shylhy commited on
Commit
090fe41
·
verified ·
1 Parent(s): 50fa858

Training in progress, epoch 7

Browse files
README.md ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: cc-by-nc-4.0
4
+ base_model: MCG-NJU/videomae-large
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: videomae-large-finetuned-deepfake-subset
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # videomae-large-finetuned-deepfake-subset
16
+
17
+ This model is a fine-tuned version of [MCG-NJU/videomae-large](https://huggingface.co/MCG-NJU/videomae-large) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.4257
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 5e-05
39
+ - train_batch_size: 8
40
+ - eval_batch_size: 8
41
+ - seed: 42
42
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
43
+ - lr_scheduler_type: linear
44
+ - lr_scheduler_warmup_ratio: 0.1
45
+ - training_steps: 2235
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:-----:|:----:|:---------------:|
51
+ | 0.7063 | 0.2 | 447 | 0.6715 |
52
+ | 0.6721 | 1.2 | 894 | 0.6247 |
53
+ | 0.4569 | 2.2 | 1341 | 0.6014 |
54
+ | 0.3716 | 3.2 | 1788 | 0.5119 |
55
+ | 0.3029 | 4.2 | 2235 | 0.4187 |
56
+
57
+
58
+ ### Framework versions
59
+
60
+ - Transformers 4.44.2
61
+ - Pytorch 2.5.0+cu121
62
+ - Datasets 3.1.0
63
+ - Tokenizers 0.19.1
all_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.2,
3
+ "eval_loss": 0.42570874094963074,
4
+ "eval_runtime": 1996.1684,
5
+ "eval_samples_per_second": 9.919,
6
+ "eval_steps_per_second": 1.24
7
+ }
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "MCG-NJU/videomae-large",
3
+ "architectures": [
4
+ "VideoMAEForVideoClassification"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.0,
7
+ "decoder_hidden_size": 512,
8
+ "decoder_intermediate_size": 2048,
9
+ "decoder_num_attention_heads": 8,
10
+ "decoder_num_hidden_layers": 12,
11
+ "hidden_act": "gelu",
12
+ "hidden_dropout_prob": 0.0,
13
+ "hidden_size": 1024,
14
+ "id2label": {
15
+ "0": "deepfake",
16
+ "1": "real"
17
+ },
18
+ "image_size": 224,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 4096,
21
+ "label2id": {
22
+ "deepfake": 0,
23
+ "real": 1
24
+ },
25
+ "layer_norm_eps": 1e-12,
26
+ "model_type": "videomae",
27
+ "norm_pix_loss": true,
28
+ "num_attention_heads": 16,
29
+ "num_channels": 3,
30
+ "num_frames": 16,
31
+ "num_hidden_layers": 24,
32
+ "patch_size": 16,
33
+ "problem_type": "single_label_classification",
34
+ "qkv_bias": true,
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.44.2",
37
+ "tubelet_size": 2,
38
+ "use_mean_pooling": false
39
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bca7c090098ee1563fbeadb22f3f9de079bc6dae132a1272bf784a056943d29e
3
+ size 1215496248
preprocessor_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_normalize": true,
8
+ "do_rescale": true,
9
+ "do_resize": true,
10
+ "image_mean": [
11
+ 0.485,
12
+ 0.456,
13
+ 0.406
14
+ ],
15
+ "image_processor_type": "VideoMAEImageProcessor",
16
+ "image_std": [
17
+ 0.229,
18
+ 0.224,
19
+ 0.225
20
+ ],
21
+ "resample": 2,
22
+ "rescale_factor": 0.00392156862745098,
23
+ "size": {
24
+ "shortest_edge": 224
25
+ }
26
+ }
test_results.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 4.2,
3
+ "eval_loss": 0.42570874094963074,
4
+ "eval_runtime": 1996.1684,
5
+ "eval_samples_per_second": 9.919,
6
+ "eval_steps_per_second": 1.24
7
+ }
trainer_state.json ADDED
@@ -0,0 +1,1659 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4186529219150543,
3
+ "best_model_checkpoint": "videomae-large-finetuned-deepfake-subset/checkpoint-2235",
4
+ "epoch": 4.2,
5
+ "eval_steps": 500,
6
+ "global_step": 2235,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.0044742729306487695,
13
+ "grad_norm": 9.121190071105957,
14
+ "learning_rate": 2.2321428571428573e-06,
15
+ "loss": 0.836,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.008948545861297539,
20
+ "grad_norm": 15.70935344696045,
21
+ "learning_rate": 4.464285714285715e-06,
22
+ "loss": 0.7173,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.013422818791946308,
27
+ "grad_norm": 11.579286575317383,
28
+ "learning_rate": 6.696428571428572e-06,
29
+ "loss": 0.6874,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.017897091722595078,
34
+ "grad_norm": 10.262760162353516,
35
+ "learning_rate": 8.92857142857143e-06,
36
+ "loss": 0.6875,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.02237136465324385,
41
+ "grad_norm": 8.599472999572754,
42
+ "learning_rate": 1.1160714285714287e-05,
43
+ "loss": 0.6995,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.026845637583892617,
48
+ "grad_norm": 17.292194366455078,
49
+ "learning_rate": 1.3392857142857144e-05,
50
+ "loss": 0.6985,
51
+ "step": 60
52
+ },
53
+ {
54
+ "epoch": 0.03131991051454139,
55
+ "grad_norm": 9.358028411865234,
56
+ "learning_rate": 1.5625e-05,
57
+ "loss": 0.7185,
58
+ "step": 70
59
+ },
60
+ {
61
+ "epoch": 0.035794183445190156,
62
+ "grad_norm": 15.182479858398438,
63
+ "learning_rate": 1.785714285714286e-05,
64
+ "loss": 0.7199,
65
+ "step": 80
66
+ },
67
+ {
68
+ "epoch": 0.040268456375838924,
69
+ "grad_norm": 13.037087440490723,
70
+ "learning_rate": 2.0089285714285717e-05,
71
+ "loss": 0.6846,
72
+ "step": 90
73
+ },
74
+ {
75
+ "epoch": 0.0447427293064877,
76
+ "grad_norm": 9.370818138122559,
77
+ "learning_rate": 2.2321428571428575e-05,
78
+ "loss": 0.7172,
79
+ "step": 100
80
+ },
81
+ {
82
+ "epoch": 0.049217002237136466,
83
+ "grad_norm": 4.834555149078369,
84
+ "learning_rate": 2.455357142857143e-05,
85
+ "loss": 0.6675,
86
+ "step": 110
87
+ },
88
+ {
89
+ "epoch": 0.053691275167785234,
90
+ "grad_norm": 7.898409366607666,
91
+ "learning_rate": 2.6785714285714288e-05,
92
+ "loss": 0.6891,
93
+ "step": 120
94
+ },
95
+ {
96
+ "epoch": 0.058165548098434,
