bobox commited on
Commit
d6e1f65
·
verified ·
1 Parent(s): ed48317

Training in progress, step 112, checkpoint

Browse files
checkpoint-112/1_AdvancedWeightedPooling/config.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "embed_dim": 1024,
3
+ "num_heads": 8,
4
+ "dropout": 0.05,
5
+ "bias": true,
6
+ "use_layernorm": true,
7
+ "use_MLP": true,
8
+ "MLP_h_size": 2048,
9
+ "use_residual": false
10
+ }
checkpoint-112/1_AdvancedWeightedPooling/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27222186ba8547a23d22f54be8d773b47f63957d774504fdf763120019fe40a2
3
+ size 41992722
checkpoint-112/README.md ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-112/config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "XLMRobertaModel"
4
+ ],
5
+ "attention_probs_dropout_prob": 0.1,
6
+ "bos_token_id": 0,
7
+ "classifier_dropout": null,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "gelu",
10
+ "hidden_dropout_prob": 0.1,
11
+ "hidden_size": 1024,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 8194,
16
+ "model_type": "xlm-roberta",
17
+ "num_attention_heads": 16,
18
+ "num_hidden_layers": 24,
19
+ "output_past": true,
20
+ "pad_token_id": 1,
21
+ "position_embedding_type": "absolute",
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.51.1",
24
+ "type_vocab_size": 1,
25
+ "use_cache": true,
26
+ "vocab_size": 250002
27
+ }
checkpoint-112/config_sentence_transformers.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "__version__": {
3
+ "sentence_transformers": "3.4.1",
4
+ "transformers": "4.51.1",
5
+ "pytorch": "2.5.1+cu124"
6
+ },
7
+ "prompts": {},
8
+ "default_prompt_name": null,
9
+ "similarity_fn_name": "cosine"
10
+ }
checkpoint-112/modules.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "idx": 0,
4
+ "name": "0",
5
+ "path": "",
6
+ "type": "sentence_transformers.models.Transformer"
7
+ },
8
+ {
9
+ "idx": 1,
10
+ "name": "1",
11
+ "path": "1_AdvancedWeightedPooling",
12
+ "type": "__main__.AdvancedWeightedPooling"
13
+ }
14
+ ]
checkpoint-112/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fd9111e48f82d2c7c8758f2b4a38cfacdb7bfbe8223c36da4713177973de791
3
+ size 83986682
checkpoint-112/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e969b03be79a3f792216f1febef058e86c2b7f27374fb1e044d87938ceea1ba
3
+ size 2271151270
checkpoint-112/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:edbef4b2e205baafa955cc340f09dce1950158f6958e4321187687836b9435b4
3
+ size 14244
checkpoint-112/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afba8a210f6177200348bfd327c437e1e03a1ba9a0445b261068eed683aa44d8
3
+ size 988
checkpoint-112/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fff05aee53cf63adee7d4b757e500d2f47c668b7b9c1f5451d40f40ef0cbaa51
3
+ size 1000
checkpoint-112/sentence_bert_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_seq_length": 8192,
3
+ "do_lower_case": false
4
+ }
checkpoint-112/sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
3
+ size 5069051
checkpoint-112/special_tokens_map.json ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "cls_token": {
10
+ "content": "<s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "eos_token": {
17
+ "content": "</s>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "mask_token": {
24
+ "content": "<mask>",
25
+ "lstrip": true,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "pad_token": {
31
+ "content": "<pad>",
32
+ "lstrip": false,
33
+ "normalized": false,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "sep_token": {
38
+ "content": "</s>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false
43
+ },
44
+ "unk_token": {
45
+ "content": "<unk>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false
50
+ }
51
+ }
