Hugging Face's logo

Spaces:
malavika4089
/
misinformation-truthteller
Sleeping

App Files Community
malavika4089 commited on
Commit
90472d7
·
verified ·
1 Parent(s): cf86f20

Model folder

Browse files
Files changed (20) hide show
  1. my_saved_model/checkpoint-5688/config.json +35 -0
  2. my_saved_model/checkpoint-5688/model.safetensors +3 -0
  3. my_saved_model/checkpoint-5688/optimizer.pt +3 -0
  4. my_saved_model/checkpoint-5688/rng_state.pth +3 -0
  5. my_saved_model/checkpoint-5688/scheduler.pt +3 -0
  6. my_saved_model/checkpoint-5688/trainer_state.json +191 -0
  7. my_saved_model/checkpoint-5688/training_args.bin +3 -0
  8. my_saved_model/checkpoint-6320/config.json +35 -0
  9. my_saved_model/checkpoint-6320/model.safetensors +3 -0
  10. my_saved_model/checkpoint-6320/optimizer.pt +3 -0
  11. my_saved_model/checkpoint-6320/rng_state.pth +3 -0
  12. my_saved_model/checkpoint-6320/scheduler.pt +3 -0
  13. my_saved_model/checkpoint-6320/trainer_state.json +207 -0
  14. my_saved_model/checkpoint-6320/training_args.bin +3 -0
  15. my_saved_model/runs/Dec25_14-09-59_34510bebc3b2/events.out.tfevents.1735135804.34510bebc3b2.1741.0 +3 -0
  16. my_saved_model/runs/Dec25_14-21-54_34510bebc3b2/events.out.tfevents.1735136515.34510bebc3b2.1741.1 +3 -0
  17. my_saved_model/runs/Dec25_14-23-11_34510bebc3b2/events.out.tfevents.1735136592.34510bebc3b2.1741.2 +3 -0
  18. my_saved_model/runs/Dec25_14-30-12_34510bebc3b2/events.out.tfevents.1735137013.34510bebc3b2.1741.3 +3 -0
  19. my_saved_model/runs/Dec25_14-46-09_34510bebc3b2/events.out.tfevents.1735137971.34510bebc3b2.19477.0 +3 -0
  20. my_saved_model/runs/Dec25_14-46-42_34510bebc3b2/events.out.tfevents.1735138002.34510bebc3b2.19477.1 +3 -0
my_saved_model/checkpoint-5688/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "sst-2",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "NEGATIVE": 0,
19
+ "POSITIVE": 1
20
+ },
21
+ "max_position_embeddings": 512,
22
+ "model_type": "distilbert",
23
+ "n_heads": 12,
24
+ "n_layers": 6,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.47.1",
34
+ "vocab_size": 30522
35
+ }
my_saved_model/checkpoint-5688/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7c6f0fd04770e958a2d37b6c3d7c3eed1433b68f6919e96a1eecde5690fb2ce
3
+ size 267832560
my_saved_model/checkpoint-5688/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d34b0885a04f02e1cc0319c55cdd793bf2eaba0a49d021cf056870b5ed28f34f
3
+ size 15132
my_saved_model/checkpoint-5688/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3662d305608b2f13f14b9b9619078b753dc930ab7819eaa6682d0ce1227e409
3
+ size 14244
my_saved_model/checkpoint-5688/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eae61e626b5bd02edeb004b9321474f283b11385ae5802a683afdade457d5c89
3
+ size 1064
my_saved_model/checkpoint-5688/trainer_state.json ADDED
@@ -0,0 +1,191 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4109877347946167,
3
+ "best_model_checkpoint": "./my_saved_model/checkpoint-5688",
4
+ "epoch": 9.0,
5
+ "eval_steps": 500,
6
+ "global_step": 5688,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7911392405063291,
13
+ "grad_norm": 2.325883388519287,
14
+ "learning_rate": 4.604430379746836e-05,
15
+ "loss": 1.123,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.688195991091314,
