Hugging Face's logo

alex2awesome
/
quote-detection__roberta-base-sentence-v2

Transformers
PyTorch
roberta
Inference Endpoints
Model card Files Community
Alex Spangher commited on
Commit
97da542
·
1 Parent(s): e0ac58f

e

Browse files
Files changed (14) hide show
  1. all_results.json +14 -0
  2. callback-metrics-state-10000.json +1 -0
  3. callback-metrics-state-12000.json +1 -0
  4. callback-metrics-state-2000.json +1 -0
  5. callback-metrics-state-4000.json +1 -0
  6. callback-metrics-state-6000.json +1 -0
  7. callback-metrics-state-8000.json +1 -0
  8. config.json +42 -0
  9. post-training eval_results.json +8 -0
  10. prediction_output.jsonl +1 -0
  11. pytorch_model.bin +3 -0
  12. train_results.json +8 -0
  13. trainer_state.json +232 -0
  14. training_args.bin +3 -0
all_results.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "eval_samples": 86,
4
+ "test_f1": 0.8056872037914692,
5
+ "test_loss": 0.4573868425250922,
6
+ "test_runtime": 9.4978,
7
+ "test_samples_per_second": 9.055,
8
+ "test_steps_per_second": 9.055,
9
+ "train_loss": 0.12557823169776508,
10
+ "train_runtime": 2775.7723,
11
+ "train_samples": 2515,
12
+ "train_samples_per_second": 4.53,
13
+ "train_steps_per_second": 4.53
14
+ }
callback-metrics-state-10000.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"DIRECT QUOTE_f1": 0.9279359430604982, "full_f1": 0.8029407524866656, "BACKGROUND_f1": 0.7656033287101248, "NO QUOTE_f1": 0.0, "INDIRECT QUOTE_f1": 0.8148541114058356, "PUBLISHED WORK_f1": 0.8333333333333333, "STATEMENT_f1": 0.9477124183006536, "PRESS REPORT_f1": 0.9375, "DECLINED COMMENT_f1": 0.9444444444444444, "SOCIAL MEDIA POST_f1": 0.8936170212765957, "PROPOSAL/ORDER/LAW_f1": 0.5517241379310345, "PRICE SIGNAL_f1": 0.7272727272727273, "NARRATIVE_f1": 0.8739495798319328, "DIRECT OBSERVATION_f1": 0.4109589041095891, "COMMUNICATION_f1": 0.9672131147540983, "PUBLIC SPEECH_f1": 0.983050847457627, "VOTE/POLL_f1": 0.8205128205128205, "COURT PROCEEDING_f1": 0.9491525423728813}
callback-metrics-state-12000.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"DIRECT QUOTE_f1": 0.9284126278345932, "full_f1": 0.8055235903337169, "BACKGROUND_f1": 0.770718232044199, "NO QUOTE_f1": 0.0, "INDIRECT QUOTE_f1": 0.8142250530785562, "PUBLISHED WORK_f1": 0.8680851063829788, "STATEMENT_f1": 0.9477124183006536, "PRESS REPORT_f1": 0.9457364341085273, "DECLINED COMMENT_f1": 0.9444444444444444, "SOCIAL MEDIA POST_f1": 0.8936170212765957, "PROPOSAL/ORDER/LAW_f1": 0.5616438356164384, "PRICE SIGNAL_f1": 0.7272727272727273, "NARRATIVE_f1": 0.8833333333333333, "DIRECT OBSERVATION_f1": 0.4324324324324324, "COMMUNICATION_f1": 0.9672131147540983, "PUBLIC SPEECH_f1": 0.983050847457627, "VOTE/POLL_f1": 0.8205128205128205, "COURT PROCEEDING_f1": 0.9491525423728813}
