Hugging Face's logo

benjamintli
/
rt-detr-v2_barcode-detection

Object Detection
Transformers
TensorBoard
Safetensors
rt_detr_v2
Generated from Trainer
Model card Files
xet
 Metrics Community
benjamintli commited on
Commit
8c98d9a
·
verified ·
1 Parent(s): e1c5ef5

Training in progress, epoch 8, checkpoint

Browse files
Files changed (8) hide show
  1. checkpoint-13088/config.json +125 -0
  2. checkpoint-13088/model.safetensors +3 -0
  3. checkpoint-13088/optimizer.pt +3 -0
  4. checkpoint-13088/preprocessor_config.json +36 -0
  5. checkpoint-13088/rng_state.pth +3 -0
  6. checkpoint-13088/scheduler.pt +3 -0
  7. checkpoint-13088/trainer_state.json +392 -0
  8. checkpoint-13088/training_args.bin +3 -0
checkpoint-13088/config.json ADDED
@@ -0,0 +1,125 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "silu",
4
+ "anchor_image_size": null,
5
+ "architectures": [
6
+ "RTDetrV2ForObjectDetection"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "auxiliary_loss": true,
10
+ "backbone": null,
11
+ "backbone_config": {
12
+ "depths": [
13
+ 2,
14
+ 2,
15
+ 2,
16
+ 2
17
+ ],
18
+ "downsample_in_bottleneck": false,
19
+ "downsample_in_first_stage": false,
20
+ "dtype": "float32",
21
+ "embedding_size": 64,
22
+ "hidden_act": "relu",
23
+ "hidden_sizes": [
24
+ 64,
25
+ 128,
26
+ 256,
27
+ 512
28
+ ],
29
+ "layer_type": "basic",
30
+ "model_type": "rt_detr_resnet",
31
+ "num_channels": 3,
32
+ "out_features": [
33
+ "stage2",
34
+ "stage3",
35
+ "stage4"
36
+ ],
37
+ "out_indices": [
38
+ 2,
39
+ 3,
40
+ 4
41
+ ],
42
+ "stage_names": [
43
+ "stem",
44
+ "stage1",
45
+ "stage2",
46
+ "stage3",
47
+ "stage4"
48
+ ]
49
+ },
50
+ "backbone_kwargs": null,
51
+ "batch_norm_eps": 1e-05,
52
+ "box_noise_scale": 1.0,
53
+ "d_model": 256,
54
+ "decoder_activation_function": "relu",
55
+ "decoder_attention_heads": 8,
56
+ "decoder_ffn_dim": 1024,
57
+ "decoder_in_channels": [
58
+ 256,
59
+ 256,
60
+ 256
61
+ ],
62
+ "decoder_layers": 3,
63
+ "decoder_method": "default",
64
+ "decoder_n_levels": 3,
65
+ "decoder_n_points": 4,
66
+ "decoder_offset_scale": 0.5,
67
+ "disable_custom_kernels": true,
68
+ "dropout": 0.0,
69
+ "dtype": "float32",
70
+ "encode_proj_layers": [
71
+ 2
72
+ ],
73
+ "encoder_activation_function": "gelu",
74
+ "encoder_attention_heads": 8,
75
+ "encoder_ffn_dim": 1024,
76
+ "encoder_hidden_dim": 256,
77
+ "encoder_in_channels": [
78
+ 128,
79
+ 256,
80
+ 512
81
+ ],
82
+ "encoder_layers": 1,
83
+ "eos_coefficient": 0.0001,
84
+ "eval_size": null,
85
+ "feat_strides": [
86
+ 8,
87
+ 16,
88
+ 32
89
+ ],
90
+ "focal_loss_alpha": 0.75,
91
+ "focal_loss_gamma": 2.0,
92
+ "freeze_backbone_batch_norms": true,
93
+ "hidden_expansion": 0.5,
94
+ "id2label": {
95
+ "0": "barcode"
96
+ },
97
+ "initializer_bias_prior_prob": null,
98
+ "initializer_range": 0.01,
99
+ "is_encoder_decoder": true,
100
+ "label2id": {
101
+ "barcode": 0
102
+ },
103
+ "label_noise_ratio": 0.5,
104
+ "layer_norm_eps": 1e-05,
105
+ "learn_initial_query": false,
106
+ "matcher_alpha": 0.25,
107
+ "matcher_bbox_cost": 5.0,
108
+ "matcher_class_cost": 2.0,
109
+ "matcher_gamma": 2.0,
110
+ "matcher_giou_cost": 2.0,
111