checkpoint-112/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4f7e21bec3fb0044ca0bb2d50eb5d4d8c596273c422baef84466d2c73748b9c
3
+ size 17083053
checkpoint-112/tokenizer_config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "250001": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ }
43
+ },
44
+ "bos_token": "<s>",
45
+ "clean_up_tokenization_spaces": true,
46
+ "cls_token": "<s>",
47
+ "eos_token": "</s>",
48
+ "extra_special_tokens": {},
49
+ "mask_token": "<mask>",
50
+ "model_max_length": 8192,
51
+ "pad_token": "<pad>",
52
+ "sep_token": "</s>",
53
+ "sp_model_kwargs": {},
54
+ "tokenizer_class": "XLMRobertaTokenizer",
55
+ "unk_token": "<unk>"
56
+ }
checkpoint-112/trainer_state.json ADDED
@@ -0,0 +1,952 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.3018867924528302,
6
+ "eval_steps": 56,
7
+ "global_step": 112,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.0026954177897574125,
14
+ "grad_norm": NaN,
15
+ "learning_rate": 0.0,
16
+ "loss": 7.8455,
17
+ "step": 1
18
+ },
19
+ {
20
+ "epoch": 0.005390835579514825,
21
+ "grad_norm": Infinity,
22
+ "learning_rate": 0.0,
23
+ "loss": 10.2716,
24
+ "step": 2
25
+ },
26
+ {
27
+ "epoch": 0.008086253369272238,
28
+ "grad_norm": 34.31669235229492,
29
+ "learning_rate": 0.0,
30
+ "loss": 8.8104,
31
+ "step": 3
32
+ },
33
+ {
34
+ "epoch": 0.01078167115902965,
35
+ "grad_norm": 38.142417907714844,
36
+ "learning_rate": 4.484304932735426e-06,
37
+ "loss": 9.723,
38
+ "step": 4
39
+ },
40
+ {
41
+ "epoch": 0.013477088948787063,
42
+ "grad_norm": 35.18172073364258,
43
+ "learning_rate": 8.968609865470853e-06,
44
+ "loss": 8.2787,
45
+ "step": 5
46
+ },
47
+ {
48
+ "epoch": 0.016172506738544475,
49
+ "grad_norm": 23.283090591430664,
50
+ "learning_rate": 1.345291479820628e-05,
51
+ "loss": 2.1849,
52
+ "step": 6
53
+ },
54
+ {
55
+ "epoch": 0.018867924528301886,
56
+ "grad_norm": 32.1314697265625,
57
+ "learning_rate": 1.7937219730941705e-05,
58
+ "loss": 6.9562,
59
+ "step": 7
60
+ },
61
+ {
62
+ "epoch": 0.0215633423180593,
63
+ "grad_norm": 38.64030456542969,
64
+ "learning_rate": 2.242152466367713e-05,
65
+ "loss": 8.0012,
66
+ "step": 8
67
+ },
68
+ {
69
+ "epoch": 0.02425876010781671,
70
+ "grad_norm": 41.87654495239258,
71
+ "learning_rate": 2.690582959641256e-05,
72
+ "loss": 7.2178,
73
+ "step": 9
74
+ },
75
+ {
76
+ "epoch": 0.026954177897574125,
77
+ "grad_norm": 31.957489013671875,
78
+ "learning_rate": 3.139013452914798e-05,
79
+ "loss": 3.7548,
80
+ "step": 10
81
+ },
82
+ {
83
+ "epoch": 0.029649595687331536,
84
+ "grad_norm": 17.911823272705078,
85
+ "learning_rate": 3.587443946188341e-05,
86
+ "loss": 1.9087,
87
+ "step": 11
88
+ },
89
+ {
90
+ "epoch": 0.03234501347708895,
91
+ "grad_norm": 24.171329498291016,
92
+ "learning_rate": 4.035874439461883e-05,
93
+ "loss": 2.4871,
94
+ "step": 12
95
+ },
96
+ {
97
+ "epoch": 0.03504043126684636,
98
+ "grad_norm": 18.464874267578125,
99
+ "learning_rate": 4.484304932735426e-05,
100
+ "loss": 2.0275,
101
+ "step": 13
102
+ },
103
+ {
104
+ "epoch": 0.03773584905660377,
105
+ "grad_norm": 11.906213760375977,
106
+ "learning_rate": 4.9327354260089685e-05,
107
+ "loss": 1.7456,
108
+ "step": 14
109
+ },
110
+ {
111
+ "epoch": 0.04043126684636118,
112
+ "grad_norm": 26.37287712097168,
113
+ "learning_rate": 5.381165919282512e-05,
114
+ "loss": 1.8779,
115
+ "step": 15
116
+ },
117
+ {
118
+ "epoch": 0.0431266846361186,
119
+ "grad_norm": 14.933402061462402,
120
+ "learning_rate": 5.829596412556054e-05,
121
+ "loss": 1.3286,
122
+ "step": 16
123
+ },
124
+ {
125
+ "epoch": 0.04582210242587601,
126
+ "grad_norm": 21.439697265625,
127
+ "learning_rate": 6.278026905829597e-05,
128
+ "loss": 1.9446,
129
+ "step": 17
130
+ },
131
+ {
132
+ "epoch": 0.04851752021563342,
133
+ "grad_norm": 20.07025146484375,
134
+ "learning_rate": 6.72645739910314e-05,