callback-metrics-state-2000.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"DIRECT QUOTE_f1": 0.9114724480578139, "full_f1": 0.8002317832826308, "BACKGROUND_f1": 0.7604456824512534, "NO QUOTE_f1": 0.0, "INDIRECT QUOTE_f1": 0.8148541114058356, "PUBLISHED WORK_f1": 0.8484848484848484, "STATEMENT_f1": 0.9511400651465798, "PRESS REPORT_f1": 0.9457364341085273, "DECLINED COMMENT_f1": 0.9444444444444444, "SOCIAL MEDIA POST_f1": 0.8936170212765957, "PROPOSAL/ORDER/LAW_f1": 0.7037037037037037, "PRICE SIGNAL_f1": 0.5517241379310345, "NARRATIVE_f1": 0.8497854077253219, "DIRECT OBSERVATION_f1": 0.4533333333333333, "COMMUNICATION_f1": 0.9672131147540983, "PUBLIC SPEECH_f1": 0.983050847457627, "VOTE/POLL_f1": 0.7567567567567568, "COURT PROCEEDING_f1": 0.9579831932773109}
callback-metrics-state-4000.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"DIRECT QUOTE_f1": 0.923626619026351, "full_f1": 0.797415004214667, "BACKGROUND_f1": 0.8196286472148542, "NO QUOTE_f1": 0.0, "INDIRECT QUOTE_f1": 0.8154825026511134, "PUBLISHED WORK_f1": 0.8823529411764706, "STATEMENT_f1": 0.9545454545454545, "PRESS REPORT_f1": 0.9457364341085273, "DECLINED COMMENT_f1": 1.0, "SOCIAL MEDIA POST_f1": 0.8936170212765957, "PROPOSAL/ORDER/LAW_f1": 0.6538461538461539, "PRICE SIGNAL_f1": 0.7647058823529412, "NARRATIVE_f1": 0.869198312236287, "DIRECT OBSERVATION_f1": 0.4533333333333333, "COMMUNICATION_f1": 0.975609756097561, "PUBLIC SPEECH_f1": 0.9743589743589743, "VOTE/POLL_f1": 0.7894736842105263, "COURT PROCEEDING_f1": 0.9579831932773109}
callback-metrics-state-6000.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"DIRECT QUOTE_f1": 0.9805414551607444, "full_f1": 0.785323775968898, "BACKGROUND_f1": 0.9699074074074074, "NO QUOTE_f1": 0.0, "INDIRECT QUOTE_f1": 0.825446898002103, "PUBLISHED WORK_f1": 0.9609375000000001, "STATEMENT_f1": 0.9905956112852665, "PRESS REPORT_f1": 0.9538461538461539, "DECLINED COMMENT_f1": 1.0, "SOCIAL MEDIA POST_f1": 0.9387755102040816, "PROPOSAL/ORDER/LAW_f1": 0.9447236180904524, "PRICE SIGNAL_f1": 0.975609756097561, "NARRATIVE_f1": 0.9886792452830189, "DIRECT OBSERVATION_f1": 0.7789473684210527, "COMMUNICATION_f1": 0.9838709677419354, "PUBLIC SPEECH_f1": 0.983050847457627, "VOTE/POLL_f1": 0.9545454545454545, "COURT PROCEEDING_f1": 1.0}
callback-metrics-state-8000.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"DIRECT QUOTE_f1": 0.8837424733672997, "full_f1": 0.7811158798283263, "BACKGROUND_f1": 0.6853766617429837, "NO QUOTE_f1": 0.0, "INDIRECT QUOTE_f1": 0.8059861036878675, "PUBLISHED WORK_f1": 0.7511737089201878, "STATEMENT_f1": 0.9158249158249159, "PRESS REPORT_f1": 0.9032258064516129, "DECLINED COMMENT_f1": 0.9444444444444444, "SOCIAL MEDIA POST_f1": 0.7317073170731707, "PROPOSAL/ORDER/LAW_f1": 0.3464566929133859, "PRICE SIGNAL_f1": 0.5517241379310345, "NARRATIVE_f1": 0.8547008547008548, "DIRECT OBSERVATION_f1": 0.26865671641791045, "COMMUNICATION_f1": 0.9137931034482758, "PUBLIC SPEECH_f1": 0.9285714285714286, "VOTE/POLL_f1": 0.7894736842105263, "COURT PROCEEDING_f1": 0.8411214953271028}
