ 16,
151
+ 32
152
+ ],
153
+ "num_layers": 4,
154
+ "num_return_sequences": 1,
155
+ "output_attentions": false,
156
+ "output_hidden_states": false,
157
+ "output_scores": false,
158
+ "pad_token_id": null,
159
+ "patch_size": 4,
160
+ "path_norm": true,
161
+ "prefix": null,
162
+ "problem_type": null,
163
+ "pruned_heads": {},
164
+ "qkv_bias": true,
165
+ "remove_invalid_values": false,
166
+ "repetition_penalty": 1.0,
167
+ "return_dict": true,
168
+ "return_dict_in_generate": false,
169
+ "sep_token_id": null,
170
+ "suppress_tokens": null,
171
+ "task_specific_params": null,
172
+ "temperature": 1.0,
173
+ "tf_legacy_loss": false,
174
+ "tie_encoder_decoder": false,
175
+ "tie_word_embeddings": true,
176
+ "tokenizer_class": null,
177
+ "top_k": 50,
178
+ "top_p": 1.0,
179
+ "torch_dtype": null,
180
+ "torchscript": false,
181
+ "typical_p": 1.0,
182
+ "use_absolute_embeddings": false,
183
+ "use_bfloat16": false,
184
+ "window_size": 10
185
+ },
186
+ "is_encoder_decoder": true,
187
+ "model_type": "vision-encoder-decoder",
188
+ "pad_token_id": 1,
189
+ "tie_word_embeddings": false,
190
+ "torch_dtype": "float32",
191
+ "transformers_version": "4.38.2"
192
+ }
generation_config.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 0,
4
+ "eos_token_id": 2,
5
+ "forced_eos_token_id": 2,
6
+ "pad_token_id": 1,
7
+ "transformers_version": "4.38.2"
8
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c53d94c63a7306a429aa181421e8eedf075a047f585561bd25dbf9b5bc5bc88
3
+ size 809111704
optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65debd166f8685e1a8bc5ff1e3862653f2d56190eb653faf2c04f881eb1489d
3
+ size 1615285631
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_align_long_axis": false,
3
+ "do_normalize": true,
4
+ "do_pad": true,
5
+ "do_rescale": true,
6
+ "do_resize": true,
7
+ "do_thumbnail": true,
8
+ "image_mean": [
9
+ 0.5,
10
+ 0.5,
11
+ 0.5
12
+ ],
13
+ "image_processor_type": "DonutImageProcessor",
14
+ "image_std": [
15
+ 0.5,
16
+ 0.5,
17
+ 0.5
18
+ ],
19
+ "processor_class": "DonutProcessor",
20
+ "resample": 2,
21
+ "rescale_factor": 0.00392156862745098,
22
+ "size": [
23
+ 960,
24
+ 550
25
+ ]
26
+ }
rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b15614d912a2b89c617584e8ec932228eb5c10c981726a18e255e380282d2f6
3
+ size 14244
scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6323a4a11036359a80107f6079ec08f6fd864b58d3a71938d832f444b4f7ac00
3
+ size 1064
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9e3dce4c326195d08fc3dd0f7e2eee1da8595c847bf4c1a9c78b7a82d47e2d
3
+ size 1296245
special_tokens_map.json ADDED
@@ -0,0 +1,137 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<s_untaxed_price>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "</s_untaxed_price>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<s_total_price>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "</s_total_price>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<s_tax>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "</s_tax>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<s_invoice_num>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "</s_invoice_num>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<s_invoice_date>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "</s_invoice_date>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<s>",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "</s>",