+ "model_type": "rt_detr_v2",
112
+ "normalize_before": false,
113
+ "num_denoising": 100,
114
+ "num_feature_levels": 3,
115
+ "num_queries": 300,
116
+ "positional_encoding_temperature": 10000,
117
+ "transformers_version": "4.57.3",
118
+ "use_focal_loss": true,
119
+ "use_pretrained_backbone": false,
120
+ "use_timm_backbone": false,
121
+ "weight_loss_bbox": 5.0,
122
+ "weight_loss_giou": 2.0,
123
+ "weight_loss_vfl": 1.0,
124
+ "with_box_refine": true
125
+ }
checkpoint-13088/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:520382c539c3af36262c8d8da94bb499c1bf6a9e4c5aade427b953a61ecd8aec
3
+ size 80498888
checkpoint-13088/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a75cf69d5acc4a784ad2d1df197583a8bbdf01fb9dcd083977fc7c41efba506a
3
+ size 160838091
checkpoint-13088/preprocessor_config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": null,
3
+ "data_format": "channels_first",
4
+ "default_to_square": false,
5
+ "device": null,
6
+ "disable_grouping": null,
7
+ "do_center_crop": null,
8
+ "do_convert_annotations": true,
9
+ "do_convert_rgb": null,
10
+ "do_normalize": false,
11
+ "do_pad": false,
12
+ "do_rescale": true,
13
+ "do_resize": true,
14
+ "format": "coco_detection",
15
+ "image_mean": [
16
+ 0.485,
17
+ 0.456,
18
+ 0.406
19
+ ],
20
+ "image_processor_type": "RTDetrImageProcessorFast",
21
+ "image_std": [
22
+ 0.229,
23
+ 0.224,
24
+ 0.225
25
+ ],
26
+ "input_data_format": null,
27
+ "pad_size": null,
28
+ "resample": 2,
29
+ "rescale_factor": 0.00392156862745098,
30
+ "return_segmentation_masks": null,
31
+ "return_tensors": null,
32
+ "size": {
33
+ "height": 480,
34
+ "width": 480
35
+ }
36
+ }
checkpoint-13088/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1180fcfc7bfb9ebc78e53052788d8df5536da7332c10b34f406467887019bd3
3
+ size 14645
checkpoint-13088/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e7445e5f447a13482796a193cfa0aaeb6d276c9f744ddb3d22e3e23185736fc
3
+ size 1465
checkpoint-13088/trainer_state.json ADDED
@@ -0,0 +1,392 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 8180,
3
+ "best_metric": 0.6944,
4
+ "best_model_checkpoint": "output/checkpoint-8180",
5
+ "epoch": 8.0,
6
+ "eval_steps": 500,
7
+ "global_step": 13088,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.3056234718826406,
14
+ "grad_norm": 22.77391815185547,
15
+ "learning_rate": 4.255239520958084e-05,
16
+ "loss": 52.1418,
17
+ "step": 500
18
+ },
19
+ {
20
+ "epoch": 0.6112469437652812,
21
+ "grad_norm": 15.196788787841797,
22
+ "learning_rate": 2.383982035928144e-05,
23
+ "loss": 7.7913,
24
+ "step": 1000
25
+ },
26
+ {
27
+ "epoch": 0.9168704156479217,
28
+ "grad_norm": 13.545781135559082,
29
+ "learning_rate": 5.127245508982037e-06,
30
+ "loss": 7.43,
31
+ "step": 1500
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "eval_loss": 5.054670810699463,
36
+ "eval_map": 0.623,
37
+ "eval_map_50": 0.7756,
38
+ "eval_map_75": 0.6841,
39
+ "eval_map_barcode": 0.623,
40
+ "eval_map_large": 0.6594,
41
+ "eval_map_medium": 0.6674,
42
+ "eval_map_small": 0.2648,
43
+ "eval_mar_1": 0.3542,
44
+ "eval_mar_10": 0.8117,
45
+ "eval_mar_100": 0.8521,
46
+ "eval_mar_100_barcode": 0.8521,