21
+ "eval_loss": 0.6270885467529297,
22
+ "eval_runtime": 70.865,
23
+ "eval_samples_per_second": 63.36,
24
+ "eval_steps_per_second": 1.002,
25
+ "step": 632
26
+ },
27
+ {
28
+ "epoch": 1.5822784810126582,
29
+ "grad_norm": 1.8189690113067627,
30
+ "learning_rate": 4.208860759493671e-05,
31
+ "loss": 0.6186,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8383073496659242,
37
+ "eval_loss": 0.5550462007522583,
38
+ "eval_runtime": 70.8726,
39
+ "eval_samples_per_second": 63.353,
40
+ "eval_steps_per_second": 1.002,
41
+ "step": 1264
42
+ },
43
+ {
44
+ "epoch": 2.3734177215189876,
45
+ "grad_norm": 1.0061662197113037,
46
+ "learning_rate": 3.813291139240506e-05,
47
+ "loss": 0.5672,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8472160356347439,
53
+ "eval_loss": 0.5077998042106628,
54
+ "eval_runtime": 71.0525,
55
+ "eval_samples_per_second": 63.193,
56
+ "eval_steps_per_second": 0.999,
57
+ "step": 1896
58
+ },
59
+ {
60
+ "epoch": 3.1645569620253164,
61
+ "grad_norm": 0.8065588474273682,
62
+ "learning_rate": 3.4177215189873416e-05,
63
+ "loss": 0.5307,
64
+ "step": 2000
65
+ },
66
+ {
67
+ "epoch": 3.9556962025316453,
68
+ "grad_norm": 1.4700500965118408,
69
+ "learning_rate": 3.0221518987341774e-05,
70
+ "loss": 0.5023,
71
+ "step": 2500
72
+ },
73
+ {
74
+ "epoch": 4.0,
75
+ "eval_accuracy": 0.8688195991091314,
76
+ "eval_loss": 0.47517454624176025,
77
+ "eval_runtime": 70.885,
78
+ "eval_samples_per_second": 63.342,
79
+ "eval_steps_per_second": 1.002,
80
+ "step": 2528
81
+ },
82
+ {
83
+ "epoch": 4.746835443037975,
84
+ "grad_norm": 0.5362122654914856,
85
+ "learning_rate": 2.626582278481013e-05,
86
+ "loss": 0.4817,
87
+ "step": 3000
88
+ },
89
+ {
90
+ "epoch": 5.0,
91
+ "eval_accuracy": 0.8748329621380846,
92
+ "eval_loss": 0.45159268379211426,
93
+ "eval_runtime": 71.0334,
94
+ "eval_samples_per_second": 63.21,
95
+ "eval_steps_per_second": 1.0,
96
+ "step": 3160
97
+ },
98
+ {
99
+ "epoch": 5.537974683544304,
100
+ "grad_norm": 0.7847274541854858,
101
+ "learning_rate": 2.231012658227848e-05,
102
+ "loss": 0.4665,
103
+ "step": 3500
104
+ },
105
+ {
106
+ "epoch": 6.0,
107
+ "eval_accuracy": 0.8792873051224944,
108
+ "eval_loss": 0.4351290166378021,
109
+ "eval_runtime": 70.9077,
110
+ "eval_samples_per_second": 63.322,
111
+ "eval_steps_per_second": 1.001,
112
+ "step": 3792
113
+ },
114
+ {
115
+ "epoch": 6.329113924050633,
116
+ "grad_norm": 0.6061320304870605,
117
+ "learning_rate": 1.8354430379746836e-05,
118
+ "loss": 0.4567,
119
+ "step": 4000
120
+ },
121
+ {
122
+ "epoch": 7.0,
123
+ "eval_accuracy": 0.8797327394209354,
124
+ "eval_loss": 0.422820121049881,
125
+ "eval_runtime": 71.2032,
126
+ "eval_samples_per_second": 63.059,
127
+ "eval_steps_per_second": 0.997,
128
+ "step": 4424
129
+ },
130
+ {
131
+ "epoch": 7.120253164556962,
132
+ "grad_norm": 1.0778601169586182,
133
+ "learning_rate": 1.439873417721519e-05,
134
+ "loss": 0.4469,
135
+ "step": 4500
136
+ },
137
+ {
138
+ "epoch": 7.911392405063291,
139
+ "grad_norm": 1.6876882314682007,
140
+ "learning_rate": 1.0443037974683544e-05,
141
+ "loss": 0.4404,
142
+ "step": 5000
143
+ },
144
+ {
145
+ "epoch": 8.0,
146
+ "eval_accuracy": 0.8832962138084632,
147
+ "eval_loss": 0.4156254827976227,
148
+ "eval_runtime": 70.8877,