82
+ "lstrip": false,
83
+ "normalized": false,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ }
87
+ ],
88
+ "bos_token": {
89
+ "content": "<s>",
90
+ "lstrip": false,
91
+ "normalized": false,
92
+ "rstrip": false,
93
+ "single_word": false
94
+ },
95
+ "cls_token": {
96
+ "content": "<s>",
97
+ "lstrip": false,
98
+ "normalized": false,
99
+ "rstrip": false,
100
+ "single_word": false
101
+ },
102
+ "eos_token": {
103
+ "content": "</s>",
104
+ "lstrip": false,
105
+ "normalized": false,
106
+ "rstrip": false,
107
+ "single_word": false
108
+ },
109
+ "mask_token": {
110
+ "content": "<mask>",
111
+ "lstrip": true,
112
+ "normalized": true,
113
+ "rstrip": false,
114
+ "single_word": false
115
+ },
116
+ "pad_token": {
117
+ "content": "<pad>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false
122
+ },
123
+ "sep_token": {
124
+ "content": "</s>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false
129
+ },
130
+ "unk_token": {
131
+ "content": "<unk>",
132
+ "lstrip": false,
133
+ "normalized": false,
134
+ "rstrip": false,
135
+ "single_word": false
136
+ }
137
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "57521": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "57522": {
44
+ "content": "<sep/>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": false
50
+ },
51
+ "57523": {
52
+ "content": "<s_iitcdip>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "57524": {
60
+ "content": "<s_synthdog>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "57525": {
68
+ "content": "<s_untaxed_price>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "57526": {
76
+ "content": "</s_untaxed_price>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "57527": {
84
+ "content": "<s_total_price>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "57528": {
92
+ "content": "</s_total_price>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "57529": {
100
+ "content": "<s_tax>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "57530": {
108
+ "content": "</s_tax>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "57531": {
116
+ "content": "<s_invoice_num>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "57532": {
124
+ "content": "</s_invoice_num>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "57533": {
132
+ "content": "<s_invoice_date>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "57534": {
140
+ "content": "</s_invoice_date>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ }
147
+ },
148
+ "additional_special_tokens": [
149
+ "<s_untaxed_price>",
150
+ "</s_untaxed_price>",
151
+ "<s_total_price>",
152
+ "</s_total_price>",
153
+ "<s_tax>",
154
+ "</s_tax>",
155
+ "<s_invoice_num>",
156
+ "</s_invoice_num>",
157
+ "<s_invoice_date>",
158
+ "</s_invoice_date>",
159
+ "<s>",
160
+ "</s>"
161
+ ],
162
+ "bos_token": "<s>",
163
+ "clean_up_tokenization_spaces": true,
164
+ "cls_token": "<s>",
165
+ "eos_token": "</s>",
166
+ "mask_token": "<mask>",
167
+ "model_max_length": 1000000000000000019884624838656,
168
+ "pad_token": "<pad>",
169
+ "processor_class": "DonutProcessor",
170