97
+ "grad_norm": 4.438570499420166,
98
+ "learning_rate": 2.9017857142857146e-05,
99
+ "loss": 0.6143,
100
+ "step": 130
101
+ },
102
+ {
103
+ "epoch": 0.06263982102908278,
104
+ "grad_norm": 7.656393527984619,
105
+ "learning_rate": 3.125e-05,
106
+ "loss": 0.7623,
107
+ "step": 140
108
+ },
109
+ {
110
+ "epoch": 0.06711409395973154,
111
+ "grad_norm": 5.428772926330566,
112
+ "learning_rate": 3.348214285714286e-05,
113
+ "loss": 0.6636,
114
+ "step": 150
115
+ },
116
+ {
117
+ "epoch": 0.07158836689038031,
118
+ "grad_norm": 7.641555309295654,
119
+ "learning_rate": 3.571428571428572e-05,
120
+ "loss": 0.7166,
121
+ "step": 160
122
+ },
123
+ {
124
+ "epoch": 0.07606263982102908,
125
+ "grad_norm": 6.560756683349609,
126
+ "learning_rate": 3.794642857142857e-05,
127
+ "loss": 0.6535,
128
+ "step": 170
129
+ },
130
+ {
131
+ "epoch": 0.08053691275167785,
132
+ "grad_norm": 4.703638076782227,
133
+ "learning_rate": 4.017857142857143e-05,
134
+ "loss": 0.7921,
135
+ "step": 180
136
+ },
137
+ {
138
+ "epoch": 0.08501118568232663,
139
+ "grad_norm": 4.143082618713379,
140
+ "learning_rate": 4.2410714285714285e-05,
141
+ "loss": 0.7667,
142
+ "step": 190
143
+ },
144
+ {
145
+ "epoch": 0.0894854586129754,
146
+ "grad_norm": 4.66807746887207,
147
+ "learning_rate": 4.464285714285715e-05,
148
+ "loss": 0.7517,
149
+ "step": 200
150
+ },
151
+ {
152
+ "epoch": 0.09395973154362416,
153
+ "grad_norm": 5.823754787445068,
154
+ "learning_rate": 4.6875e-05,
155
+ "loss": 0.7432,
156
+ "step": 210
157
+ },
158
+ {
159
+ "epoch": 0.09843400447427293,
160
+ "grad_norm": 3.090379476547241,
161
+ "learning_rate": 4.910714285714286e-05,
162
+ "loss": 0.7178,
163
+ "step": 220
164
+ },
165
+ {
166
+ "epoch": 0.1029082774049217,
167
+ "grad_norm": 3.7575201988220215,
168
+ "learning_rate": 4.985082048731974e-05,
169
+ "loss": 0.7814,
170
+ "step": 230
171
+ },
172
+ {
173
+ "epoch": 0.10738255033557047,
174
+ "grad_norm": 2.1599221229553223,
175
+ "learning_rate": 4.960218796618598e-05,
176
+ "loss": 0.6634,
177
+ "step": 240
178
+ },
179
+ {
180
+ "epoch": 0.11185682326621924,
181
+ "grad_norm": 3.909114122390747,
182
+ "learning_rate": 4.935355544505221e-05,
183
+ "loss": 0.7343,
184
+ "step": 250
185
+ },
186
+ {
187
+ "epoch": 0.116331096196868,
188
+ "grad_norm": 2.0854549407958984,
189
+ "learning_rate": 4.910492292391845e-05,
190
+ "loss": 0.735,
191
+ "step": 260
192
+ },
193
+ {
194
+ "epoch": 0.12080536912751678,
195
+ "grad_norm": 1.8805179595947266,
196
+ "learning_rate": 4.8856290402784686e-05,
197
+ "loss": 0.7272,
198
+ "step": 270
199
+ },
200
+ {
201
+ "epoch": 0.12527964205816555,
202
+ "grad_norm": 3.551156759262085,
203
+ "learning_rate": 4.860765788165092e-05,
204
+ "loss": 0.7012,
205
+ "step": 280
206
+ },
207
+ {
208
+ "epoch": 0.1297539149888143,
209
+ "grad_norm": 1.680455207824707,
210
+ "learning_rate": 4.8359025360517155e-05,
211
+ "loss": 0.7097,
212
+ "step": 290
213
+ },
214
+ {
215
+ "epoch": 0.1342281879194631,
216
+ "grad_norm": 2.605672597885132,
217
+ "learning_rate": 4.81103928393834e-05,
218
+ "loss": 0.6903,
219
+ "step": 300
220
+ },
221
+ {
222
+ "epoch": 0.13870246085011187,
223
+ "grad_norm": 2.4527103900909424,
224
+ "learning_rate": 4.7861760318249625e-05,
225
+ "loss": 0.685,
226
+ "step": 310
227
+ },
228
+ {
229
+ "epoch": 0.14317673378076062,
230
+ "grad_norm": 1.669677734375,
231
+ "learning_rate": 4.7613127797115866e-05,
232
+ "loss": 0.6973,
233
+ "step": 320
234
+ },
235
+ {
236
+ "epoch": 0.1476510067114094,
237
+ "grad_norm": 3.61020565032959,
238
+ "learning_rate": 4.73644952759821e-05,
239
+ "loss": 0.6892,
240
+ "step": 330
241
+ },
242
+ {
243
+ "epoch": 0.15212527964205816,
244
+ "grad_norm": 2.7334518432617188,
245
+ "learning_rate": 4.7115862754848336e-05,
246
+ "loss": 0.6788,
247
+ "step": 340
248
+ },
249
+ {
250
+ "epoch": 0.15659955257270694,
251
+ "grad_norm": 3.9570696353912354,
252
+ "learning_rate": 4.686723023371457e-05,
253
+ "loss": 0.6979,
254
+ "step": 350
255
+ },
256
+ {
257
+ "epoch": 0.1610738255033557,
258
+ "grad_norm": 8.10511302947998,
259
+ "learning_rate": 4.6618597712580805e-05,
260
+ "loss": 0.6879,
261
+ "step": 360
262
+ },
263
+ {
264
+ "epoch": 0.16554809843400448,
265
+ "grad_norm": 3.7966678142547607,
266
+ "learning_rate": 4.6369965191447047e-05,
267
+ "loss": 0.6911,
268
+ "step": 370
269
+ },
270
+ {
271
+ "epoch": 0.17002237136465326,
272
+ "grad_norm": 5.181058883666992,
273
+ "learning_rate": 4.6121332670313274e-05,
274
+ "loss": 0.7149,
275
+ "step": 380
276
+ },
277
+ {
278
+ "epoch": 0.174496644295302,
279
+ "grad_norm": 8.394612312316895,
280
+ "learning_rate": 4.5872700149179516e-05,
281
+ "loss": 0.7491,
282
+ "step": 390
283
+ },
284
+ {
285
+ "epoch": 0.1789709172259508,
286
+ "grad_norm": 2.155719757080078,
287
+ "learning_rate": 4.562406762804575e-05,
288
+ "loss": 0.7565,
289
+ "step": 400
290
+ },
291
+ {
292
+ "epoch": 0.18344519015659955,
293
+ "grad_norm": 7.401564598083496,
294
+ "learning_rate": 4.5375435106911985e-05,
295
+ "loss": 0.7791,
296
+ "step": 410
297
+ },
298
+ {
299
+ "epoch": 0.18791946308724833,
300
+ "grad_norm": 4.933328628540039,
301
+ "learning_rate": 4.512680258577822e-05,
302
+ "loss": 0.7122,
303
+ "step": 420
304
+ },
305
+ {
306
+ "epoch": 0.19239373601789708,
307
+ "grad_norm": 4.831381320953369,
308
+ "learning_rate": 4.487817006464446e-05,
309
+ "loss": 0.6825,
310
+ "step": 430
311
+ },
312
+ {
313
+ "epoch": 0.19686800894854586,
314
+ "grad_norm": 3.8832848072052,
315
+ "learning_rate": 4.462953754351069e-05,
316
+ "loss": 0.7063,
317
+ "step": 440
318
+ },
319
+ {
320
+ "epoch": 0.2,
321
+ "eval_loss": 0.6715182662010193,
322
+ "eval_runtime": 1761.8072,
323
+ "eval_samples_per_second": 8.419,
324