149
+ "eval_samples_per_second": 63.34,
150
+ "eval_steps_per_second": 1.002,
151
+ "step": 5056
152
+ },
153
+ {
154
+ "epoch": 8.70253164556962,
155
+ "grad_norm": 0.5833732485771179,
156
+ "learning_rate": 6.487341772151899e-06,
157
+ "loss": 0.436,
158
+ "step": 5500
159
+ },
160
+ {
161
+ "epoch": 9.0,
162
+ "eval_accuracy": 0.8830734966592427,
163
+ "eval_loss": 0.4109877347946167,
164
+ "eval_runtime": 71.1738,
165
+ "eval_samples_per_second": 63.085,
166
+ "eval_steps_per_second": 0.998,
167
+ "step": 5688
168
+ }
169
+ ],
170
+ "logging_steps": 500,
171
+ "max_steps": 6320,
172
+ "num_input_tokens_seen": 0,
173
+ "num_train_epochs": 10,
174
+ "save_steps": 10000,
175
+ "stateful_callbacks": {
176
+ "TrainerControl": {
177
+ "args": {
178
+ "should_epoch_stop": false,
179
+ "should_evaluate": false,
180
+ "should_log": false,
181
+ "should_save": true,
182
+ "should_training_stop": false
183
+ },
184
+ "attributes": {}
185
+ }
186
+ },
187
+ "total_flos": 4.817468380402483e+16,
188
+ "train_batch_size": 64,
189
+ "trial_name": null,
190
+ "trial_params": null
191
+ }
my_saved_model/checkpoint-5688/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9162c452e06b5bc1fa2ff33c6cc7bc1aa032599e0106cccaf2dd0f3c53f5c8e2
3
+ size 5304
my_saved_model/checkpoint-6320/config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "distilbert-base-uncased-finetuned-sst-2-english",
3
+ "activation": "gelu",
4
+ "architectures": [
5
+ "DistilBertForSequenceClassification"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "dim": 768,
9
+ "dropout": 0.1,
10
+ "finetuning_task": "sst-2",
11
+ "hidden_dim": 3072,
12
+ "id2label": {
13
+ "0": "NEGATIVE",
14
+ "1": "POSITIVE"
15
+ },
16
+ "initializer_range": 0.02,
17
+ "label2id": {
18
+ "NEGATIVE": 0,
19
+ "POSITIVE": 1
20
+ },
21
+ "max_position_embeddings": 512,
22
+ "model_type": "distilbert",
23
+ "n_heads": 12,
24
+ "n_layers": 6,
25
+ "output_past": true,
26
+ "pad_token_id": 0,
27
+ "problem_type": "single_label_classification",
28
+ "qa_dropout": 0.1,
29
+ "seq_classif_dropout": 0.2,
30
+ "sinusoidal_pos_embds": false,
31
+ "tie_weights_": true,
32
+ "torch_dtype": "float32",
33
+ "transformers_version": "4.47.1",
34
+ "vocab_size": 30522
35
+ }
my_saved_model/checkpoint-6320/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:810a4b3c50afe2d4e174286595adbae4790b88ac678c8ed86048261866d26228
3
+ size 267832560
my_saved_model/checkpoint-6320/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a264c2957ccc68bd2e329cf97ae19f2830a3d37a6099b405bbe841752704d5f
3
+ size 15132
my_saved_model/checkpoint-6320/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f81a08e8885bed619dc00b851d6b0585f5877872ab58ab65a0405208132e0b5f
3
+ size 14244
my_saved_model/checkpoint-6320/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab9dfd73a49e92bbc1fbd012b4ca0aad191e873db2dab452f4becbd6400bcaaf
3
+ size 1064
my_saved_model/checkpoint-6320/trainer_state.json ADDED
@@ -0,0 +1,207 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.4097345769405365,
3
+ "best_model_checkpoint": "./my_saved_model/checkpoint-6320",
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 6320,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.7911392405063291,
13
+ "grad_norm": 2.325883388519287,