+ "sep_token": "</s>",
171
+ "sp_model_kwargs": {},
172
+ "tokenizer_class": "XLMRobertaTokenizer",
173
+ "unk_token": "<unk>"
174
+ }
trainer_state.json ADDED
@@ -0,0 +1,413 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5620,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.18,
13
+ "grad_norm": 48.51668930053711,
14
+ "learning_rate": 1.98220640569395e-06,
15
+ "loss": 10.5512,
16
+ "step": 100
17
+ },
18
+ {
19
+ "epoch": 0.36,
20
+ "grad_norm": 33.89441680908203,
21
+ "learning_rate": 1.9644128113879e-06,
22
+ "loss": 6.656,
23
+ "step": 200
24
+ },
25
+ {
26
+ "epoch": 0.53,
27
+ "grad_norm": 54.47207260131836,
28
+ "learning_rate": 1.9466192170818503e-06,
29
+ "loss": 4.8936,
30
+ "step": 300
31
+ },
32
+ {
33
+ "epoch": 0.71,
34
+ "grad_norm": 37.983856201171875,
35
+ "learning_rate": 1.9288256227758005e-06,
36
+ "loss": 3.5277,
37
+ "step": 400
38
+ },
39
+ {
40
+ "epoch": 0.89,
41
+ "grad_norm": 23.24921417236328,
42
+ "learning_rate": 1.9110320284697506e-06,
43
+ "loss": 2.8756,
44
+ "step": 500
45
+ },
46
+ {
47
+ "epoch": 1.07,
48
+ "grad_norm": 26.32309913635254,
49
+ "learning_rate": 1.8932384341637008e-06,
50
+ "loss": 2.4437,
51
+ "step": 600
52
+ },
53
+ {
54
+ "epoch": 1.25,
55
+ "grad_norm": 154.72117614746094,
56
+ "learning_rate": 1.8754448398576511e-06,
57
+ "loss": 2.2582,
58
+ "step": 700
59
+ },
60
+ {
61
+ "epoch": 1.42,
62
+ "grad_norm": 16.39977264404297,
63
+ "learning_rate": 1.8576512455516013e-06,
64
+ "loss": 2.2289,
65
+ "step": 800
66
+ },
67
+ {
68
+ "epoch": 1.6,
69
+ "grad_norm": 22.533836364746094,
70
+ "learning_rate": 1.8398576512455514e-06,
71
+ "loss": 2.091,
72
+ "step": 900
73
+ },
74
+ {
75
+ "epoch": 1.78,
76
+ "grad_norm": 16.523881912231445,
77
+ "learning_rate": 1.8220640569395016e-06,
78
+ "loss": 2.0129,
79
+ "step": 1000
80
+ },
81
+ {
82
+ "epoch": 1.96,
83
+ "grad_norm": 69.78620147705078,
84
+ "learning_rate": 1.804270462633452e-06,
85
+ "loss": 1.926,
86
+ "step": 1100
87
+ },
88
+ {
89
+ "epoch": 2.14,
90
+ "grad_norm": 21.385257720947266,
91
+ "learning_rate": 1.786476868327402e-06,
92
+ "loss": 1.8193,
93
+ "step": 1200
94
+ },
95
+ {
96
+ "epoch": 2.31,
97
+ "grad_norm": 23.061298370361328,
98
+ "learning_rate": 1.7686832740213522e-06,
99
+ "loss": 1.804,
100
+ "step": 1300
101
+ },
102
+ {
103
+ "epoch": 2.49,
104
+ "grad_norm": 21.625669479370117,
105
+ "learning_rate": 1.7508896797153024e-06,
106
+ "loss": 1.7568,
107
+ "step": 1400
108
+ },
109
+ {
110
+ "epoch": 2.67,
111
+ "grad_norm": 13.98591136932373,
112
+ "learning_rate": 1.7330960854092527e-06,
113
+ "loss": 1.7313,
114
+ "step": 1500
115
+ },
116
+ {
117
+ "epoch": 2.85,
118
+ "grad_norm": 18.47169303894043,
119
+ "learning_rate": 1.7153024911032029e-06,
120
+ "loss": 1.733,
121
+ "step": 1600
122
+ },
123
+ {
124
+ "epoch": 3.02,
125
+ "grad_norm": 20.671327590942383,
126
+ "learning_rate": 1.697508896797153e-06,
127
+ "loss": 1.698,
128
+ "step": 1700
129
+ },
130
+ {
131
+ "epoch": 3.2,
132
+ "grad_norm": 20.78021812438965,
133
+ "learning_rate": 1.6797153024911032e-06,
134
+ "loss": 1.6192,
135
+ "step": 1800
136
+ },
137
+ {
138
+ "epoch": 3.38,
139
+ "grad_norm": 35.38755416870117,
140
+ "learning_rate": 1.6619217081850533e-06,
141
+ "loss": 1.5752,
142