+ "eval_steps_per_second": 1.052,
325
+ "step": 447
326
+ },
327
+ {
328
+ "epoch": 1.0013422818791946,
329
+ "grad_norm": 2.4441919326782227,
330
+ "learning_rate": 4.438090502237693e-05,
331
+ "loss": 0.6982,
332
+ "step": 450
333
+ },
334
+ {
335
+ "epoch": 1.0058165548098434,
336
+ "grad_norm": 4.019735813140869,
337
+ "learning_rate": 4.4132272501243166e-05,
338
+ "loss": 0.6895,
339
+ "step": 460
340
+ },
341
+ {
342
+ "epoch": 1.010290827740492,
343
+ "grad_norm": 3.720690965652466,
344
+ "learning_rate": 4.38836399801094e-05,
345
+ "loss": 0.6632,
346
+ "step": 470
347
+ },
348
+ {
349
+ "epoch": 1.014765100671141,
350
+ "grad_norm": 3.920600414276123,
351
+ "learning_rate": 4.3635007458975635e-05,
352
+ "loss": 0.6411,
353
+ "step": 480
354
+ },
355
+ {
356
+ "epoch": 1.0192393736017897,
357
+ "grad_norm": 2.9505422115325928,
358
+ "learning_rate": 4.338637493784187e-05,
359
+ "loss": 0.7189,
360
+ "step": 490
361
+ },
362
+ {
363
+ "epoch": 1.0237136465324386,
364
+ "grad_norm": 2.0582175254821777,
365
+ "learning_rate": 4.313774241670811e-05,
366
+ "loss": 0.6505,
367
+ "step": 500
368
+ },
369
+ {
370
+ "epoch": 1.0281879194630872,
371
+ "grad_norm": 4.039003849029541,
372
+ "learning_rate": 4.288910989557434e-05,
373
+ "loss": 0.5782,
374
+ "step": 510
375
+ },
376
+ {
377
+ "epoch": 1.032662192393736,
378
+ "grad_norm": 5.828691005706787,
379
+ "learning_rate": 4.264047737444058e-05,
380
+ "loss": 0.6767,
381
+ "step": 520
382
+ },
383
+ {
384
+ "epoch": 1.0371364653243849,
385
+ "grad_norm": 7.356812000274658,
386
+ "learning_rate": 4.2391844853306815e-05,
387
+ "loss": 0.6889,
388
+ "step": 530
389
+ },
390
+ {
391
+ "epoch": 1.0416107382550335,
392
+ "grad_norm": 2.9041857719421387,
393
+ "learning_rate": 4.214321233217305e-05,
394
+ "loss": 0.7148,
395
+ "step": 540
396
+ },
397
+ {
398
+ "epoch": 1.0460850111856823,
399
+ "grad_norm": 5.191349983215332,
400
+ "learning_rate": 4.1894579811039285e-05,
401
+ "loss": 0.6634,
402
+ "step": 550
403
+ },
404
+ {
405
+ "epoch": 1.0505592841163311,
406
+ "grad_norm": 3.5279178619384766,
407
+ "learning_rate": 4.1645947289905526e-05,
408
+ "loss": 0.7082,
409
+ "step": 560
410
+ },
411
+ {
412
+ "epoch": 1.0550335570469798,
413
+ "grad_norm": 3.045534372329712,
414
+ "learning_rate": 4.1397314768771754e-05,
415
+ "loss": 0.6653,
416
+ "step": 570
417
+ },
418
+ {
419
+ "epoch": 1.0595078299776286,
420
+ "grad_norm": 4.6366777420043945,
421
+ "learning_rate": 4.1148682247637995e-05,
422
+ "loss": 0.6732,
423
+ "step": 580
424
+ },
425
+ {
426
+ "epoch": 1.0639821029082774,
427
+ "grad_norm": 3.5409884452819824,
428
+ "learning_rate": 4.090004972650423e-05,
429
+ "loss": 0.6431,
430
+ "step": 590
431
+ },
432
+ {
433
+ "epoch": 1.0684563758389263,
434
+ "grad_norm": 1.765350103378296,
435
+ "learning_rate": 4.0651417205370465e-05,
436
+ "loss": 0.6744,
437
+ "step": 600
438
+ },
439
+ {
440
+ "epoch": 1.072930648769575,
441
+ "grad_norm": 1.904794454574585,
442
+ "learning_rate": 4.04027846842367e-05,
443
+ "loss": 0.7072,
444
+ "step": 610
445
+ },
446
+ {
447
+ "epoch": 1.0774049217002237,
448
+ "grad_norm": 3.329349994659424,
449
+ "learning_rate": 4.0154152163102934e-05,
450
+ "loss": 0.7258,
451
+ "step": 620
452
+ },
453
+ {
454
+ "epoch": 1.0818791946308726,
455
+ "grad_norm": 1.9617691040039062,
456
+ "learning_rate": 3.990551964196917e-05,
457
+ "loss": 0.7212,
458
+ "step": 630
459
+ },
460
+ {
461
+ "epoch": 1.0863534675615212,
462
+ "grad_norm": 2.310046911239624,
463
+ "learning_rate": 3.9656887120835404e-05,
464
+ "loss": 0.707,
465
+ "step": 640
466
+ },
467
+ {
468
+ "epoch": 1.09082774049217,
469
+ "grad_norm": 5.466283321380615,
470
+ "learning_rate": 3.9408254599701645e-05,
471
+ "loss": 0.6715,
472
+ "step": 650
473
+ },
474
+ {
475
+ "epoch": 1.0953020134228189,
476
+ "grad_norm": 2.3053205013275146,
477
+ "learning_rate": 3.915962207856787e-05,
478
+ "loss": 0.658,
479
+ "step": 660
480
+ },
481
+ {
482
+ "epoch": 1.0997762863534675,
483
+ "grad_norm": 5.147640228271484,
484
+ "learning_rate": 3.8910989557434114e-05,
485
+ "loss": 0.6494,
486
+ "step": 670
487
+ },
488
+ {
489
+ "epoch": 1.1042505592841163,
490
+ "grad_norm": 2.81063175201416,
491
+ "learning_rate": 3.866235703630035e-05,
492
+ "loss": 0.7073,
493
+ "step": 680
494
+ },
495
+ {
496
+ "epoch": 1.1087248322147651,
497
+ "grad_norm": 1.4132980108261108,
498
+ "learning_rate": 3.841372451516659e-05,
499
+ "loss": 0.6668,
500
+ "step": 690
501
+ },
502
+ {
503
+ "epoch": 1.113199105145414,
504
+ "grad_norm": 1.825891137123108,
505
+ "learning_rate": 3.816509199403282e-05,
506
+ "loss": 0.7262,
507
+ "step": 700
508
+ },
509
+ {
510
+ "epoch": 1.1176733780760626,
511
+ "grad_norm": 3.7974932193756104,
512
+ "learning_rate": 3.791645947289906e-05,
513
+ "loss": 0.6731,
514
+ "step": 710
515
+ },
516
+ {
517
+ "epoch": 1.1221476510067114,
518
+ "grad_norm": 3.443728446960449,
519
+ "learning_rate": 3.7667826951765295e-05,
520
+ "loss": 0.6229,
521
+ "step": 720
522
+ },
523
+ {
524
+ "epoch": 1.1266219239373603,
525
+ "grad_norm": 1.7325217723846436,
526
+ "learning_rate": 3.741919443063153e-05,
527
+ "loss": 0.7448,
528
+ "step": 730
529
+ },
530
+ {
531
+ "epoch": 1.1310961968680089,
532
+ "grad_norm": 2.9110777378082275,
533
+ "learning_rate": 3.7170561909497764e-05,
534
+ "loss": 0.655,
535
+ "step": 740
536
+ },
537
+ {
538
+ "epoch": 1.1355704697986577,
539
+ "grad_norm": 2.406698226928711,
540
+ "learning_rate": 3.6921929388364e-05,
541
+ "loss": 0.6215,
542
+ "step": 750
543
+ },
544
+ {
545
+ "epoch": 1.1400447427293066,
546
+ "grad_norm": 3.4812052249908447,
547
+ "learning_rate": 3.6673296867230234e-05,
548
+ "loss": 0.563,
549
+ "step": 760
550
+ },
551
+ {
552
+ "epoch": 1.1445190156599552,
553