config.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "roberta-base",
3
+ "architectures": [
4
+ "SentenceClassificationModel"
5
+ ],
6
+ "attention_probs_dropout_prob": 0.1,
7
+ "bos_token_id": 0,
8
+ "classification_head": {
9
+ "num_labels": 1,
10
+ "pooling_method": "attention"
11
+ },
12
+ "classifier_dropout": null,
13
+ "context_layer": null,
14
+ "eos_token_id": 2,
15
+ "frozen_layers": [
16
+ 0,
17
+ 1,
18
+ 2,
19
+ 3,
20
+ 4,
21
+ 5,
22
+ 6,
23
+ 7
24
+ ],
25
+ "hidden_act": "gelu",
26
+ "hidden_dropout_prob": 0.1,
27
+ "hidden_size": 768,
28
+ "initializer_range": 0.02,
29
+ "intermediate_size": 3072,
30
+ "layer_norm_eps": 1e-05,
31
+ "max_position_embeddings": 514,
32
+ "model_type": "roberta",
33
+ "num_attention_heads": 12,
34
+ "num_hidden_layers": 12,
35
+ "pad_token_id": 1,
36
+ "position_embedding_type": "absolute",
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.33.2",
39
+ "type_vocab_size": 1,
40
+ "use_cache": true,
41
+ "vocab_size": 50265
42
+ }
post-training eval_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "eval_samples": 86,
3
+ "test_f1": 0.8056872037914692,
4
+ "test_loss": 0.4573868425250922,
5
+ "test_runtime": 9.4978,
6
+ "test_samples_per_second": 9.055,
7
+ "test_steps_per_second": 9.055
8
+ }
prediction_output.jsonl ADDED
@@ -0,0 +1 @@
 
 
1
+ [{"pred": -1.8532243967056274, "label": 1.0}, {"pred": 1.1651102304458618, "label": 1.0}, {"pred": 2.043649435043335, "label": 1.0}, {"pred": -0.94322270154953, "label": 0.0}, {"pred": 7.705276012420654, "label": 1.0}, {"pred": -0.94322270154953, "label": 1.0}, {"pred": 0.783161997795105, "label": 1.0}, {"pred": -4.46294641494751, "label": 0.0}, {"pred": 4.064390659332275, "label": 1.0}, {"pred": 3.504645824432373, "label": 1.0}, {"pred": 1.139365792274475, "label": 1.0}, {"pred": 4.107277870178223, "label": 1.0}, {"pred": 2.425071954727173, "label": 1.0}, {"pred": 4.992768287658691, "label": 1.0}, {"pred": -3.566384792327881, "label": 0.0}, {"pred": 8.3724946975708, "label": 1.0}, {"pred": -0.94322270154953, "label": 1.0}, {"pred": 2.2570552825927734, "label": 1.0}, {"pred": 3.5059964656829834, "label": 1.0}, {"pred": 2.354095935821533, "label": 1.0}, {"pred": -4.46294641494751, "label": 0.0}, {"pred": 0.7503432631492615, "label": 1.0}, {"pred": 6.353982925415039, "label": 1.0}, {"pred": 0.9827572703361511, "label": 1.0}, {"pred": -0.4256363809108734, "label": 0.0}, {"pred": -1.804305911064148, "label": 0.0}, {"pred": -0.94322270154953, "label": 