135
+ "loss": 1.7784,
136
+ "step": 18
137
+ },
138
+ {
139
+ "epoch": 0.05121293800539083,
140
+ "grad_norm": 20.499950408935547,
141
+ "learning_rate": 7.174887892376682e-05,
142
+ "loss": 2.2488,
143
+ "step": 19
144
+ },
145
+ {
146
+ "epoch": 0.05390835579514825,
147
+ "grad_norm": 16.047183990478516,
148
+ "learning_rate": 7.623318385650225e-05,
149
+ "loss": 1.4934,
150
+ "step": 20
151
+ },
152
+ {
153
+ "epoch": 0.05660377358490566,
154
+ "grad_norm": 22.647197723388672,
155
+ "learning_rate": 8.071748878923766e-05,
156
+ "loss": 1.6026,
157
+ "step": 21
158
+ },
159
+ {
160
+ "epoch": 0.05929919137466307,
161
+ "grad_norm": 12.95447063446045,
162
+ "learning_rate": 8.520179372197309e-05,
163
+ "loss": 1.1284,
164
+ "step": 22
165
+ },
166
+ {
167
+ "epoch": 0.06199460916442048,
168
+ "grad_norm": 14.77773666381836,
169
+ "learning_rate": 8.968609865470852e-05,
170
+ "loss": 0.8786,
171
+ "step": 23
172
+ },
173
+ {
174
+ "epoch": 0.0646900269541779,
175
+ "grad_norm": 14.360855102539062,
176
+ "learning_rate": 9.417040358744394e-05,
177
+ "loss": 0.9379,
178
+ "step": 24
179
+ },
180
+ {
181
+ "epoch": 0.0673854447439353,
182
+ "grad_norm": 13.631448745727539,
183
+ "learning_rate": 9.865470852017937e-05,
184
+ "loss": 1.4386,
185
+ "step": 25
186
+ },
187
+ {
188
+ "epoch": 0.07008086253369272,
189
+ "grad_norm": 14.13251781463623,
190
+ "learning_rate": 0.00010313901345291481,
191
+ "loss": 1.4041,
192
+ "step": 26
193
+ },
194
+ {
195
+ "epoch": 0.07277628032345014,
196
+ "grad_norm": 8.827373504638672,
197
+ "learning_rate": 0.00010762331838565024,
198
+ "loss": 0.5954,
199
+ "step": 27
200
+ },
201
+ {
202
+ "epoch": 0.07547169811320754,
203
+ "grad_norm": 14.249119758605957,
204
+ "learning_rate": 0.00011210762331838565,
205
+ "loss": 1.0351,
206
+ "step": 28
207
+ },
208
+ {
209
+ "epoch": 0.07816711590296496,
210
+ "grad_norm": 12.5848970413208,
211
+ "learning_rate": 0.00011659192825112108,
212
+ "loss": 1.1524,
213
+ "step": 29
214
+ },
215
+ {
216
+ "epoch": 0.08086253369272237,
217
+ "grad_norm": 7.9695916175842285,
218
+ "learning_rate": 0.0001210762331838565,
219
+ "loss": 0.4302,
220
+ "step": 30
221
+ },
222
+ {
223
+ "epoch": 0.08355795148247978,
224
+ "grad_norm": 13.62413501739502,
225
+ "learning_rate": 0.00012556053811659193,
226
+ "loss": 1.3629,
227
+ "step": 31
228
+ },
229
+ {
230
+ "epoch": 0.0862533692722372,
231
+ "grad_norm": 8.850028991699219,
232
+ "learning_rate": 0.00013004484304932735,
233
+ "loss": 0.801,
234
+ "step": 32
235
+ },
236
+ {
237
+ "epoch": 0.0889487870619946,
238
+ "grad_norm": 8.944876670837402,
239
+ "learning_rate": 0.0001345291479820628,
240
+ "loss": 0.7135,
241
+ "step": 33
242
+ },
243
+ {
244
+ "epoch": 0.09164420485175202,
245
+ "grad_norm": 12.567760467529297,
246
+ "learning_rate": 0.00013901345291479823,
247
+ "loss": 1.0678,
248
+ "step": 34
249
+ },
250
+ {
251
+ "epoch": 0.09433962264150944,
252
+ "grad_norm": 10.23857593536377,
253
+ "learning_rate": 0.00014349775784753364,
254
+ "loss": 0.8164,
255
+ "step": 35
256
+ },
257
+ {
258
+ "epoch": 0.09703504043126684,
259
+ "grad_norm": 12.49679183959961,
260
+ "learning_rate": 0.00014798206278026908,
261
+ "loss": 0.7157,
262
+ "step": 36
263
+ },
264
+ {
265
+ "epoch": 0.09973045822102426,
266
+ "grad_norm": 8.037866592407227,
267
+ "learning_rate": 0.0001524663677130045,
268
+ "loss": 0.4396,
269
+ "step": 37
270
+ },
271
+ {
272
+ "epoch": 0.10242587601078167,
273
+ "grad_norm": 9.758255004882812,
274
+ "learning_rate": 0.0001569506726457399,
275
+ "loss": 0.9716,
276
+ "step": 38
277
+ },
278
+ {
279
+ "epoch": 0.10512129380053908,
280
+ "grad_norm": 10.123546600341797,
281
+ "learning_rate": 0.00016143497757847532,
282
+ "loss": 0.9321,
283
+ "step": 39
284