+ "grad_norm": 3.899214029312134,
554
+ "learning_rate": 3.642466434609647e-05,
555
+ "loss": 0.6997,
556
+ "step": 770
557
+ },
558
+ {
559
+ "epoch": 1.148993288590604,
560
+ "grad_norm": 3.2445719242095947,
561
+ "learning_rate": 3.617603182496271e-05,
562
+ "loss": 0.7645,
563
+ "step": 780
564
+ },
565
+ {
566
+ "epoch": 1.1534675615212528,
567
+ "grad_norm": 3.465245485305786,
568
+ "learning_rate": 3.592739930382894e-05,
569
+ "loss": 0.6791,
570
+ "step": 790
571
+ },
572
+ {
573
+ "epoch": 1.1579418344519015,
574
+ "grad_norm": 2.491565465927124,
575
+ "learning_rate": 3.567876678269518e-05,
576
+ "loss": 0.683,
577
+ "step": 800
578
+ },
579
+ {
580
+ "epoch": 1.1624161073825503,
581
+ "grad_norm": 5.133494853973389,
582
+ "learning_rate": 3.5430134261561414e-05,
583
+ "loss": 0.6078,
584
+ "step": 810
585
+ },
586
+ {
587
+ "epoch": 1.1668903803131991,
588
+ "grad_norm": 2.245474338531494,
589
+ "learning_rate": 3.518150174042765e-05,
590
+ "loss": 0.5367,
591
+ "step": 820
592
+ },
593
+ {
594
+ "epoch": 1.171364653243848,
595
+ "grad_norm": 4.2087082862854,
596
+ "learning_rate": 3.493286921929388e-05,
597
+ "loss": 0.6008,
598
+ "step": 830
599
+ },
600
+ {
601
+ "epoch": 1.1758389261744966,
602
+ "grad_norm": 4.76090145111084,
603
+ "learning_rate": 3.4684236698160125e-05,
604
+ "loss": 0.7077,
605
+ "step": 840
606
+ },
607
+ {
608
+ "epoch": 1.1803131991051454,
609
+ "grad_norm": 2.1628592014312744,
610
+ "learning_rate": 3.443560417702636e-05,
611
+ "loss": 0.5769,
612
+ "step": 850
613
+ },
614
+ {
615
+ "epoch": 1.1847874720357943,
616
+ "grad_norm": 2.682377815246582,
617
+ "learning_rate": 3.4186971655892594e-05,
618
+ "loss": 0.6384,
619
+ "step": 860
620
+ },
621
+ {
622
+ "epoch": 1.1892617449664429,
623
+ "grad_norm": 6.282998561859131,
624
+ "learning_rate": 3.393833913475883e-05,
625
+ "loss": 0.6722,
626
+ "step": 870
627
+ },
628
+ {
629
+ "epoch": 1.1937360178970917,
630
+ "grad_norm": 9.779953956604004,
631
+ "learning_rate": 3.3689706613625063e-05,
632
+ "loss": 0.791,
633
+ "step": 880
634
+ },
635
+ {
636
+ "epoch": 1.1982102908277406,
637
+ "grad_norm": 1.8788007497787476,
638
+ "learning_rate": 3.34410740924913e-05,
639
+ "loss": 0.6721,
640
+ "step": 890
641
+ },
642
+ {
643
+ "epoch": 1.2,
644
+ "eval_loss": 0.6246910095214844,
645
+ "eval_runtime": 1487.4015,
646
+ "eval_samples_per_second": 9.972,
647
+ "eval_steps_per_second": 1.246,
648
+ "step": 894
649
+ },
650
+ {
651
+ "epoch": 2.002684563758389,
652
+ "grad_norm": 1.6846109628677368,
653
+ "learning_rate": 3.319244157135753e-05,
654
+ "loss": 0.6539,
655
+ "step": 900
656
+ },
657
+ {
658
+ "epoch": 2.007158836689038,
659
+ "grad_norm": 3.035057544708252,
660
+ "learning_rate": 3.2943809050223774e-05,
661
+ "loss": 0.5134,
662
+ "step": 910
663
+ },
664
+ {
665
+ "epoch": 2.011633109619687,
666
+ "grad_norm": 2.8990113735198975,
667
+ "learning_rate": 3.269517652909e-05,
668
+ "loss": 0.6534,
669
+ "step": 920
670
+ },
671
+ {
672
+ "epoch": 2.0161073825503357,
673
+ "grad_norm": 3.068324565887451,
674
+ "learning_rate": 3.2446544007956244e-05,
675
+ "loss": 0.5266,
676
+ "step": 930
677
+ },
678
+ {
679
+ "epoch": 2.020581655480984,
680
+ "grad_norm": 2.821528673171997,
681
+ "learning_rate": 3.219791148682248e-05,
682
+ "loss": 0.6418,
683
+ "step": 940
684
+ },
685
+ {
686
+ "epoch": 2.025055928411633,
687
+ "grad_norm": 3.9796924591064453,
688
+ "learning_rate": 3.194927896568871e-05,
689
+ "loss": 0.7007,
690
+ "step": 950
691
+ },
692
+ {
693
+ "epoch": 2.029530201342282,
694
+ "grad_norm": 2.3926808834075928,
695
+ "learning_rate": 3.170064644455495e-05,
696
+ "loss": 0.6197,
697
+ "step": 960
698
+ },
699
+ {
700
+ "epoch": 2.0340044742729306,
701
+ "grad_norm": 3.085684299468994,
702
+ "learning_rate": 3.145201392342119e-05,
703
+ "loss": 0.6777,
704
+ "step": 970
705
+ },
706
+ {
707
+ "epoch": 2.0384787472035795,
708
+ "grad_norm": 5.555381774902344,
709
+ "learning_rate": 3.120338140228742e-05,
710
+ "loss": 0.6501,
711
+ "step": 980
712
+ },
713
+ {
714
+ "epoch": 2.0429530201342283,
715
+ "grad_norm": 4.209506034851074,
716
+ "learning_rate": 3.095474888115366e-05,
717
+ "loss": 0.5444,
718
+ "step": 990
719
+ },
720
+ {
721
+ "epoch": 2.047427293064877,
722
+ "grad_norm": 5.272610187530518,
723
+ "learning_rate": 3.070611636001989e-05,
724
+ "loss": 0.5932,
725
+ "step": 1000
726
+ },
727
+ {
728
+ "epoch": 2.0519015659955255,
729
+ "grad_norm": 6.082980632781982,
730
+ "learning_rate": 3.0457483838886125e-05,
731
+ "loss": 0.5373,
732
+ "step": 1010
733
+ },
734
+ {
735
+ "epoch": 2.0563758389261744,
736
+ "grad_norm": 8.720032691955566,
737
+ "learning_rate": 3.0208851317752363e-05,
738
+ "loss": 0.6193,
739
+ "step": 1020
740
+ },
741
+ {
742
+ "epoch": 2.060850111856823,
743
+ "grad_norm": 5.651848316192627,
744
+ "learning_rate": 2.99602187966186e-05,
745
+ "loss": 0.784,
746
+ "step": 1030
747
+ },
748
+ {
749
+ "epoch": 2.065324384787472,
750
+ "grad_norm": 3.823605537414551,
751
+ "learning_rate": 2.971158627548484e-05,
752
+ "loss": 0.6691,
753
+ "step": 1040
754
+ },
755
+ {
756
+ "epoch": 2.069798657718121,
757
+ "grad_norm": 8.381941795349121,
758
+ "learning_rate": 2.946295375435107e-05,
759
+ "loss": 0.8144,
760
+ "step": 1050
761
+ },
762
+ {
763
+ "epoch": 2.0742729306487697,
764
+ "grad_norm": 2.2700552940368652,
765
+ "learning_rate": 2.9214321233217308e-05,
766
+ "loss": 0.6561,
767
+ "step": 1060
768
+ },
769
+ {
770
+ "epoch": 2.0787472035794186,
771
+ "grad_norm": 2.6026828289031982,
772
+ "learning_rate": 2.8965688712083543e-05,
773
+ "loss": 0.5758,
774
+ "step": 1070
775
+ },
776
+ {
777
+ "epoch": 2.083221476510067,
778
+ "grad_norm": 2.6692521572113037,
779
+ "learning_rate": 2.8717056190949778e-05,
780
+ "loss": 0.5744,