47
+ "eval_mar_large": 0.8749,
48
+ "eval_mar_medium": 0.8552,
49
+ "eval_mar_small": 0.5325,
50
+ "eval_runtime": 71.7672,
51
+ "eval_samples_per_second": 39.071,
52
+ "eval_steps_per_second": 4.891,
53
+ "step": 1636
54
+ },
55
+ {
56
+ "epoch": 1.2224938875305624,
57
+ "grad_norm": 14.290430068969727,
58
+ "learning_rate": 3.921954314720812e-05,
59
+ "loss": 7.2123,
60
+ "step": 2000
61
+ },
62
+ {
63
+ "epoch": 1.528117359413203,
64
+ "grad_norm": 15.990227699279785,
65
+ "learning_rate": 3.6046954314720814e-05,
66
+ "loss": 7.0995,
67
+ "step": 2500
68
+ },
69
+ {
70
+ "epoch": 1.8337408312958434,
71
+ "grad_norm": 11.737943649291992,
72
+ "learning_rate": 3.2874365482233505e-05,
73
+ "loss": 6.9538,
74
+ "step": 3000
75
+ },
76
+ {
77
+ "epoch": 2.0,
78
+ "eval_loss": 4.950796604156494,
79
+ "eval_map": 0.6297,
80
+ "eval_map_50": 0.7829,
81
+ "eval_map_75": 0.6878,
82
+ "eval_map_barcode": 0.6297,
83
+ "eval_map_large": 0.7109,
84
+ "eval_map_medium": 0.6449,
85
+ "eval_map_small": 0.261,
86
+ "eval_mar_1": 0.3612,
87
+ "eval_mar_10": 0.8238,
88
+ "eval_mar_100": 0.8604,
89
+ "eval_mar_100_barcode": 0.8604,
90
+ "eval_mar_large": 0.8794,
91
+ "eval_mar_medium": 0.8624,
92
+ "eval_mar_small": 0.5972,
93
+ "eval_runtime": 67.4554,
94
+ "eval_samples_per_second": 41.568,
95
+ "eval_steps_per_second": 5.203,
96
+ "step": 3272
97
+ },
98
+ {
99
+ "epoch": 2.139364303178484,
100
+ "grad_norm": 14.22537899017334,
101
+ "learning_rate": 2.9701776649746192e-05,
102
+ "loss": 6.8515,
103
+ "step": 3500
104
+ },
105
+ {
106
+ "epoch": 2.444987775061125,
107
+ "grad_norm": 19.026344299316406,
108
+ "learning_rate": 2.6529187817258883e-05,
109
+ "loss": 6.7831,
110
+ "step": 4000
111
+ },
112
+ {
113
+ "epoch": 2.750611246943765,
114
+ "grad_norm": 13.106438636779785,
115
+ "learning_rate": 2.3356598984771574e-05,
116
+ "loss": 6.6733,
117
+ "step": 4500
118
+ },
119
+ {
120
+ "epoch": 3.0,
121
+ "eval_loss": 5.005562782287598,
122
+ "eval_map": 0.6553,
123
+ "eval_map_50": 0.8073,
124
+ "eval_map_75": 0.7122,
125
+ "eval_map_barcode": 0.6553,
126
+ "eval_map_large": 0.7359,
127
+ "eval_map_medium": 0.6782,
128
+ "eval_map_small": 0.2319,
129
+ "eval_mar_1": 0.3481,
130
+ "eval_mar_10": 0.8201,
131
+ "eval_mar_100": 0.8542,
132
+ "eval_mar_100_barcode": 0.8542,
133
+ "eval_mar_large": 0.8712,
134
+ "eval_mar_medium": 0.8573,
135
+ "eval_mar_small": 0.6107,
136
+ "eval_runtime": 62.2135,
137
+ "eval_samples_per_second": 45.071,
138
+ "eval_steps_per_second": 5.642,
139
+ "step": 4908
140
+ },
141
+ {
142
+ "epoch": 3.056234718826406,
143
+ "grad_norm": 15.877172470092773,
144
+ "learning_rate": 2.0184010152284265e-05,
145
+ "loss": 6.6537,
146
+ "step": 5000
147
+ },
148
+ {
149
+ "epoch": 3.3618581907090466,
150
+ "grad_norm": 21.57083511352539,
151
+ "learning_rate": 1.7011421319796956e-05,
152
+ "loss": 6.5493,
153
+ "step": 5500
154
+ },
155
+ {
156
+ "epoch": 3.667481662591687,
157
+ "grad_norm": 11.728562355041504,
158
+ "learning_rate": 1.3838832487309645e-05,
159
+ "loss": 6.4896,
160
+ "step": 6000
161
+ },
162
+ {
163
+ "epoch": 3.9731051344743276,
164
+ "grad_norm": 9.994644165039062,