0.0}, {"pred": 7.299091815948486, "label": 1.0}, {"pred": 3.8024141788482666, "label": 0.0}, {"pred": -1.1329771280288696, "label": 0.0}, {"pred": -0.94322270154953, "label": 0.0}, {"pred": 8.182953834533691, "label": 1.0}, {"pred": -0.94322270154953, "label": 1.0}, {"pred": 3.2885842323303223, "label": 1.0}, {"pred": -4.46294641494751, "label": 0.0}, {"pred": -0.9792708158493042, "label": 0.0}, {"pred": 3.822896957397461, "label": 1.0}, {"pred": -1.8717443943023682, "label": 0.0}, {"pred": -0.94322270154953, "label": 0.0}, {"pred": 8.366045951843262, "label": 1.0}, {"pred": -0.94322270154953, "label": 1.0}, {"pred": 7.455105781555176, "label": 1.0}, {"pred": -1.361657977104187, "label": 1.0}, {"pred": 2.631812334060669, "label": 1.0}, {"pred": 2.319370985031128, "label": 1.0}, {"pred": -3.2320010662078857, "label": 0.0}, {"pred": -0.5146999359130859, "label": 1.0}, {"pred": -0.94322270154953, "label": 0.0}, {"pred": 7.594902038574219, "label": 1.0}, {"pred": 3.5566954612731934, "label": 1.0}, {"pred": 1.4515318870544434, "label": 1.0}, {"pred": -0.94322270154953, "label": 0.0}, {"pred": 5.623931884765625, "label": 1.0}, {"pred": 2.283346176147461, "label": 1.0}, {"pred": 2.6207327842712402, "label": 1.0}, {"pred": 0.6767005920410156, "label": 0.0}, {"pred": 1.4779468774795532, "label": 0.0}, {"pred": -0.3948862850666046, "label": 0.0}, {"pred": -1.2129184007644653, "label": 0.0}, {"pred": -0.94322270154953, "label": 0.0}, {"pred": 8.195367813110352, "label": 1.0}, {"pred": 7.7748308181762695, "label": 0.0}, {"pred": 4.182348251342773, "label": 1.0}, {"pred": -0.94322270154953, "label": 0.0}, {"pred": 8.267129898071289, "label": 1.0}, {"pred": 1.3268805742263794, "label": 0.0}, {"pred": -2.2637319564819336, "label": 0.0}, {"pred": 6.017037391662598, "label": 1.0}, {"pred": -0.94322270154953, "label": 1.0}, {"pred": 8.279480934143066, "label": 1.0}, {"pred": 3.7376227378845215, "label": 1.0}, {"pred": 3.537707567214966, "label": 1.0}, {"pred": 2.5254549980163574, "label": 1.0}, {"pred": -1.4268559217453003, "label": 0.0}, {"pred": -0.94322270154953, "label": 0.0}, {"pred": 8.59853744506836, "label": 1.0}, {"pred": -0.94322270154953, "label": 1.0}, {"pred": 3.4714865684509277, "label": 1.0}, {"pred": 5.058969974517822, "label": 1.0}, {"pred": -4.46294641494751, "label": 0.0}, {"pred": 4.699585437774658, "label": 0.0}, {"pred": 3.4796693325042725, "label": 1.0}, {"pred": 0.9136394262313843, "label": 0.0}, {"pred": 0.8958767652511597, "label": 0.0}, {"pred": 0.8505266904830933, "label": 0.0}, {"pred": 0.49777188897132874, "label": 0.0}, {"pred": 2.0507519245147705, "label": 0.0}]
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d88396107bd3a18e099f616094deebc486df3754e86eb7b3c9574275c44086a9
3
+ size 501021053