781
+ "step": 1080
782
+ },
783
+ {
784
+ "epoch": 2.087695749440716,
785
+ "grad_norm": 2.2459254264831543,
786
+ "learning_rate": 2.8468423669816012e-05,
787
+ "loss": 0.5685,
788
+ "step": 1090
789
+ },
790
+ {
791
+ "epoch": 2.0921700223713646,
792
+ "grad_norm": 5.383577346801758,
793
+ "learning_rate": 2.821979114868225e-05,
794
+ "loss": 0.6373,
795
+ "step": 1100
796
+ },
797
+ {
798
+ "epoch": 2.0966442953020135,
799
+ "grad_norm": 8.249171257019043,
800
+ "learning_rate": 2.797115862754848e-05,
801
+ "loss": 0.6714,
802
+ "step": 1110
803
+ },
804
+ {
805
+ "epoch": 2.1011185682326623,
806
+ "grad_norm": 2.999361515045166,
807
+ "learning_rate": 2.772252610641472e-05,
808
+ "loss": 0.5913,
809
+ "step": 1120
810
+ },
811
+ {
812
+ "epoch": 2.105592841163311,
813
+ "grad_norm": 9.099119186401367,
814
+ "learning_rate": 2.7473893585280958e-05,
815
+ "loss": 0.5828,
816
+ "step": 1130
817
+ },
818
+ {
819
+ "epoch": 2.1100671140939595,
820
+ "grad_norm": 3.917780637741089,
821
+ "learning_rate": 2.722526106414719e-05,
822
+ "loss": 0.621,
823
+ "step": 1140
824
+ },
825
+ {
826
+ "epoch": 2.1145413870246084,
827
+ "grad_norm": 3.7017178535461426,
828
+ "learning_rate": 2.6976628543013427e-05,
829
+ "loss": 0.6114,
830
+ "step": 1150
831
+ },
832
+ {
833
+ "epoch": 2.119015659955257,
834
+ "grad_norm": 3.644044876098633,
835
+ "learning_rate": 2.6727996021879665e-05,
836
+ "loss": 0.5885,
837
+ "step": 1160
838
+ },
839
+ {
840
+ "epoch": 2.123489932885906,
841
+ "grad_norm": 5.438238143920898,
842
+ "learning_rate": 2.6479363500745897e-05,
843
+ "loss": 0.5192,
844
+ "step": 1170
845
+ },
846
+ {
847
+ "epoch": 2.127964205816555,
848
+ "grad_norm": 3.882387638092041,
849
+ "learning_rate": 2.6230730979612135e-05,
850
+ "loss": 0.5705,
851
+ "step": 1180
852
+ },
853
+ {
854
+ "epoch": 2.1324384787472037,
855
+ "grad_norm": 5.98944091796875,
856
+ "learning_rate": 2.598209845847837e-05,
857
+ "loss": 0.6853,
858
+ "step": 1190
859
+ },
860
+ {
861
+ "epoch": 2.1369127516778526,
862
+ "grad_norm": 4.663422107696533,
863
+ "learning_rate": 2.5733465937344607e-05,
864
+ "loss": 0.5025,
865
+ "step": 1200
866
+ },
867
+ {
868
+ "epoch": 2.141387024608501,
869
+ "grad_norm": 6.064481258392334,
870
+ "learning_rate": 2.548483341621084e-05,
871
+ "loss": 0.6278,
872
+ "step": 1210
873
+ },
874
+ {
875
+ "epoch": 2.14586129753915,
876
+ "grad_norm": 2.134000301361084,
877
+ "learning_rate": 2.5236200895077077e-05,
878
+ "loss": 0.5154,
879
+ "step": 1220
880
+ },
881
+ {
882
+ "epoch": 2.1503355704697986,
883
+ "grad_norm": 4.727463245391846,
884
+ "learning_rate": 2.498756837394331e-05,
885
+ "loss": 0.6088,
886
+ "step": 1230
887
+ },
888
+ {
889
+ "epoch": 2.1548098434004475,
890
+ "grad_norm": 11.16874885559082,
891
+ "learning_rate": 2.473893585280955e-05,
892
+ "loss": 0.5871,
893
+ "step": 1240
894
+ },
895
+ {
896
+ "epoch": 2.1592841163310963,
897
+ "grad_norm": 10.524863243103027,
898
+ "learning_rate": 2.4490303331675784e-05,
899
+ "loss": 0.5797,
900
+ "step": 1250
901
+ },
902
+ {
903
+ "epoch": 2.163758389261745,
904
+ "grad_norm": 3.4899938106536865,
905
+ "learning_rate": 2.424167081054202e-05,
906
+ "loss": 0.525,
907
+ "step": 1260
908
+ },
909
+ {
910
+ "epoch": 2.168232662192394,
911
+ "grad_norm": 3.9333999156951904,
912
+ "learning_rate": 2.3993038289408257e-05,
913
+ "loss": 0.6021,
914
+ "step": 1270
915
+ },
916
+ {
917
+ "epoch": 2.1727069351230424,
918
+ "grad_norm": 8.3557710647583,
919
+ "learning_rate": 2.3744405768274492e-05,
920
+ "loss": 0.5118,
921
+ "step": 1280
922
+ },
923
+ {
924
+ "epoch": 2.177181208053691,
925
+ "grad_norm": 6.4609808921813965,
926
+ "learning_rate": 2.3495773247140727e-05,
927
+ "loss": 0.5269,
928
+ "step": 1290
929
+ },
930
+ {
931
+ "epoch": 2.18165548098434,
932
+ "grad_norm": 6.468663215637207,
933
+ "learning_rate": 2.3247140726006965e-05,
934
+ "loss": 0.6008,
935
+ "step": 1300
936
+ },
937
+ {
938
+ "epoch": 2.186129753914989,
939
+ "grad_norm": 7.775058269500732,
940
+ "learning_rate": 2.29985082048732e-05,
941
+ "loss": 0.5065,
942
+ "step": 1310
943
+ },
944
+ {
945
+ "epoch": 2.1906040268456377,
946
+ "grad_norm": 5.685559272766113,
947
+ "learning_rate": 2.2749875683739434e-05,
948
+ "loss": 0.6822,
949
+ "step": 1320
950
+ },
951
+ {
952
+ "epoch": 2.1950782997762865,
953
+ "grad_norm": 3.1594507694244385,
954
+ "learning_rate": 2.250124316260567e-05,
955
+ "loss": 0.4971,
956
+ "step": 1330
957
+ },
958
+ {
959
+ "epoch": 2.199552572706935,
960
+ "grad_norm": 4.630302429199219,
961
+ "learning_rate": 2.2252610641471903e-05,
962
+ "loss": 0.4569,
963
+ "step": 1340
964
+ },
965
+ {
966
+ "epoch": 2.2,
967
+ "eval_loss": 0.6014084219932556,
968
+ "eval_runtime": 1492.9737,
969
+ "eval_samples_per_second": 9.935,
970
+ "eval_steps_per_second": 1.242,
971
+ "step": 1341
972
+ },
973
+ {
974
+ "epoch": 3.004026845637584,
975
+ "grad_norm": 5.828940391540527,
976
+ "learning_rate": 2.200397812033814e-05,
977
+ "loss": 0.4597,
978
+ "step": 1350
979
+ },
980
+ {
981
+ "epoch": 3.008501118568233,
982
+ "grad_norm": 7.898725509643555,
983
+ "learning_rate": 2.1755345599204376e-05,
984
+ "loss": 0.5478,
985
+ "step": 1360
986
+ },
987
+ {
988
+ "epoch": 3.0129753914988813,
989
+ "grad_norm": 5.81334924697876,
990
+ "learning_rate": 2.150671307807061e-05,
991
+ "loss": 0.4605,
992
+ "step": 1370
993
+ },
994
+ {
995
+ "epoch": 3.01744966442953,
996
+ "grad_norm": 8.778861045837402,
997
+ "learning_rate": 2.125808055693685e-05,
998
+ "loss": 0.55,
999
+ "step": 1380
1000
+ },
1001
+ {
1002
+ "epoch": 3.021923937360179,
1003
+ "grad_norm": 5.120452404022217,
1004
+ "learning_rate": 2.1009448035803084e-05,
1005
+ "loss": 0.4859,
1006
+ "step": 1390
1007
+ },
1008
+ {
1009