14
+ "learning_rate": 4.604430379746836e-05,
15
+ "loss": 1.123,
16
+ "step": 500
17
+ },
18
+ {
19
+ "epoch": 1.0,
20
+ "eval_accuracy": 0.688195991091314,
21
+ "eval_loss": 0.6270885467529297,
22
+ "eval_runtime": 70.865,
23
+ "eval_samples_per_second": 63.36,
24
+ "eval_steps_per_second": 1.002,
25
+ "step": 632
26
+ },
27
+ {
28
+ "epoch": 1.5822784810126582,
29
+ "grad_norm": 1.8189690113067627,
30
+ "learning_rate": 4.208860759493671e-05,
31
+ "loss": 0.6186,
32
+ "step": 1000
33
+ },
34
+ {
35
+ "epoch": 2.0,
36
+ "eval_accuracy": 0.8383073496659242,
37
+ "eval_loss": 0.5550462007522583,
38
+ "eval_runtime": 70.8726,
39
+ "eval_samples_per_second": 63.353,
40
+ "eval_steps_per_second": 1.002,
41
+ "step": 1264
42
+ },
43
+ {
44
+ "epoch": 2.3734177215189876,
45
+ "grad_norm": 1.0061662197113037,
46
+ "learning_rate": 3.813291139240506e-05,
47
+ "loss": 0.5672,
48
+ "step": 1500
49
+ },
50
+ {
51
+ "epoch": 3.0,
52
+ "eval_accuracy": 0.8472160356347439,
53
+ "eval_loss": 0.5077998042106628,
54
+ "eval_runtime": 71.0525,
55
+ "eval_samples_per_second": 63.193,
56
+ "eval_steps_per_second": 0.999,
57
+ "step": 1896
58
+ },
59
+ {
60
+ "epoch": 3.1645569620253164,
61
+ "grad_norm": 0.8065588474273682,
62
+ "learning_rate": 3.4177215189873416e-05,
63
+ "loss": 0.5307,
64
+ "step": 2000
65
+ },
66
+ {
67
+ "epoch": 3.9556962025316453,
68
+ "grad_norm": 1.4700500965118408,
69
+ "learning_rate": 3.0221518987341774e-05,
70
+ "loss": 0.5023,
71
+ "step": 2500
72
+ },
73
+ {
74
+ "epoch": 4.0,
75
+ "eval_accuracy": 0.8688195991091314,
76
+ "eval_loss": 0.47517454624176025,
77
+ "eval_runtime": 70.885,
78
+ "eval_samples_per_second": 63.342,
79
+ "eval_steps_per_second": 1.002,
80
+ "step": 2528
81
+ },
82
+ {
83
+ "epoch": 4.746835443037975,
84
+ "grad_norm": 0.5362122654914856,
85
+ "learning_rate": 2.626582278481013e-05,
86
+ "loss": 0.4817,
87
+ "step": 3000
88
+ },
89
+ {
90
+ "epoch": 5.0,
91
+ "eval_accuracy": 0.8748329621380846,
92
+ "eval_loss": 0.45159268379211426,
93
+ "eval_runtime": 71.0334,
94
+ "eval_samples_per_second": 63.21,
95
+ "eval_steps_per_second": 1.0,
96
+ "step": 3160
97
+ },
98
+ {
99
+ "epoch": 5.537974683544304,
100
+ "grad_norm": 0.7847274541854858,
101
+ "learning_rate": 2.231012658227848e-05,
102
+ "loss": 0.4665,
103
+ "step": 3500
104
+ },
105
+ {
106
+ "epoch": 6.0,
107
+ "eval_accuracy": 0.8792873051224944,
108
+ "eval_loss": 0.4351290166378021,
109
+ "eval_runtime": 70.9077,
110
+ "eval_samples_per_second": 63.322,
111
+ "eval_steps_per_second": 1.001,
112
+ "step": 3792
113
+ },
114
+ {
115
+ "epoch": 6.329113924050633,
116
+ "grad_norm": 0.6061320304870605,
117
+ "learning_rate": 1.8354430379746836e-05,
118
+ "loss": 0.4567,
119
+ "step": 4000
120
+ },
121
+ {
122
+ "epoch": 7.0,
123
+ "eval_accuracy": 0.8797327394209354,
124
+ "eval_loss": 0.422820121049881,
125
+ "eval_runtime": 71.2032,
126
+ "eval_samples_per_second": 63.059,
127
+ "eval_steps_per_second": 0.997,
128
+ "step": 4424
129
+ },
130
+ {
131
+ "epoch": 7.120253164556962,
132
+ "grad_norm": 1.0778601169586182,
133
+ "learning_rate": 1.439873417721519e-05,
134
+ "loss": 0.4469,
135
+ "step": 4500
136
+ },
137
+ {
138
+ "epoch": 7.911392405063291,
139
+ "grad_norm": 1.6876882314682007,
140