+ },
285
+ {
286
+ "epoch": 0.1078167115902965,
287
+ "grad_norm": 8.194007873535156,
288
+ "learning_rate": 0.00016591928251121076,
289
+ "loss": 0.5171,
290
+ "step": 40
291
+ },
292
+ {
293
+ "epoch": 0.1105121293800539,
294
+ "grad_norm": 13.357998847961426,
295
+ "learning_rate": 0.00017040358744394618,
296
+ "loss": 1.9291,
297
+ "step": 41
298
+ },
299
+ {
300
+ "epoch": 0.11320754716981132,
301
+ "grad_norm": 12.821917533874512,
302
+ "learning_rate": 0.00017488789237668162,
303
+ "loss": 1.0919,
304
+ "step": 42
305
+ },
306
+ {
307
+ "epoch": 0.11590296495956873,
308
+ "grad_norm": 15.714422225952148,
309
+ "learning_rate": 0.00017937219730941703,
310
+ "loss": 1.4841,
311
+ "step": 43
312
+ },
313
+ {
314
+ "epoch": 0.11859838274932614,
315
+ "grad_norm": 9.68891429901123,
316
+ "learning_rate": 0.00018385650224215247,
317
+ "loss": 1.1497,
318
+ "step": 44
319
+ },
320
+ {
321
+ "epoch": 0.12129380053908356,
322
+ "grad_norm": 11.406339645385742,
323
+ "learning_rate": 0.00018834080717488789,
324
+ "loss": 0.7006,
325
+ "step": 45
326
+ },
327
+ {
328
+ "epoch": 0.12398921832884097,
329
+ "grad_norm": 13.979656219482422,
330
+ "learning_rate": 0.00019282511210762333,
331
+ "loss": 1.7046,
332
+ "step": 46
333
+ },
334
+ {
335
+ "epoch": 0.12668463611859837,
336
+ "grad_norm": 11.99986743927002,
337
+ "learning_rate": 0.00019730941704035874,
338
+ "loss": 0.8556,
339
+ "step": 47
340
+ },
341
+ {
342
+ "epoch": 0.1293800539083558,
343
+ "grad_norm": 13.813502311706543,
344
+ "learning_rate": 0.00020179372197309418,
345
+ "loss": 1.6158,
346
+ "step": 48
347
+ },
348
+ {
349
+ "epoch": 0.1320754716981132,
350
+ "grad_norm": 10.904289245605469,
351
+ "learning_rate": 0.00020627802690582962,
352
+ "loss": 1.3545,
353
+ "step": 49
354
+ },
355
+ {
356
+ "epoch": 0.1347708894878706,
357
+ "grad_norm": 10.595293045043945,
358
+ "learning_rate": 0.00021076233183856503,
359
+ "loss": 1.0598,
360
+ "step": 50
361
+ },
362
+ {
363
+ "epoch": 0.13746630727762804,
364
+ "grad_norm": 11.345131874084473,
365
+ "learning_rate": 0.00021524663677130048,
366
+ "loss": 1.3435,
367
+ "step": 51
368
+ },
369
+ {
370
+ "epoch": 0.14016172506738545,
371
+ "grad_norm": 7.457268714904785,
372
+ "learning_rate": 0.00021973094170403586,
373
+ "loss": 0.5441,
374
+ "step": 52
375
+ },
376
+ {
377
+ "epoch": 0.14285714285714285,
378
+ "grad_norm": 11.910417556762695,
379
+ "learning_rate": 0.0002242152466367713,
380
+ "loss": 0.8275,
381
+ "step": 53
382
+ },
383
+ {
384
+ "epoch": 0.14555256064690028,
385
+ "grad_norm": 9.867291450500488,
386
+ "learning_rate": 0.00022869955156950672,
387
+ "loss": 1.0796,
388
+ "step": 54
389
+ },
390
+ {
391
+ "epoch": 0.14824797843665768,
392
+ "grad_norm": 10.172917366027832,
393
+ "learning_rate": 0.00023318385650224216,
394
+ "loss": 0.9102,
395
+ "step": 55
396
+ },
397
+ {
398
+ "epoch": 0.1509433962264151,
399
+ "grad_norm": 8.819664001464844,
400
+ "learning_rate": 0.00023766816143497757,
401
+ "loss": 0.6044,
402
+ "step": 56
403
+ },
404
+ {
405
+ "epoch": 0.1509433962264151,
406
+ "eval_NLI_loss": 0.7544407844543457,
407
+ "eval_NLI_runtime": 7.8068,
408
+ "eval_NLI_samples_per_second": 10.888,
409
+ "eval_NLI_steps_per_second": 0.128,
410
+ "eval_Qnli-dev_cosine_accuracy": 0.70703125,
411
+ "eval_Qnli-dev_cosine_accuracy_threshold": 0.6635605096817017,
412
+ "eval_Qnli-dev_cosine_ap": 0.7579116921492454,
413
+ "eval_Qnli-dev_cosine_f1": 0.7244582043343653,
414
+ "eval_Qnli-dev_cosine_f1_threshold": 0.5038043260574341,
415
+ "eval_Qnli-dev_cosine_mcc": 0.39539276409398366,
416
+ "eval_Qnli-dev_cosine_precision": 0.585,
417
+ "eval_Qnli-dev_cosine_recall": 0.9512195121951219,
418
+ "eval_allNLI-dev_cosine_accuracy": 0.78125,
419
+ "eval_allNLI-dev_cosine_accuracy_threshold": 0.7955116629600525,