+ "step": 1900
143
+ },
144
+ {
145
+ "epoch": 3.56,
146
+ "grad_norm": 24.105249404907227,
147
+ "learning_rate": 1.6441281138790034e-06,
148
+ "loss": 1.5921,
149
+ "step": 2000
150
+ },
151
+ {
152
+ "epoch": 3.74,
153
+ "grad_norm": 11.530924797058105,
154
+ "learning_rate": 1.6263345195729536e-06,
155
+ "loss": 1.5497,
156
+ "step": 2100
157
+ },
158
+ {
159
+ "epoch": 3.91,
160
+ "grad_norm": 17.551040649414062,
161
+ "learning_rate": 1.6085409252669037e-06,
162
+ "loss": 1.5751,
163
+ "step": 2200
164
+ },
165
+ {
166
+ "epoch": 4.09,
167
+ "grad_norm": 22.44804573059082,
168
+ "learning_rate": 1.590747330960854e-06,
169
+ "loss": 1.6072,
170
+ "step": 2300
171
+ },
172
+ {
173
+ "epoch": 4.27,
174
+ "grad_norm": 14.482297897338867,
175
+ "learning_rate": 1.5729537366548042e-06,
176
+ "loss": 1.552,
177
+ "step": 2400
178
+ },
179
+ {
180
+ "epoch": 4.45,
181
+ "grad_norm": 17.7537899017334,
182
+ "learning_rate": 1.5551601423487544e-06,
183
+ "loss": 1.4403,
184
+ "step": 2500
185
+ },
186
+ {
187
+ "epoch": 4.63,
188
+ "grad_norm": 23.001920700073242,
189
+ "learning_rate": 1.5373665480427045e-06,
190
+ "loss": 1.4955,
191
+ "step": 2600
192
+ },
193
+ {
194
+ "epoch": 4.8,
195
+ "grad_norm": 14.721695899963379,
196
+ "learning_rate": 1.5195729537366549e-06,
197
+ "loss": 1.4456,
198
+ "step": 2700
199
+ },
200
+ {
201
+ "epoch": 4.98,
202
+ "grad_norm": 15.371649742126465,
203
+ "learning_rate": 1.501779359430605e-06,
204
+ "loss": 1.4303,
205
+ "step": 2800
206
+ },
207
+ {
208
+ "epoch": 5.16,
209
+ "grad_norm": 14.734794616699219,
210
+ "learning_rate": 1.4839857651245552e-06,
211
+ "loss": 1.4544,
212
+ "step": 2900
213
+ },
214
+ {
215
+ "epoch": 5.34,
216
+ "grad_norm": 13.686590194702148,
217
+ "learning_rate": 1.4661921708185053e-06,
218
+ "loss": 1.401,
219
+ "step": 3000
220
+ },
221
+ {
222
+ "epoch": 5.52,
223
+ "grad_norm": 18.93415641784668,
224
+ "learning_rate": 1.4483985765124555e-06,
225
+ "loss": 1.4612,
226
+ "step": 3100
227
+ },
228
+ {
229
+ "epoch": 5.69,
230
+ "grad_norm": 9.70661735534668,
231
+ "learning_rate": 1.4306049822064056e-06,
232
+ "loss": 1.3558,
233
+ "step": 3200
234
+ },
235
+ {
236
+ "epoch": 5.87,
237
+ "grad_norm": 16.12574577331543,
238
+ "learning_rate": 1.4128113879003557e-06,
239
+ "loss": 1.3686,
240
+ "step": 3300
241
+ },
242
+ {
243
+ "epoch": 6.05,
244
+ "grad_norm": 29.739870071411133,
245
+ "learning_rate": 1.3950177935943059e-06,
246
+ "loss": 1.3703,
247
+ "step": 3400
248
+ },
249
+ {
250
+ "epoch": 6.23,
251
+ "grad_norm": 22.152677536010742,
252
+ "learning_rate": 1.377224199288256e-06,
253
+ "loss": 1.2662,
254
+ "step": 3500
255
+ },
256
+ {
257
+ "epoch": 6.41,
258
+ "grad_norm": 24.051326751708984,
259
+ "learning_rate": 1.3594306049822064e-06,
260
+ "loss": 1.35,
261
+ "step": 3600
262
+ },
263
+ {
264
+ "epoch": 6.58,
265
+ "grad_norm": 11.552955627441406,
266
+ "learning_rate": 1.3416370106761565e-06,
267
+ "loss": 1.3592,
268
+ "step": 3700
269
+ },
270
+ {
271
+ "epoch": 6.76,
272
+ "grad_norm": 16.08234977722168,
273
+ "learning_rate": 1.3238434163701067e-06,
274
+ "loss": 1.3566,
275
+ "step": 3800
276
+ },
277
+ {
278
+ "epoch": 6.94,
279
+ "grad_norm": 14.58088493347168,
280
+ "learning_rate": 1.3060498220640568e-06,