train_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 5.0,
3
+ "train_loss": 0.12557823169776508,
4
+ "train_runtime": 2775.7723,
5
+ "train_samples": 2515,
6
+ "train_samples_per_second": 4.53,
7
+ "train_steps_per_second": 4.53
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,232 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 5.0,
5
+ "eval_steps": 2000,
6
+ "global_step": 12575,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2,
13
+ "learning_rate": 4.801192842942346e-05,
14
+ "loss": 0.2793,
15
+ "step": 500
16
+ },
17
+ {
18
+ "epoch": 0.4,
19
+ "learning_rate": 4.602385685884692e-05,
20
+ "loss": 0.167,
21
+ "step": 1000
22
+ },
23
+ {
24
+ "epoch": 0.6,
25
+ "learning_rate": 4.403578528827038e-05,
26
+ "loss": 0.1142,
27
+ "step": 1500
28
+ },
29
+ {
30
+ "epoch": 0.8,
31
+ "learning_rate": 4.204771371769384e-05,
32
+ "loss": 0.1172,
33
+ "step": 2000
34
+ },
35
+ {
36
+ "epoch": 0.8,
37
+ "eval_f1": 0.8002317832826308,
38
+ "eval_loss": 0.6091572739421863,
39
+ "eval_runtime": 11.3587,
40
+ "eval_samples_per_second": 7.571,
41
+ "eval_steps_per_second": 7.571,
42
+ "step": 2000
43
+ },
44
+ {
45
+ "epoch": 0.99,
46
+ "learning_rate": 4.00596421471173e-05,
47
+ "loss": 0.1046,
48
+ "step": 2500
49
+ },
50
+ {
51
+ "epoch": 1.19,
52
+ "learning_rate": 3.8071570576540756e-05,
53
+ "loss": 0.1103,
54
+ "step": 3000
55
+ },
56
+ {
57
+ "epoch": 1.39,
58
+ "learning_rate": 3.6083499005964215e-05,
59
+ "loss": 0.1216,
60
+ "step": 3500
61
+ },
62
+ {
63
+ "epoch": 1.59,
64
+ "learning_rate": 3.409542743538768e-05,
65
+ "loss": 0.1201,
66
+ "step": 4000
67
+ },
68
+ {
69
+ "epoch": 1.59,
70
+ "eval_f1": 0.797415004214667,
71
+ "eval_loss": 0.570012144717545,
72
+ "eval_runtime": 11.2237,
73
+ "eval_samples_per_second": 7.662,
74
+ "eval_steps_per_second": 7.662,
75
+ "step": 4000
76
+ },
77
+ {
78
+ "epoch": 1.79,
79
+ "learning_rate": 3.210735586481113e-05,
80
+ "loss": 0.1239,
81
+ "step": 4500
82
+ },
83
+ {
84
+ "epoch": 1.99,
85
+ "learning_rate": 3.0119284294234595e-05,
86
+ "loss": 0.1259,
87
+ "step": 5000
88
+ },
89
+ {
90
+ "epoch": 2.19,
91
+ "learning_rate": 2.813121272365805e-05,
92
+ "loss": 0.1254,
93
+ "step": 5500
94
+ },
95
+ {
96
+ "epoch": 2.39,
97
+ "learning_rate": 2.6143141153081513e-05,
98
+ "loss": 0.1738,
99
+ "step": 6000
100
+ },
101
+ {
102
+ "epoch": 2.39,
103
+ "eval_f1": 0.785323775968898,
104
+ "eval_loss": 1.3082878860688905,
105
+ "eval_runtime": 11.1911,
106
+ "eval_samples_per_second": 7.685,
107
+ "eval_steps_per_second": 7.685,
108
+ "step": 6000
109
+ },
110
+ {
111
+ "epoch": 2.58,
112
+ "learning_rate": 2.415506958250497e-05,
113
+ "loss": 0.1656,
114
+ "step": 6500
115
+ },
116
+ {
117
+ "epoch": 2.78,
118
+ "learning_rate": 2.216699801192843e-05,