165
+ "learning_rate": 1.0666243654822336e-05,
166
+ "loss": 6.5783,
167
+ "step": 6500
168
+ },
169
+ {
170
+ "epoch": 4.0,
171
+ "eval_loss": 5.049291610717773,
172
+ "eval_map": 0.6524,
173
+ "eval_map_50": 0.808,
174
+ "eval_map_75": 0.711,
175
+ "eval_map_barcode": 0.6524,
176
+ "eval_map_large": 0.7472,
177
+ "eval_map_medium": 0.6782,
178
+ "eval_map_small": 0.2391,
179
+ "eval_mar_1": 0.3581,
180
+ "eval_mar_10": 0.8268,
181
+ "eval_mar_100": 0.8629,
182
+ "eval_mar_100_barcode": 0.8629,
183
+ "eval_mar_large": 0.8819,
184
+ "eval_mar_medium": 0.8639,
185
+ "eval_mar_small": 0.6066,
186
+ "eval_runtime": 62.2975,
187
+ "eval_samples_per_second": 45.01,
188
+ "eval_steps_per_second": 5.634,
189
+ "step": 6544
190
+ },
191
+ {
192
+ "epoch": 4.278728606356968,
193
+ "grad_norm": 14.572711944580078,
194
+ "learning_rate": 7.493654822335027e-06,
195
+ "loss": 6.434,
196
+ "step": 7000
197
+ },
198
+ {
199
+ "epoch": 4.5843520782396086,
200
+ "grad_norm": 16.59506607055664,
201
+ "learning_rate": 4.321065989847716e-06,
202
+ "loss": 6.456,
203
+ "step": 7500
204
+ },
205
+ {
206
+ "epoch": 4.88997555012225,
207
+ "grad_norm": 12.59866714477539,
208
+ "learning_rate": 1.148477157360406e-06,
209
+ "loss": 6.4986,
210
+ "step": 8000
211
+ },
212
+ {
213
+ "epoch": 5.0,
214
+ "eval_loss": 5.020848274230957,
215
+ "eval_map": 0.6944,
216
+ "eval_map_50": 0.8578,
217
+ "eval_map_75": 0.7542,
218
+ "eval_map_barcode": 0.6944,
219
+ "eval_map_large": 0.7651,
220
+ "eval_map_medium": 0.7135,
221
+ "eval_map_small": 0.2808,
222
+ "eval_mar_1": 0.3706,
223
+ "eval_mar_10": 0.8307,
224
+ "eval_mar_100": 0.8611,
225
+ "eval_mar_100_barcode": 0.8611,
226
+ "eval_mar_large": 0.879,
227
+ "eval_mar_medium": 0.863,
228
+ "eval_mar_small": 0.6131,
229
+ "eval_runtime": 59.6178,
230
+ "eval_samples_per_second": 47.033,
231
+ "eval_steps_per_second": 5.888,
232
+ "step": 8180
233
+ },
234
+ {
235
+ "epoch": 5.19559902200489,
236
+ "grad_norm": 20.511093139648438,
237
+ "learning_rate": 6.9199243379571245e-06,
238
+ "loss": 6.3808,
239
+ "step": 8500
240
+ },
241
+ {
242
+ "epoch": 5.50122249388753,
243
+ "grad_norm": 11.316178321838379,
244
+ "learning_rate": 4.2927700714585965e-06,
245
+ "loss": 6.4084,
246
+ "step": 9000
247
+ },
248
+ {
249
+ "epoch": 5.806845965770171,
250
+ "grad_norm": 136.69931030273438,
251
+ "learning_rate": 1.6656158049600673e-06,
252
+ "loss": 6.4056,
253
+ "step": 9500
254
+ },
255
+ {
256
+ "epoch": 6.0,
257
+ "eval_loss": 5.011576175689697,
258
+ "eval_map": 0.6843,
259
+ "eval_map_50": 0.8399,
260
+ "eval_map_75": 0.7445,
261
+ "eval_map_barcode": 0.6843,
262
+ "eval_map_large": 0.7607,
263
+ "eval_map_medium": 0.7126,
264
+ "eval_map_small": 0.3026,
265
+ "eval_mar_1": 0.371,
266
+ "eval_mar_10": 0.8374,
267
+ "eval_mar_100": 0.8664,
268
+ "eval_mar_100_barcode": 0.8664,
269
+ "eval_mar_large": 0.8864,
270
+ "eval_mar_medium": 0.8646,
271
+ "eval_mar_small": 0.6176,
272
+ "eval_runtime": 61.3823,
273
+ "eval_samples_per_second": 45.681,
274
+ "eval_steps_per_second": 5.718,
275
+ "step": 9816
276
+ },
277
+ {
278
+ "epoch": 6.112469437652812,
279
+ "grad_norm": 17.210508346557617,