+ "learning_rate": 1.0443037974683544e-05,
141
+ "loss": 0.4404,
142
+ "step": 5000
143
+ },
144
+ {
145
+ "epoch": 8.0,
146
+ "eval_accuracy": 0.8832962138084632,
147
+ "eval_loss": 0.4156254827976227,
148
+ "eval_runtime": 70.8877,
149
+ "eval_samples_per_second": 63.34,
150
+ "eval_steps_per_second": 1.002,
151
+ "step": 5056
152
+ },
153
+ {
154
+ "epoch": 8.70253164556962,
155
+ "grad_norm": 0.5833732485771179,
156
+ "learning_rate": 6.487341772151899e-06,
157
+ "loss": 0.436,
158
+ "step": 5500
159
+ },
160
+ {
161
+ "epoch": 9.0,
162
+ "eval_accuracy": 0.8830734966592427,
163
+ "eval_loss": 0.4109877347946167,
164
+ "eval_runtime": 71.1738,
165
+ "eval_samples_per_second": 63.085,
166
+ "eval_steps_per_second": 0.998,
167
+ "step": 5688
168
+ },
169
+ {
170
+ "epoch": 9.49367088607595,
171
+ "grad_norm": 0.5988475680351257,
172
+ "learning_rate": 2.531645569620253e-06,
173
+ "loss": 0.4309,
174
+ "step": 6000
175
+ },
176
+ {
177
+ "epoch": 10.0,
178
+ "eval_accuracy": 0.8832962138084632,
179
+ "eval_loss": 0.4097345769405365,
180
+ "eval_runtime": 71.362,
181
+ "eval_samples_per_second": 62.919,
182
+ "eval_steps_per_second": 0.995,
183
+ "step": 6320
184
+ }
185
+ ],
186
+ "logging_steps": 500,
187
+ "max_steps": 6320,
188
+ "num_input_tokens_seen": 0,
189
+ "num_train_epochs": 10,
190
+ "save_steps": 10000,
191
+ "stateful_callbacks": {
192
+ "TrainerControl": {
193
+ "args": {
194
+ "should_epoch_stop": false,
195
+ "should_evaluate": false,
196
+ "should_log": false,
197
+ "should_save": true,
198
+ "should_training_stop": true
199
+ },
200
+ "attributes": {}
201
+ }
202
+ },
203
+ "total_flos": 5.352742644891648e+16,
204
+ "train_batch_size": 64,
205
+ "trial_name": null,
206
+ "trial_params": null
207
+ }
my_saved_model/checkpoint-6320/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9162c452e06b5bc1fa2ff33c6cc7bc1aa032599e0106cccaf2dd0f3c53f5c8e2
3
+ size 5304
my_saved_model/runs/Dec25_14-09-59_34510bebc3b2/events.out.tfevents.1735135804.34510bebc3b2.1741.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a281b019ba592858399225def41448a675476c108cc5b51d3a2d60fbd43ac0bb
3
+ size 5149
my_saved_model/runs/Dec25_14-21-54_34510bebc3b2/events.out.tfevents.1735136515.34510bebc3b2.1741.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba84455597dcfec110f9455d464187b33dccd3d4795ed07cb50dd09996617d40
3
+ size 5136
my_saved_model/runs/Dec25_14-23-11_34510bebc3b2/events.out.tfevents.1735136592.34510bebc3b2.1741.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21176277439c9345287055b68c44c64b7e5097715d84ce2e8345cb3f3fd978e5
3
+ size 5133
my_saved_model/runs/Dec25_14-30-12_34510bebc3b2/events.out.tfevents.1735137013.34510bebc3b2.1741.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9bbfa45e1033a1789ed48c14722a111e351ea0e2173250528393125f5f8c729
3
+ size 5133
my_saved_model/runs/Dec25_14-46-09_34510bebc3b2/events.out.tfevents.1735137971.34510bebc3b2.19477.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4004bc0b2f7b6c6bedd5d3c41eea1dfbea9d19c2aaa1e4541824cb098da7e18d
3
+ size 5146
my_saved_model/runs/Dec25_14-46-42_34510bebc3b2/events.out.tfevents.1735138002.34510bebc3b2.19477.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19b0fe07a396d4f322cf39090f4943c6d31ec5b29df2a74af98c1196a34e9c9e
3
+ size 11249