+ "epoch": 3.026398210290828,
1010
+ "grad_norm": 5.020923614501953,
1011
+ "learning_rate": 2.076081551466932e-05,
1012
+ "loss": 0.6555,
1013
+ "step": 1400
1014
+ },
1015
+ {
1016
+ "epoch": 3.0308724832214766,
1017
+ "grad_norm": 3.6531450748443604,
1018
+ "learning_rate": 2.0512182993535556e-05,
1019
+ "loss": 0.7016,
1020
+ "step": 1410
1021
+ },
1022
+ {
1023
+ "epoch": 3.0353467561521255,
1024
+ "grad_norm": 6.611879825592041,
1025
+ "learning_rate": 2.026355047240179e-05,
1026
+ "loss": 0.5688,
1027
+ "step": 1420
1028
+ },
1029
+ {
1030
+ "epoch": 3.039821029082774,
1031
+ "grad_norm": 4.798068523406982,
1032
+ "learning_rate": 2.001491795126803e-05,
1033
+ "loss": 0.5278,
1034
+ "step": 1430
1035
+ },
1036
+ {
1037
+ "epoch": 3.0442953020134227,
1038
+ "grad_norm": 7.155426502227783,
1039
+ "learning_rate": 1.9766285430134264e-05,
1040
+ "loss": 0.6829,
1041
+ "step": 1440
1042
+ },
1043
+ {
1044
+ "epoch": 3.0487695749440715,
1045
+ "grad_norm": 3.3493528366088867,
1046
+ "learning_rate": 1.95176529090005e-05,
1047
+ "loss": 0.4513,
1048
+ "step": 1450
1049
+ },
1050
+ {
1051
+ "epoch": 3.0532438478747204,
1052
+ "grad_norm": 4.92922830581665,
1053
+ "learning_rate": 1.9269020387866733e-05,
1054
+ "loss": 0.5048,
1055
+ "step": 1460
1056
+ },
1057
+ {
1058
+ "epoch": 3.057718120805369,
1059
+ "grad_norm": 2.6366868019104004,
1060
+ "learning_rate": 1.9020387866732968e-05,
1061
+ "loss": 0.5779,
1062
+ "step": 1470
1063
+ },
1064
+ {
1065
+ "epoch": 3.062192393736018,
1066
+ "grad_norm": 4.534608364105225,
1067
+ "learning_rate": 1.8771755345599203e-05,
1068
+ "loss": 0.5773,
1069
+ "step": 1480
1070
+ },
1071
+ {
1072
+ "epoch": 3.066666666666667,
1073
+ "grad_norm": 3.9741370677948,
1074
+ "learning_rate": 1.852312282446544e-05,
1075
+ "loss": 0.4721,
1076
+ "step": 1490
1077
+ },
1078
+ {
1079
+ "epoch": 3.0711409395973153,
1080
+ "grad_norm": 6.1377949714660645,
1081
+ "learning_rate": 1.8274490303331675e-05,
1082
+ "loss": 0.4262,
1083
+ "step": 1500
1084
+ },
1085
+ {
1086
+ "epoch": 3.075615212527964,
1087
+ "grad_norm": 3.841529130935669,
1088
+ "learning_rate": 1.8025857782197914e-05,
1089
+ "loss": 0.5487,
1090
+ "step": 1510
1091
+ },
1092
+ {
1093
+ "epoch": 3.080089485458613,
1094
+ "grad_norm": 3.916842460632324,
1095
+ "learning_rate": 1.7777225261064148e-05,
1096
+ "loss": 0.3911,
1097
+ "step": 1520
1098
+ },
1099
+ {
1100
+ "epoch": 3.084563758389262,
1101
+ "grad_norm": 7.478826999664307,
1102
+ "learning_rate": 1.7528592739930383e-05,
1103
+ "loss": 0.6058,
1104
+ "step": 1530
1105
+ },
1106
+ {
1107
+ "epoch": 3.0890380313199106,
1108
+ "grad_norm": 6.842457294464111,
1109
+ "learning_rate": 1.727996021879662e-05,
1110
+ "loss": 0.4515,
1111
+ "step": 1540
1112
+ },
1113
+ {
1114
+ "epoch": 3.0935123042505595,
1115
+ "grad_norm": 3.2963719367980957,
1116
+ "learning_rate": 1.7031327697662856e-05,
1117
+ "loss": 0.5026,
1118
+ "step": 1550
1119
+ },
1120
+ {
1121
+ "epoch": 3.097986577181208,
1122
+ "grad_norm": 7.006161212921143,
1123
+ "learning_rate": 1.678269517652909e-05,
1124
+ "loss": 0.3824,
1125
+ "step": 1560
1126
+ },
1127
+ {
1128
+ "epoch": 3.1024608501118567,
1129
+ "grad_norm": 7.763972282409668,
1130
+ "learning_rate": 1.653406265539533e-05,
1131
+ "loss": 0.508,
1132
+ "step": 1570
1133
+ },
1134
+ {
1135
+ "epoch": 3.1069351230425055,
1136
+ "grad_norm": 5.557806968688965,
1137
+ "learning_rate": 1.6285430134261563e-05,
1138
+ "loss": 0.4799,
1139
+ "step": 1580
1140
+ },
1141
+ {
1142
+ "epoch": 3.1114093959731544,
1143
+ "grad_norm": 5.409721851348877,
1144
+ "learning_rate": 1.6036797613127798e-05,
1145
+ "loss": 0.4949,
1146
+ "step": 1590
1147
+ },
1148
+ {
1149
+ "epoch": 3.115883668903803,
1150
+ "grad_norm": 3.6915335655212402,
1151
+ "learning_rate": 1.5788165091994033e-05,
1152
+ "loss": 0.3343,
1153
+ "step": 1600
1154
+ },
1155
+ {
1156
+ "epoch": 3.120357941834452,
1157
+ "grad_norm": 9.01720142364502,
1158
+ "learning_rate": 1.5539532570860267e-05,
1159
+ "loss": 0.6496,
1160
+ "step": 1610
1161
+ },
1162
+ {
1163
+ "epoch": 3.124832214765101,
1164
+ "grad_norm": 6.928211212158203,
1165
+ "learning_rate": 1.5290900049726505e-05,
1166
+ "loss": 0.6609,
1167
+ "step": 1620
1168
+ },
1169
+ {
1170
+ "epoch": 3.1293064876957493,
1171
+ "grad_norm": 4.305416107177734,
1172
+ "learning_rate": 1.504226752859274e-05,
1173
+ "loss": 0.529,
1174
+ "step": 1630
1175
+ },
1176
+ {
1177
+ "epoch": 3.133780760626398,
1178
+ "grad_norm": 7.057407379150391,
1179
+ "learning_rate": 1.4793635007458975e-05,
1180
+ "loss": 0.4313,
1181
+ "step": 1640
1182
+ },
1183
+ {
1184
+ "epoch": 3.138255033557047,
1185
+ "grad_norm": 3.027143955230713,
1186
+ "learning_rate": 1.4545002486325213e-05,
1187
+ "loss": 0.5001,
1188
+ "step": 1650
1189
+ },
1190
+ {
1191
+ "epoch": 3.1427293064876958,
1192
+ "grad_norm": 6.385172367095947,
1193
+ "learning_rate": 1.4296369965191447e-05,
1194
+ "loss": 0.5285,
1195
+ "step": 1660
1196
+ },
1197
+ {
1198
+ "epoch": 3.1472035794183446,
1199
+ "grad_norm": 3.7403576374053955,
1200
+ "learning_rate": 1.4047737444057686e-05,
1201
+ "loss": 0.4909,
1202
+ "step": 1670
1203
+ },
1204
+ {
1205
+ "epoch": 3.1516778523489934,
1206
+ "grad_norm": 3.044612407684326,
1207
+ "learning_rate": 1.379910492292392e-05,
1208
+ "loss": 0.4693,
1209
+ "step": 1680
1210
+ },
1211
+ {
1212
+ "epoch": 3.1561521252796423,
1213
+ "grad_norm": 2.8008298873901367,
1214
+ "learning_rate": 1.3550472401790153e-05,
1215
+ "loss": 0.4481,
1216
+ "step": 1690
1217
+ },
1218
+ {
1219
+ "epoch": 3.1606263982102907,
1220
+ "grad_norm": 8.774086952209473,
1221
+ "learning_rate": 1.3301839880656391e-05,
1222
+ "loss": 0.4807,
1223
+ "step": 1700
1224
+ },
1225
+ {
1226
+ "epoch": 3.1651006711409395,
1227