420
+ "eval_allNLI-dev_cosine_ap": 0.6859718496364101,
421
+ "eval_allNLI-dev_cosine_f1": 0.6857142857142857,
422
+ "eval_allNLI-dev_cosine_f1_threshold": 0.6457934975624084,
423
+ "eval_allNLI-dev_cosine_mcc": 0.5238511237227645,
424
+ "eval_allNLI-dev_cosine_precision": 0.5581395348837209,
425
+ "eval_allNLI-dev_cosine_recall": 0.8888888888888888,
426
+ "eval_sequential_score": 0.7579116921492454,
427
+ "eval_sts-test_pearson_cosine": 0.8834267284176791,
428
+ "eval_sts-test_spearman_cosine": 0.9131686859687813,
429
+ "step": 56
430
+ },
431
+ {
432
+ "epoch": 0.1509433962264151,
433
+ "eval_natural-questions_loss": 0.12529510259628296,
434
+ "eval_natural-questions_runtime": 7.7929,
435
+ "eval_natural-questions_samples_per_second": 14.5,
436
+ "eval_natural-questions_steps_per_second": 0.128,
437
+ "step": 56
438
+ },
439
+ {
440
+ "epoch": 0.1509433962264151,
441
+ "eval_vitaminc_loss": 1.7376117706298828,
442
+ "eval_vitaminc_runtime": 1.558,
443
+ "eval_vitaminc_samples_per_second": 72.527,
444
+ "eval_vitaminc_steps_per_second": 0.642,
445
+ "step": 56
446
+ },
447
+ {
448
+ "epoch": 0.1509433962264151,
449
+ "eval_xsum_loss": 0.30277687311172485,
450
+ "eval_xsum_runtime": 7.6031,
451
+ "eval_xsum_samples_per_second": 14.862,
452
+ "eval_xsum_steps_per_second": 0.132,
453
+ "step": 56
454
+ },
455
+ {
456
+ "epoch": 0.1509433962264151,
457
+ "eval_paws_loss": 0.022768845781683922,
458
+ "eval_paws_runtime": 1.2613,
459
+ "eval_paws_samples_per_second": 89.589,
460
+ "eval_paws_steps_per_second": 0.793,
461
+ "step": 56
462
+ },
463
+ {
464
+ "epoch": 0.1509433962264151,
465
+ "eval_global_dataset_loss": 0.36483433842658997,
466
+ "eval_global_dataset_runtime": 17.4308,
467
+ "eval_global_dataset_samples_per_second": 14.687,
468
+ "eval_global_dataset_steps_per_second": 0.057,
469
+ "step": 56
470
+ },
471
+ {
472
+ "epoch": 0.15363881401617252,
473
+ "grad_norm": 9.806305885314941,
474
+ "learning_rate": 0.000242152466367713,
475
+ "loss": 0.6791,
476
+ "step": 57
477
+ },
478
+ {
479
+ "epoch": 0.15633423180592992,
480
+ "grad_norm": 13.261207580566406,
481
+ "learning_rate": 0.0002466367713004484,
482
+ "loss": 2.0332,
483
+ "step": 58
484
+ },
485
+ {
486
+ "epoch": 0.15902964959568733,
487
+ "grad_norm": 12.368124008178711,
488
+ "learning_rate": 0.00025112107623318387,
489
+ "loss": 1.6908,
490
+ "step": 59
491
+ },
492
+ {
493
+ "epoch": 0.16172506738544473,
494
+ "grad_norm": 12.33912467956543,
495
+ "learning_rate": 0.0002556053811659193,
496
+ "loss": 1.9835,
497
+ "step": 60
498
+ },
499
+ {
500
+ "epoch": 0.16442048517520216,
501
+ "grad_norm": 6.012735366821289,
502
+ "learning_rate": 0.0002600896860986547,
503
+ "loss": 0.5596,
504
+ "step": 61
505
+ },
506
+ {
507
+ "epoch": 0.16711590296495957,
508
+ "grad_norm": 7.400477409362793,
509
+ "learning_rate": 0.00026457399103139013,
510
+ "loss": 0.5455,
511
+ "step": 62
512
+ },
513
+ {
514
+ "epoch": 0.16981132075471697,
515
+ "grad_norm": 11.265143394470215,
516
+ "learning_rate": 0.0002690582959641256,
517
+ "loss": 1.4403,
518
+ "step": 63
519
+ },
520
+ {
521
+ "epoch": 0.1725067385444744,
522
+ "grad_norm": 10.963008880615234,
523
+ "learning_rate": 0.000273542600896861,
524
+ "loss": 1.3612,
525
+ "step": 64
526
+ },
527
+ {
528
+ "epoch": 0.1752021563342318,
529
+ "grad_norm": 6.337466716766357,
530
+ "learning_rate": 0.00027802690582959646,
531
+ "loss": 0.4134,
532
+ "step": 65
533
+ },
534
+ {
535
+ "epoch": 0.1778975741239892,
536
+ "grad_norm": 9.300302505493164,
537
+ "learning_rate": 0.00028251121076233184,
538
+ "loss": 1.1737,
539
+ "step": 66
540
+ },
541
+ {
542
+ "epoch": 0.18059299191374664,
543
+ "grad_norm": 11.601908683776855,
544
+ "learning_rate": 0.0002869955156950673,
545