280
+ "learning_rate": 1.2077729121050987e-05,
281
+ "loss": 6.4193,
282
+ "step": 10000
283
+ },
284
+ {
285
+ "epoch": 6.418092909535452,
286
+ "grad_norm": 11.933845520019531,
287
+ "learning_rate": 1.0122771348138881e-05,
288
+ "loss": 6.4259,
289
+ "step": 10500
290
+ },
291
+ {
292
+ "epoch": 6.723716381418093,
293
+ "grad_norm": 9.762476921081543,
294
+ "learning_rate": 8.167813575226775e-06,
295
+ "loss": 6.4074,
296
+ "step": 11000
297
+ },
298
+ {
299
+ "epoch": 7.0,
300
+ "eval_loss": 5.022867679595947,
301
+ "eval_map": 0.653,
302
+ "eval_map_50": 0.7989,
303
+ "eval_map_75": 0.7106,
304
+ "eval_map_barcode": 0.653,
305
+ "eval_map_large": 0.731,
306
+ "eval_map_medium": 0.7112,
307
+ "eval_map_small": 0.2768,
308
+ "eval_mar_1": 0.3513,
309
+ "eval_mar_10": 0.8326,
310
+ "eval_mar_100": 0.8694,
311
+ "eval_mar_100_barcode": 0.8694,
312
+ "eval_mar_large": 0.8896,
313
+ "eval_mar_medium": 0.8675,
314
+ "eval_mar_small": 0.619,
315
+ "eval_runtime": 61.6541,
316
+ "eval_samples_per_second": 45.48,
317
+ "eval_steps_per_second": 5.693,
318
+ "step": 11452
319
+ },
320
+ {
321
+ "epoch": 7.029339853300733,
322
+ "grad_norm": 14.839144706726074,
323
+ "learning_rate": 6.21285580231467e-06,
324
+ "loss": 6.4012,
325
+ "step": 11500
326
+ },
327
+ {
328
+ "epoch": 7.334963325183374,
329
+ "grad_norm": 14.738309860229492,
330
+ "learning_rate": 4.257898029402565e-06,
331
+ "loss": 6.4156,
332
+ "step": 12000
333
+ },
334
+ {
335
+ "epoch": 7.640586797066015,
336
+ "grad_norm": 13.090365409851074,
337
+ "learning_rate": 2.30294025649046e-06,
338
+ "loss": 6.3254,
339
+ "step": 12500
340
+ },
341
+ {
342
+ "epoch": 7.946210268948655,
343
+ "grad_norm": 14.906225204467773,
344
+ "learning_rate": 3.4798248357835476e-07,
345
+ "loss": 6.2576,
346
+ "step": 13000
347
+ },
348
+ {
349
+ "epoch": 8.0,
350
+ "eval_loss": 5.033987522125244,
351
+ "eval_map": 0.6583,
352
+ "eval_map_50": 0.8036,
353
+ "eval_map_75": 0.7156,
354
+ "eval_map_barcode": 0.6583,
355
+ "eval_map_large": 0.747,
356
+ "eval_map_medium": 0.7152,
357
+ "eval_map_small": 0.2754,
358
+ "eval_mar_1": 0.3589,
359
+ "eval_mar_10": 0.833,
360
+ "eval_mar_100": 0.8673,
361
+ "eval_mar_100_barcode": 0.8673,
362
+ "eval_mar_large": 0.8872,
363
+ "eval_mar_medium": 0.8656,
364
+ "eval_mar_small": 0.6183,
365
+ "eval_runtime": 58.1834,
366
+ "eval_samples_per_second": 48.192,
367
+ "eval_steps_per_second": 6.033,
368
+ "step": 13088
369
+ }
370
+ ],
371
+ "logging_steps": 500,
372
+ "max_steps": 13088,
373
+ "num_input_tokens_seen": 0,
374
+ "num_train_epochs": 8,
375
+ "save_steps": 500,
376
+ "stateful_callbacks": {
377
+ "TrainerControl": {
378
+ "args": {
379
+ "should_epoch_stop": false,
380
+ "should_evaluate": false,
381
+ "should_log": false,
382
+ "should_save": true,
383
+ "should_training_stop": true
384
+ },
385
+ "attributes": {}
386
+ }
387
+ },
388
+ "total_flos": 8.715453650952192e+18,
389
+ "train_batch_size": 8,
390
+ "trial_name": null,
391
+ "trial_params": null
392
+ }
checkpoint-13088/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43a030ff29127faf132a64769e81457c4579d6d6f3ae9342407fb43c55697357
3
+ size 5905