+ "grad_norm": 12.503308296203613,
1228
+ "learning_rate": 1.3053207359522626e-05,
1229
+ "loss": 0.537,
1230
+ "step": 1710
1231
+ },
1232
+ {
1233
+ "epoch": 3.1695749440715884,
1234
+ "grad_norm": 2.6798453330993652,
1235
+ "learning_rate": 1.280457483838886e-05,
1236
+ "loss": 0.5359,
1237
+ "step": 1720
1238
+ },
1239
+ {
1240
+ "epoch": 3.174049217002237,
1241
+ "grad_norm": 4.319638252258301,
1242
+ "learning_rate": 1.2555942317255099e-05,
1243
+ "loss": 0.4426,
1244
+ "step": 1730
1245
+ },
1246
+ {
1247
+ "epoch": 3.178523489932886,
1248
+ "grad_norm": 6.9289326667785645,
1249
+ "learning_rate": 1.2307309796121334e-05,
1250
+ "loss": 0.3618,
1251
+ "step": 1740
1252
+ },
1253
+ {
1254
+ "epoch": 3.182997762863535,
1255
+ "grad_norm": 6.457849025726318,
1256
+ "learning_rate": 1.2058677274987568e-05,
1257
+ "loss": 0.3464,
1258
+ "step": 1750
1259
+ },
1260
+ {
1261
+ "epoch": 3.1874720357941833,
1262
+ "grad_norm": 12.982036590576172,
1263
+ "learning_rate": 1.1810044753853805e-05,
1264
+ "loss": 0.3827,
1265
+ "step": 1760
1266
+ },
1267
+ {
1268
+ "epoch": 3.191946308724832,
1269
+ "grad_norm": 8.971426963806152,
1270
+ "learning_rate": 1.156141223272004e-05,
1271
+ "loss": 0.3881,
1272
+ "step": 1770
1273
+ },
1274
+ {
1275
+ "epoch": 3.196420581655481,
1276
+ "grad_norm": 6.063282012939453,
1277
+ "learning_rate": 1.1312779711586276e-05,
1278
+ "loss": 0.3716,
1279
+ "step": 1780
1280
+ },
1281
+ {
1282
+ "epoch": 3.2,
1283
+ "eval_loss": 0.5118685364723206,
1284
+ "eval_runtime": 1494.7331,
1285
+ "eval_samples_per_second": 9.923,
1286
+ "eval_steps_per_second": 1.24,
1287
+ "step": 1788
1288
+ },
1289
+ {
1290
+ "epoch": 4.00089485458613,
1291
+ "grad_norm": 6.091933250427246,
1292
+ "learning_rate": 1.1064147190452512e-05,
1293
+ "loss": 0.3984,
1294
+ "step": 1790
1295
+ },
1296
+ {
1297
+ "epoch": 4.005369127516778,
1298
+ "grad_norm": 6.938051700592041,
1299
+ "learning_rate": 1.0815514669318748e-05,
1300
+ "loss": 0.4258,
1301
+ "step": 1800
1302
+ },
1303
+ {
1304
+ "epoch": 4.009843400447427,
1305
+ "grad_norm": 4.8558244705200195,
1306
+ "learning_rate": 1.0566882148184983e-05,
1307
+ "loss": 0.5116,
1308
+ "step": 1810
1309
+ },
1310
+ {
1311
+ "epoch": 4.014317673378076,
1312
+ "grad_norm": 10.951703071594238,
1313
+ "learning_rate": 1.0318249627051218e-05,
1314
+ "loss": 0.3894,
1315
+ "step": 1820
1316
+ },
1317
+ {
1318
+ "epoch": 4.018791946308725,
1319
+ "grad_norm": 10.405500411987305,
1320
+ "learning_rate": 1.0069617105917454e-05,
1321
+ "loss": 0.5517,
1322
+ "step": 1830
1323
+ },
1324
+ {
1325
+ "epoch": 4.023266219239374,
1326
+ "grad_norm": 6.398135662078857,
1327
+ "learning_rate": 9.82098458478369e-06,
1328
+ "loss": 0.4327,
1329
+ "step": 1840
1330
+ },
1331
+ {
1332
+ "epoch": 4.027740492170023,
1333
+ "grad_norm": 4.099758625030518,
1334
+ "learning_rate": 9.572352063649925e-06,
1335
+ "loss": 0.4114,
1336
+ "step": 1850
1337
+ },
1338
+ {
1339
+ "epoch": 4.0322147651006714,
1340
+ "grad_norm": 6.407171249389648,
1341
+ "learning_rate": 9.323719542516162e-06,
1342
+ "loss": 0.4069,
1343
+ "step": 1860
1344
+ },
1345
+ {
1346
+ "epoch": 4.03668903803132,
1347
+ "grad_norm": 4.555864334106445,
1348
+ "learning_rate": 9.075087021382398e-06,
1349
+ "loss": 0.3945,
1350
+ "step": 1870
1351
+ },
1352
+ {
1353
+ "epoch": 4.041163310961968,
1354
+ "grad_norm": 10.738176345825195,
1355
+ "learning_rate": 8.826454500248633e-06,
1356
+ "loss": 0.4497,
1357
+ "step": 1880
1358
+ },
1359
+ {
1360
+ "epoch": 4.045637583892617,
1361
+ "grad_norm": 6.803495407104492,
1362
+ "learning_rate": 8.577821979114867e-06,
1363
+ "loss": 0.4051,
1364
+ "step": 1890
1365
+ },
1366
+ {
1367
+ "epoch": 4.050111856823266,
1368
+ "grad_norm": 6.758240222930908,
1369
+ "learning_rate": 8.329189457981104e-06,
1370
+ "loss": 0.3804,
1371
+ "step": 1900
1372
+ },
1373
+ {
1374
+ "epoch": 4.054586129753915,
1375
+ "grad_norm": 4.895435810089111,
1376
+ "learning_rate": 8.08055693684734e-06,
1377
+ "loss": 0.3941,
1378
+ "step": 1910
1379
+ },
1380
+ {
1381
+ "epoch": 4.059060402684564,
1382
+ "grad_norm": 6.476896286010742,
1383
+ "learning_rate": 7.831924415713577e-06,
1384
+ "loss": 0.3162,
1385
+ "step": 1920
1386
+ },
1387
+ {
1388
+ "epoch": 4.063534675615212,
1389
+ "grad_norm": 29.98179817199707,
1390
+ "learning_rate": 7.583291894579811e-06,
1391
+ "loss": 0.3908,
1392
+ "step": 1930
1393
+ },
1394
+ {
1395
+ "epoch": 4.068008948545861,
1396
+ "grad_norm": 10.254730224609375,
1397
+ "learning_rate": 7.334659373446047e-06,
1398
+ "loss": 0.3543,
1399
+ "step": 1940
1400
+ },
1401
+ {
1402
+ "epoch": 4.07248322147651,
1403
+ "grad_norm": 6.417944431304932,
1404
+ "learning_rate": 7.086026852312283e-06,
1405
+ "loss": 0.4223,
1406
+ "step": 1950
1407
+ },
1408
+ {
1409
+ "epoch": 4.076957494407159,
1410
+ "grad_norm": 5.318185806274414,
1411
+ "learning_rate": 6.837394331178519e-06,
1412
+ "loss": 0.3001,
1413
+ "step": 1960
1414
+ },
1415
+ {
1416
+ "epoch": 4.081431767337808,
1417
+ "grad_norm": 9.698352813720703,
1418
+ "learning_rate": 6.5887618100447535e-06,
1419
+ "loss": 0.4493,
1420
+ "step": 1970
1421
+ },
1422
+ {
1423
+ "epoch": 4.085906040268457,
1424
+ "grad_norm": 10.736822128295898,
1425
+ "learning_rate": 6.34012928891099e-06,
1426
+ "loss": 0.3993,
1427
+ "step": 1980
1428
+ },
1429
+ {
1430
+ "epoch": 4.0903803131991054,
1431
+ "grad_norm": 8.830057144165039,
1432
+ "learning_rate": 6.0914967677772254e-06,
1433
+ "loss": 0.4364,
1434
+ "step": 1990
1435
+ },
1436
+ {
1437
+ "epoch": 4.094854586129754,
1438
+ "grad_norm": 3.8576180934906006,
1439
+ "learning_rate": 5.842864246643461e-06,
1440
+ "loss": 0.3951,
1441
+ "step": 2000
1442
+ },
1443
+ {
1444
+ "epoch": 4.099328859060403,
1445
+ "grad_norm": 5.700314998626709,
1446