+ "loss": 0.9298,
546
+ "step": 67
547
+ },
548
+ {
549
+ "epoch": 0.18328840970350405,
550
+ "grad_norm": 10.370750427246094,
551
+ "learning_rate": 0.0002914798206278027,
552
+ "loss": 1.1334,
553
+ "step": 68
554
+ },
555
+ {
556
+ "epoch": 0.18598382749326145,
557
+ "grad_norm": 10.676084518432617,
558
+ "learning_rate": 0.00029596412556053816,
559
+ "loss": 1.0759,
560
+ "step": 69
561
+ },
562
+ {
563
+ "epoch": 0.18867924528301888,
564
+ "grad_norm": 10.255388259887695,
565
+ "learning_rate": 0.00030044843049327355,
566
+ "loss": 0.961,
567
+ "step": 70
568
+ },
569
+ {
570
+ "epoch": 0.19137466307277629,
571
+ "grad_norm": 4.847160816192627,
572
+ "learning_rate": 0.000304932735426009,
573
+ "loss": 0.329,
574
+ "step": 71
575
+ },
576
+ {
577
+ "epoch": 0.1940700808625337,
578
+ "grad_norm": 10.309353828430176,
579
+ "learning_rate": 0.00030941704035874443,
580
+ "loss": 1.4607,
581
+ "step": 72
582
+ },
583
+ {
584
+ "epoch": 0.1967654986522911,
585
+ "grad_norm": 10.96381664276123,
586
+ "learning_rate": 0.0003139013452914798,
587
+ "loss": 1.13,
588
+ "step": 73
589
+ },
590
+ {
591
+ "epoch": 0.19946091644204852,
592
+ "grad_norm": 7.316355228424072,
593
+ "learning_rate": 0.0003183856502242152,
594
+ "loss": 0.4843,
595
+ "step": 74
596
+ },
597
+ {
598
+ "epoch": 0.20215633423180593,
599
+ "grad_norm": 10.928675651550293,
600
+ "learning_rate": 0.00032286995515695065,
601
+ "loss": 1.1167,
602
+ "step": 75
603
+ },
604
+ {
605
+ "epoch": 0.20485175202156333,
606
+ "grad_norm": 8.18099594116211,
607
+ "learning_rate": 0.0003273542600896861,
608
+ "loss": 0.7438,
609
+ "step": 76
610
+ },
611
+ {
612
+ "epoch": 0.20754716981132076,
613
+ "grad_norm": 11.222527503967285,
614
+ "learning_rate": 0.0003318385650224215,
615
+ "loss": 1.0913,
616
+ "step": 77
617
+ },
618
+ {
619
+ "epoch": 0.21024258760107817,
620
+ "grad_norm": 10.6032133102417,
621
+ "learning_rate": 0.00033632286995515697,
622
+ "loss": 1.0479,
623
+ "step": 78
624
+ },
625
+ {
626
+ "epoch": 0.21293800539083557,
627
+ "grad_norm": 11.290767669677734,
628
+ "learning_rate": 0.00034080717488789235,
629
+ "loss": 1.1103,
630
+ "step": 79
631
+ },
632
+ {
633
+ "epoch": 0.215633423180593,
634
+ "grad_norm": 9.03909969329834,
635
+ "learning_rate": 0.0003452914798206278,
636
+ "loss": 0.9204,
637
+ "step": 80
638
+ },
639
+ {
640
+ "epoch": 0.2183288409703504,
641
+ "grad_norm": 10.852116584777832,
642
+ "learning_rate": 0.00034977578475336324,
643
+ "loss": 0.9669,
644
+ "step": 81
645
+ },
646
+ {
647
+ "epoch": 0.2210242587601078,
648
+ "grad_norm": 10.944169044494629,
649
+ "learning_rate": 0.0003542600896860987,
650
+ "loss": 1.6861,
651
+ "step": 82
652
+ },
653
+ {
654
+ "epoch": 0.22371967654986524,
655
+ "grad_norm": 8.94461727142334,
656
+ "learning_rate": 0.00035874439461883406,
657
+ "loss": 1.076,
658
+ "step": 83
659
+ },
660
+ {
661
+ "epoch": 0.22641509433962265,
662
+ "grad_norm": 10.783270835876465,
663
+ "learning_rate": 0.0003632286995515695,
664
+ "loss": 1.2668,
665
+ "step": 84
666
+ },
667
+ {
668
+ "epoch": 0.22911051212938005,
669
+ "grad_norm": 10.639765739440918,
670
+ "learning_rate": 0.00036771300448430494,
671
+ "loss": 1.4458,
672
+ "step": 85
673
+ },
674
+ {
675
+ "epoch": 0.23180592991913745,
676
+ "grad_norm": 8.094260215759277,
677
+ "learning_rate": 0.0003721973094170404,
678
+ "loss": 1.0282,
679
+ "step": 86
680
+ },
681
+ {
682
+ "epoch": 0.23450134770889489,
683
+ "grad_norm": 10.396455764770508,
684
+ "learning_rate": 0.00037668161434977577,
685
+ "loss": 0.9422,
686
+ "step": 87
687
+ },
688
+ {
689
+ "epoch": 0.2371967654986523,
690
+ "grad_norm": 9.362552642822266,
691
+ "learning_rate": 0.0003811659192825112,
692
+ "loss": 0.8485,
693
+ "step": 88
694
+ },
695
+ {
696