119
+ "loss": 0.1316,
120
+ "step": 7000
121
+ },
122
+ {
123
+ "epoch": 2.98,
124
+ "learning_rate": 2.017892644135189e-05,
125
+ "loss": 0.1284,
126
+ "step": 7500
127
+ },
128
+ {
129
+ "epoch": 3.18,
130
+ "learning_rate": 1.8190854870775348e-05,
131
+ "loss": 0.1431,
132
+ "step": 8000
133
+ },
134
+ {
135
+ "epoch": 3.18,
136
+ "eval_f1": 0.7811158798283263,
137
+ "eval_loss": 0.6317664683518408,
138
+ "eval_runtime": 11.2067,
139
+ "eval_samples_per_second": 7.674,
140
+ "eval_steps_per_second": 7.674,
141
+ "step": 8000
142
+ },
143
+ {
144
+ "epoch": 3.38,
145
+ "learning_rate": 1.6202783300198807e-05,
146
+ "loss": 0.1353,
147
+ "step": 8500
148
+ },
149
+ {
150
+ "epoch": 3.58,
151
+ "learning_rate": 1.4214711729622268e-05,
152
+ "loss": 0.1013,
153
+ "step": 9000
154
+ },
155
+ {
156
+ "epoch": 3.78,
157
+ "learning_rate": 1.2226640159045727e-05,
158
+ "loss": 0.1174,
159
+ "step": 9500
160
+ },
161
+ {
162
+ "epoch": 3.98,
163
+ "learning_rate": 1.0238568588469186e-05,
164
+ "loss": 0.1213,
165
+ "step": 10000
166
+ },
167
+ {
168
+ "epoch": 3.98,
169
+ "eval_f1": 0.8029407524866656,
170
+ "eval_loss": 0.4704339896264236,
171
+ "eval_runtime": 11.4371,
172
+ "eval_samples_per_second": 7.519,
173
+ "eval_steps_per_second": 7.519,
174
+ "step": 10000
175
+ },
176
+ {
177
+ "epoch": 4.17,
178
+ "learning_rate": 8.250497017892645e-06,
179
+ "loss": 0.0851,
180
+ "step": 10500
181
+ },
182
+ {
183
+ "epoch": 4.37,
184
+ "learning_rate": 6.2624254473161034e-06,
185
+ "loss": 0.096,
186
+ "step": 11000
187
+ },
188
+ {
189
+ "epoch": 4.57,
190
+ "learning_rate": 4.274353876739562e-06,
191
+ "loss": 0.0727,
192
+ "step": 11500
193
+ },
194
+ {
195
+ "epoch": 4.77,
196
+ "learning_rate": 2.286282306163022e-06,
197
+ "loss": 0.0764,
198
+ "step": 12000
199
+ },
200
+ {
201
+ "epoch": 4.77,
202
+ "eval_f1": 0.8055235903337169,
203
+ "eval_loss": 0.4711939039551899,
204
+ "eval_runtime": 11.2703,
205
+ "eval_samples_per_second": 7.631,
206
+ "eval_steps_per_second": 7.631,
207
+ "step": 12000
208
+ },
209
+ {
210
+ "epoch": 4.97,
211
+ "learning_rate": 2.982107355864811e-07,
212
+ "loss": 0.09,
213
+ "step": 12500
214
+ },
215
+ {
216
+ "epoch": 5.0,
217
+ "step": 12575,
218
+ "total_flos": 1.933020837593007e+16,
219
+ "train_loss": 0.12557823169776508,
220
+ "train_runtime": 2775.7723,
221
+ "train_samples_per_second": 4.53,
222
+ "train_steps_per_second": 4.53
223
+ }
224
+ ],
225
+ "logging_steps": 500,
226
+ "max_steps": 12575,
227
+ "num_train_epochs": 5,
228
+ "save_steps": 500,
229
+ "total_flos": 1.933020837593007e+16,
230
+ "trial_name": null,
231
+ "trial_params": null
232
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ffb5d7519a50e593c970330f3045d40d04d40b6197d8bd380db01c78b6075ca4
3
+ size 4091