+ "learning_rate": 5.594231725509697e-06,
1447
+ "loss": 0.242,
1448
+ "step": 2010
1449
+ },
1450
+ {
1451
+ "epoch": 4.103803131991051,
1452
+ "grad_norm": 9.951739311218262,
1453
+ "learning_rate": 5.345599204375933e-06,
1454
+ "loss": 0.3352,
1455
+ "step": 2020
1456
+ },
1457
+ {
1458
+ "epoch": 4.1082774049217,
1459
+ "grad_norm": 6.291647434234619,
1460
+ "learning_rate": 5.0969666832421684e-06,
1461
+ "loss": 0.3871,
1462
+ "step": 2030
1463
+ },
1464
+ {
1465
+ "epoch": 4.112751677852349,
1466
+ "grad_norm": 10.89775562286377,
1467
+ "learning_rate": 4.848334162108404e-06,
1468
+ "loss": 0.3503,
1469
+ "step": 2040
1470
+ },
1471
+ {
1472
+ "epoch": 4.117225950782998,
1473
+ "grad_norm": 9.332531929016113,
1474
+ "learning_rate": 4.59970164097464e-06,
1475
+ "loss": 0.4414,
1476
+ "step": 2050
1477
+ },
1478
+ {
1479
+ "epoch": 4.121700223713646,
1480
+ "grad_norm": 5.656005859375,
1481
+ "learning_rate": 4.351069119840875e-06,
1482
+ "loss": 0.2954,
1483
+ "step": 2060
1484
+ },
1485
+ {
1486
+ "epoch": 4.126174496644295,
1487
+ "grad_norm": 9.542107582092285,
1488
+ "learning_rate": 4.102436598707111e-06,
1489
+ "loss": 0.3443,
1490
+ "step": 2070
1491
+ },
1492
+ {
1493
+ "epoch": 4.130648769574944,
1494
+ "grad_norm": 6.114157676696777,
1495
+ "learning_rate": 3.853804077573347e-06,
1496
+ "loss": 0.4237,
1497
+ "step": 2080
1498
+ },
1499
+ {
1500
+ "epoch": 4.135123042505593,
1501
+ "grad_norm": 15.799965858459473,
1502
+ "learning_rate": 3.605171556439582e-06,
1503
+ "loss": 0.3741,
1504
+ "step": 2090
1505
+ },
1506
+ {
1507
+ "epoch": 4.139597315436242,
1508
+ "grad_norm": 7.750021457672119,
1509
+ "learning_rate": 3.356539035305818e-06,
1510
+ "loss": 0.2432,
1511
+ "step": 2100
1512
+ },
1513
+ {
1514
+ "epoch": 4.144071588366891,
1515
+ "grad_norm": 9.3380708694458,
1516
+ "learning_rate": 3.107906514172054e-06,
1517
+ "loss": 0.3788,
1518
+ "step": 2110
1519
+ },
1520
+ {
1521
+ "epoch": 4.148545861297539,
1522
+ "grad_norm": 9.167591094970703,
1523
+ "learning_rate": 2.8592739930382896e-06,
1524
+ "loss": 0.3402,
1525
+ "step": 2120
1526
+ },
1527
+ {
1528
+ "epoch": 4.153020134228188,
1529
+ "grad_norm": 12.899045944213867,
1530
+ "learning_rate": 2.610641471904525e-06,
1531
+ "loss": 0.3131,
1532
+ "step": 2130
1533
+ },
1534
+ {
1535
+ "epoch": 4.157494407158837,
1536
+ "grad_norm": 6.839434623718262,
1537
+ "learning_rate": 2.362008950770761e-06,
1538
+ "loss": 0.2966,
1539
+ "step": 2140
1540
+ },
1541
+ {
1542
+ "epoch": 4.161968680089485,
1543
+ "grad_norm": 17.693748474121094,
1544
+ "learning_rate": 2.1133764296369966e-06,
1545
+ "loss": 0.2908,
1546
+ "step": 2150
1547
+ },
1548
+ {
1549
+ "epoch": 4.166442953020134,
1550
+ "grad_norm": 19.07818031311035,
1551
+ "learning_rate": 1.8647439085032324e-06,
1552
+ "loss": 0.4378,
1553
+ "step": 2160
1554
+ },
1555
+ {
1556
+ "epoch": 4.170917225950783,
1557
+ "grad_norm": 26.521249771118164,
1558
+ "learning_rate": 1.6161113873694681e-06,
1559
+ "loss": 0.2648,
1560
+ "step": 2170
1561
+ },
1562
+ {
1563
+ "epoch": 4.175391498881432,
1564
+ "grad_norm": 6.993879318237305,
1565
+ "learning_rate": 1.3674788662357037e-06,
1566
+ "loss": 0.2574,
1567
+ "step": 2180
1568
+ },
1569
+ {
1570
+ "epoch": 4.17986577181208,
1571
+ "grad_norm": 15.205044746398926,
1572
+ "learning_rate": 1.1188463451019394e-06,
1573
+ "loss": 0.331,
1574
+ "step": 2190
1575
+ },
1576
+ {
1577
+ "epoch": 4.184340044742729,
1578
+ "grad_norm": 7.652498245239258,
1579
+ "learning_rate": 8.702138239681751e-07,
1580
+ "loss": 0.5038,
1581
+ "step": 2200
1582
+ },
1583
+ {
1584
+ "epoch": 4.188814317673378,
1585
+ "grad_norm": 23.202102661132812,
1586
+ "learning_rate": 6.215813028344107e-07,
1587
+ "loss": 0.1272,
1588
+ "step": 2210
1589
+ },
1590
+ {
1591
+ "epoch": 4.193288590604027,
1592
+ "grad_norm": 10.649360656738281,
1593
+ "learning_rate": 3.729487817006464e-07,
1594
+ "loss": 0.3878,
1595
+ "step": 2220
1596
+ },
1597
+ {
1598
+ "epoch": 4.197762863534676,
1599
+ "grad_norm": 1.5082710981369019,
1600
+ "learning_rate": 1.2431626056688215e-07,
1601
+ "loss": 0.3029,
1602
+ "step": 2230
1603
+ },
1604
+ {
1605
+ "epoch": 4.2,
1606
+ "eval_loss": 0.4186529219150543,
1607
+ "eval_runtime": 1490.9643,
1608
+ "eval_samples_per_second": 9.948,
1609
+ "eval_steps_per_second": 1.243,
1610
+ "step": 2235
1611
+ },
1612
+ {
1613
+ "epoch": 4.2,
1614
+ "step": 2235,
1615
+ "total_flos": 7.851155051750621e+19,
1616
+ "train_loss": 0.5695831977280994,
1617
+ "train_runtime": 18281.1253,
1618
+ "train_samples_per_second": 0.978,
1619
+ "train_steps_per_second": 0.122
1620
+ },
1621
+ {
1622
+ "epoch": 4.2,
1623
+ "eval_loss": 0.42570874094963074,
1624
+ "eval_runtime": 2375.8201,
1625
+ "eval_samples_per_second": 8.334,
1626
+ "eval_steps_per_second": 1.042,
1627
+ "step": 2235
1628
+ },
1629
+ {
1630
+ "epoch": 4.2,
1631
+ "eval_loss": 0.42570874094963074,
1632
+ "eval_runtime": 1996.1684,
1633
+ "eval_samples_per_second": 9.919,
1634
+ "eval_steps_per_second": 1.24,
1635
+ "step": 2235
1636
+ }
1637
+ ],
1638
+ "logging_steps": 10,
1639
+ "max_steps": 2235,
1640
+ "num_input_tokens_seen": 0,
1641
+ "num_train_epochs": 9223372036854775807,
1642
+ "save_steps": 500,
1643
+ "stateful_callbacks": {
1644
+ "TrainerControl": {
1645
+ "args": {
1646
+ "should_epoch_stop": false,
1647
+ "should_evaluate": false,
1648
+ "should_log": false,
1649
+ "should_save": true,
1650
+ "should_training_stop": true
1651
+ },
1652
+ "attributes": {}
1653
+ }
1654
+ },
1655
+ "total_flos": 7.851155051750621e+19,
1656
+ "train_batch_size": 8,
1657
+ "trial_name": null,
1658
+ "trial_params": null
1659
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bea7c68371983d030a225145537e74ee1afe51ca4bf574ec5bdad1a625b78939
3
+ size 5240