+ "epoch": 0.2398921832884097,
697
+ "grad_norm": 7.508151531219482,
698
+ "learning_rate": 0.00038565022421524665,
699
+ "loss": 0.6634,
700
+ "step": 89
701
+ },
702
+ {
703
+ "epoch": 0.24258760107816713,
704
+ "grad_norm": 7.089418888092041,
705
+ "learning_rate": 0.0003901345291479821,
706
+ "loss": 0.5559,
707
+ "step": 90
708
+ },
709
+ {
710
+ "epoch": 0.24528301886792453,
711
+ "grad_norm": 6.452119827270508,
712
+ "learning_rate": 0.0003946188340807175,
713
+ "loss": 0.4284,
714
+ "step": 91
715
+ },
716
+ {
717
+ "epoch": 0.24797843665768193,
718
+ "grad_norm": 8.258156776428223,
719
+ "learning_rate": 0.0003991031390134529,
720
+ "loss": 0.8843,
721
+ "step": 92
722
+ },
723
+ {
724
+ "epoch": 0.25067385444743934,
725
+ "grad_norm": 9.86504077911377,
726
+ "learning_rate": 0.00040358744394618836,
727
+ "loss": 1.1379,
728
+ "step": 93
729
+ },
730
+ {
731
+ "epoch": 0.25336927223719674,
732
+ "grad_norm": 9.736706733703613,
733
+ "learning_rate": 0.0004080717488789238,
734
+ "loss": 0.8325,
735
+ "step": 94
736
+ },
737
+ {
738
+ "epoch": 0.2560646900269542,
739
+ "grad_norm": 7.768691539764404,
740
+ "learning_rate": 0.00041255605381165924,
741
+ "loss": 0.7055,
742
+ "step": 95
743
+ },
744
+ {
745
+ "epoch": 0.2587601078167116,
746
+ "grad_norm": 6.694875717163086,
747
+ "learning_rate": 0.00041704035874439463,
748
+ "loss": 0.5176,
749
+ "step": 96
750
+ },
751
+ {
752
+ "epoch": 0.261455525606469,
753
+ "grad_norm": 7.5387349128723145,
754
+ "learning_rate": 0.00042152466367713007,
755
+ "loss": 0.6018,
756
+ "step": 97
757
+ },
758
+ {
759
+ "epoch": 0.2641509433962264,
760
+ "grad_norm": 11.206459045410156,
761
+ "learning_rate": 0.0004260089686098655,
762
+ "loss": 1.2091,
763
+ "step": 98
764
+ },
765
+ {
766
+ "epoch": 0.2668463611859838,
767
+ "grad_norm": 10.008997917175293,
768
+ "learning_rate": 0.00043049327354260095,
769
+ "loss": 1.1578,
770
+ "step": 99
771
+ },
772
+ {
773
+ "epoch": 0.2695417789757412,
774
+ "grad_norm": 12.285299301147461,
775
+ "learning_rate": 0.00043497757847533634,
776
+ "loss": 1.3774,
777
+ "step": 100
778
+ },
779
+ {
780
+ "epoch": 0.2722371967654987,
781
+ "grad_norm": 10.43669605255127,
782
+ "learning_rate": 0.0004394618834080717,
783
+ "loss": 1.6864,
784
+ "step": 101
785
+ },
786
+ {
787
+ "epoch": 0.2749326145552561,
788
+ "grad_norm": 11.803585052490234,
789
+ "learning_rate": 0.00044394618834080716,
790
+ "loss": 1.5131,
791
+ "step": 102
792
+ },
793
+ {
794
+ "epoch": 0.2776280323450135,
795
+ "grad_norm": 10.69809341430664,
796
+ "learning_rate": 0.0004484304932735426,
797
+ "loss": 1.5626,
798
+ "step": 103
799
+ },
800
+ {
801
+ "epoch": 0.2803234501347709,
802
+ "grad_norm": 10.971607208251953,
803
+ "learning_rate": 0.000452914798206278,
804
+ "loss": 1.5972,
805
+ "step": 104
806
+ },
807
+ {
808
+ "epoch": 0.2830188679245283,
809
+ "grad_norm": 9.838319778442383,
810
+ "learning_rate": 0.00045739910313901343,
811
+ "loss": 1.1608,
812
+ "step": 105
813
+ },
814
+ {
815
+ "epoch": 0.2857142857142857,
816
+ "grad_norm": 10.64057731628418,
817
+ "learning_rate": 0.0004618834080717489,
818
+ "loss": 1.7296,
819
+ "step": 106
820
+ },
821
+ {
822
+ "epoch": 0.2884097035040431,
823
+ "grad_norm": 9.250954627990723,
824
+ "learning_rate": 0.0004663677130044843,
825
+ "loss": 0.7756,
826
+ "step": 107
827
+ },
828
+ {
829
+ "epoch": 0.29110512129380056,
830
+ "grad_norm": 10.505428314208984,
831
+ "learning_rate": 0.00047085201793721975,
832
+ "loss": 1.4043,
833
+ "step": 108
834
+ },
835
+ {
836
+ "epoch": 0.29380053908355797,
837
+ "grad_norm": 9.503642082214355,
838
+ "learning_rate": 0.00047533632286995514,
839
+ "loss": 1.0434,
840
+ "step": 109
841
+ },
842
+ {
843
+ "epoch": 0.29649595687331537,
844
+ "grad_norm": 10.04104995727539,
845