281
+ "loss": 1.3257,
282
+ "step": 3900
283
+ },
284
+ {
285
+ "epoch": 7.12,
286
+ "grad_norm": 12.278518676757812,
287
+ "learning_rate": 1.2882562277580072e-06,
288
+ "loss": 1.3254,
289
+ "step": 4000
290
+ },
291
+ {
292
+ "epoch": 7.3,
293
+ "grad_norm": 17.330495834350586,
294
+ "learning_rate": 1.2704626334519573e-06,
295
+ "loss": 1.2095,
296
+ "step": 4100
297
+ },
298
+ {
299
+ "epoch": 7.47,
300
+ "grad_norm": 13.842063903808594,
301
+ "learning_rate": 1.2526690391459075e-06,
302
+ "loss": 1.3475,
303
+ "step": 4200
304
+ },
305
+ {
306
+ "epoch": 7.65,
307
+ "grad_norm": 13.967167854309082,
308
+ "learning_rate": 1.2348754448398574e-06,
309
+ "loss": 1.2757,
310
+ "step": 4300
311
+ },
312
+ {
313
+ "epoch": 7.83,
314
+ "grad_norm": 18.25010871887207,
315
+ "learning_rate": 1.2170818505338078e-06,
316
+ "loss": 1.2795,
317
+ "step": 4400
318
+ },
319
+ {
320
+ "epoch": 8.01,
321
+ "grad_norm": 11.46198558807373,
322
+ "learning_rate": 1.199288256227758e-06,
323
+ "loss": 1.2648,
324
+ "step": 4500
325
+ },
326
+ {
327
+ "epoch": 8.19,
328
+ "grad_norm": 18.330867767333984,
329
+ "learning_rate": 1.181494661921708e-06,
330
+ "loss": 1.2345,
331
+ "step": 4600
332
+ },
333
+ {
334
+ "epoch": 8.36,
335
+ "grad_norm": 27.236454010009766,
336
+ "learning_rate": 1.1637010676156582e-06,
337
+ "loss": 1.2998,
338
+ "step": 4700
339
+ },
340
+ {
341
+ "epoch": 8.54,
342
+ "grad_norm": 15.08573055267334,
343
+ "learning_rate": 1.1459074733096086e-06,
344
+ "loss": 1.2578,
345
+ "step": 4800
346
+ },
347
+ {
348
+ "epoch": 8.72,
349
+ "grad_norm": 15.639131546020508,
350
+ "learning_rate": 1.1281138790035587e-06,
351
+ "loss": 1.2062,
352
+ "step": 4900
353
+ },
354
+ {
355
+ "epoch": 8.9,
356
+ "grad_norm": 22.758560180664062,
357
+ "learning_rate": 1.1103202846975088e-06,
358
+ "loss": 1.2305,
359
+ "step": 5000
360
+ },
361
+ {
362
+ "epoch": 9.07,
363
+ "grad_norm": 11.382159233093262,
364
+ "learning_rate": 1.092526690391459e-06,
365
+ "loss": 1.2236,
366
+ "step": 5100
367
+ },
368
+ {
369
+ "epoch": 9.25,
370
+ "grad_norm": 14.228442192077637,
371
+ "learning_rate": 1.0747330960854093e-06,
372
+ "loss": 1.1871,
373
+ "step": 5200
374
+ },
375
+ {
376
+ "epoch": 9.43,
377
+ "grad_norm": 16.07115936279297,
378
+ "learning_rate": 1.0569395017793595e-06,
379
+ "loss": 1.2286,
380
+ "step": 5300
381
+ },
382
+ {
383
+ "epoch": 9.61,
384
+ "grad_norm": 12.73045539855957,
385
+ "learning_rate": 1.0391459074733096e-06,
386
+ "loss": 1.2837,
387
+ "step": 5400
388
+ },
389
+ {
390
+ "epoch": 9.79,
391
+ "grad_norm": 19.55732536315918,
392
+ "learning_rate": 1.0213523131672596e-06,
393
+ "loss": 1.1911,
394
+ "step": 5500
395
+ },
396
+ {
397
+ "epoch": 9.96,
398
+ "grad_norm": 13.422231674194336,
399
+ "learning_rate": 1.00355871886121e-06,
400
+ "loss": 1.1532,
401
+ "step": 5600
402
+ }
403
+ ],
404
+ "logging_steps": 100,
405
+ "max_steps": 11240,
406
+ "num_input_tokens_seen": 0,
407
+ "num_train_epochs": 20,
408
+ "save_steps": 500,
409
+ "total_flos": 1.510200611453952e+19,
410
+ "train_batch_size": 2,
411
+ "trial_name": null,
412
+ "trial_params": null
413
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22da3339874e661b72481662e90c368b4085b9b260c4cb2ef0544e160b44b549
3
+ size 5048