+ "learning_rate": 0.0004798206278026906,
846
+ "loss": 0.7851,
847
+ "step": 110
848
+ },
849
+ {
850
+ "epoch": 0.2991913746630728,
851
+ "grad_norm": 8.496233940124512,
852
+ "learning_rate": 0.000484304932735426,
853
+ "loss": 0.8959,
854
+ "step": 111
855
+ },
856
+ {
857
+ "epoch": 0.3018867924528302,
858
+ "grad_norm": 8.900400161743164,
859
+ "learning_rate": 0.0004887892376681615,
860
+ "loss": 1.1451,
861
+ "step": 112
862
+ },
863
+ {
864
+ "epoch": 0.3018867924528302,
865
+ "eval_NLI_loss": 0.7853685021400452,
866
+ "eval_NLI_runtime": 7.7802,
867
+ "eval_NLI_samples_per_second": 10.925,
868
+ "eval_NLI_steps_per_second": 0.129,
869
+ "eval_Qnli-dev_cosine_accuracy": 0.69921875,
870
+ "eval_Qnli-dev_cosine_accuracy_threshold": 0.6639883518218994,
871
+ "eval_Qnli-dev_cosine_ap": 0.7520437823272439,
872
+ "eval_Qnli-dev_cosine_f1": 0.6956521739130435,
873
+ "eval_Qnli-dev_cosine_f1_threshold": 0.6639883518218994,
874
+ "eval_Qnli-dev_cosine_mcc": 0.3994014078011956,
875
+ "eval_Qnli-dev_cosine_precision": 0.676923076923077,
876
+ "eval_Qnli-dev_cosine_recall": 0.7154471544715447,
877
+ "eval_allNLI-dev_cosine_accuracy": 0.7734375,
878
+ "eval_allNLI-dev_cosine_accuracy_threshold": 0.7482618689537048,
879
+ "eval_allNLI-dev_cosine_ap": 0.6542135747366074,
880
+ "eval_allNLI-dev_cosine_f1": 0.6769230769230768,
881
+ "eval_allNLI-dev_cosine_f1_threshold": 0.694869875907898,
882
+ "eval_allNLI-dev_cosine_mcc": 0.5058060457173612,
883
+ "eval_allNLI-dev_cosine_precision": 0.5789473684210527,
884
+ "eval_allNLI-dev_cosine_recall": 0.8148148148148148,
885
+ "eval_sequential_score": 0.7520437823272439,
886
+ "eval_sts-test_pearson_cosine": 0.9037962998590239,
887
+ "eval_sts-test_spearman_cosine": 0.9228968065127588,
888
+ "step": 112
889
+ },
890
+ {
891
+ "epoch": 0.3018867924528302,
892
+ "eval_natural-questions_loss": 0.11738906055688858,
893
+ "eval_natural-questions_runtime": 7.7914,
894
+ "eval_natural-questions_samples_per_second": 14.503,
895
+ "eval_natural-questions_steps_per_second": 0.128,
896
+ "step": 112
897
+ },
898
+ {
899
+ "epoch": 0.3018867924528302,
900
+ "eval_vitaminc_loss": 2.176020622253418,
901
+ "eval_vitaminc_runtime": 1.5419,
902
+ "eval_vitaminc_samples_per_second": 73.285,
903
+ "eval_vitaminc_steps_per_second": 0.649,
904
+ "step": 112
905
+ },
906
+ {
907
+ "epoch": 0.3018867924528302,
908
+ "eval_xsum_loss": 0.14663243293762207,
909
+ "eval_xsum_runtime": 7.5949,
910
+ "eval_xsum_samples_per_second": 14.878,
911
+ "eval_xsum_steps_per_second": 0.132,
912
+ "step": 112
913
+ },
914
+ {
915
+ "epoch": 0.3018867924528302,
916
+ "eval_paws_loss": 0.022128984332084656,
917
+ "eval_paws_runtime": 1.2514,
918
+ "eval_paws_samples_per_second": 90.302,
919
+ "eval_paws_steps_per_second": 0.799,
920
+ "step": 112
921
+ },
922
+ {
923
+ "epoch": 0.3018867924528302,
924
+ "eval_global_dataset_loss": 0.5730272531509399,
925
+ "eval_global_dataset_runtime": 17.42,
926
+ "eval_global_dataset_samples_per_second": 14.696,
927
+ "eval_global_dataset_steps_per_second": 0.057,
928
+ "step": 112
929
+ }
930
+ ],
931
+ "logging_steps": 1,
932
+ "max_steps": 1113,
933
+ "num_input_tokens_seen": 0,
934
+ "num_train_epochs": 3,
935
+ "save_steps": 112,
936
+ "stateful_callbacks": {
937
+ "TrainerControl": {
938
+ "args": {
939
+ "should_epoch_stop": false,
940
+ "should_evaluate": false,
941
+ "should_log": false,
942
+ "should_save": true,
943
+ "should_training_stop": false
944
+ },
945
+ "attributes": {}
946
+ }
947
+ },
948
+ "total_flos": 0.0,
949
+ "train_batch_size": 128,
950
+ "trial_name": null,
951
+ "trial_params": null
952
+ }
checkpoint-112/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:376f8d1f23e3afc17ce699417922837d0461cc4b226add78679286487de5c3e6
3
+ size 5880