Hugging Face's logo

Kenny008
/
model14-finetuned-SLT-subset

TensorBoard
Safetensors
videomae
Generated from Trainer
Model card Files Metrics Community
Kenny008 commited on
Commit
24b362e
·
verified ·
1 Parent(s): f2ea299

Model save

Browse files
Files changed (5) hide show
  1. README.md +2 -2
  2. all_results.json +8 -0
  3. runs/Sep08_14-17-29_d0b9a74a01d1/events.out.tfevents.1725806629.d0b9a74a01d1.1785.2 +3 -0
  4. test_results.json +8 -0
  5. trainer_state.json +197 -0
README.md CHANGED
@@ -15,8 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model was trained from scratch on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 3.6432
19
- - Accuracy: 0.05
20
 
21
  ## Model description
22
 
 
15
 
16
  This model was trained from scratch on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 3.5821
19
+ - Accuracy: 0.0
20
 
21
  ## Model description
22
 
all_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.3333333333333335,
3
+ "eval_accuracy": 0.0,
4
+ "eval_loss": 3.5820634365081787,
5
+ "eval_runtime": 2.7763,
6
+ "eval_samples_per_second": 0.36,
7
+ "eval_steps_per_second": 0.36
8
+ }
runs/Sep08_14-17-29_d0b9a74a01d1/events.out.tfevents.1725806629.d0b9a74a01d1.1785.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9f5ed6e9c167fed9ac3f404a99d0472afecdf63c3206f8424a0cb3ae834fcd8
3
+ size 411
test_results.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 2.3333333333333335,
3
+ "eval_accuracy": 0.0,
4
+ "eval_loss": 3.5820634365081787,
5
+ "eval_runtime": 2.7763,
6
+ "eval_samples_per_second": 0.36,
7
+ "eval_steps_per_second": 0.36
8
+ }
trainer_state.json ADDED
@@ -0,0 +1,197 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.05,
3
+ "best_model_checkpoint": "model14-finetuned-SLT-subset/checkpoint-59",
4
+ "epoch": 2.3333333333333335,
5
+ "eval_steps": 500,
6
+ "global_step": 177,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.05649717514124294,
13
+ "grad_norm": 15.659302711486816,
14
+ "learning_rate": 2.777777777777778e-05,
15
+ "loss": 3.8577,
16
+ "step": 10
17
+ },
18
+ {
19
+ "epoch": 0.11299435028248588,
20
+ "grad_norm": 13.975533485412598,
21
+ "learning_rate": 4.937106918238994e-05,
22
+ "loss": 3.6714,
23
+ "step": 20
24
+ },
25
+ {
26
+ "epoch": 0.1694915254237288,
27
+ "grad_norm": 13.702733039855957,
28
+ "learning_rate": 4.6226415094339625e-05,
29
+ "loss": 3.996,
30
+ "step": 30
31
+ },
32
+ {
33
+ "epoch": 0.22598870056497175,
34
+ "grad_norm": 13.188166618347168,
35
+ "learning_rate": 4.308176100628931e-05,
36
+ "loss": 4.017,
37
+ "step": 40
38
+ },
39
+ {
40
+ "epoch": 0.2824858757062147,
41
+ "grad_norm": 12.505217552185059,
42
+ "learning_rate": 3.9937106918239e-05,
43
+ "loss": 3.9073,
44
+ "step": 50
45
+ },
46
+ {
47
+ "epoch": 0.3333333333333333,
48
+ "eval_accuracy": 0.05,
49
+ "eval_loss": 3.707028865814209,
50
+ "eval_runtime": 86.3138,
51
+ "eval_samples_per_second": 0.463,
52
+ "eval_steps_per_second": 0.232,
53
+ "step": 59
54
+ },
55
+ {
56
+ "epoch": 1.0056497175141244,
57
+ "grad_norm": 12.231797218322754,
58
+ "learning_rate": 3.679245283018868e-05,
59
+ "loss": 3.906,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 1.0621468926553672,
64
+ "grad_norm": 11.97706413269043,
65
+ "learning_rate": 3.364779874213837e-05,
66
+ "loss": 3.8198,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 1.11864406779661,
71
+ "grad_norm": 11.600285530090332,
72
+ "learning_rate": 3.050314465408805e-05,
73
+ "loss": 3.7922,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 1.1751412429378532,
78
+ "grad_norm": 11.922569274902344,
79
+ "learning_rate": 2.7358490566037738e-05,
80
+ "loss": 3.8627,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 1.231638418079096,
85
+ "grad_norm": 11.862650871276855,
86
+ "learning_rate": 2.421383647798742e-05,
87
+ "loss": 3.7829,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 1.288135593220339,
92
+ "grad_norm": 12.290817260742188,
93
+ "learning_rate": 2.106918238993711e-05,
94
+ "loss": 3.8434,
95
+ "step": 110
96
+ },
97
+ {
98
+ "epoch": 1.3333333333333333,
99
+ "eval_accuracy": 0.05,
100
+ "eval_loss": 3.654296875,
101
+ "eval_runtime": 86.7853,
102
+ "eval_samples_per_second": 0.461,
103
+ "eval_steps_per_second": 0.23,
104
+ "step": 118
105
+ },
106
+ {
107
+ "epoch": 2.0112994350282487,
108
+ "grad_norm": 11.525404930114746,
109
+ "learning_rate": 1.7924528301886792e-05,
110
+ "loss": 3.8266,
111
+ "step": 120
112
+ },
113
+ {
114
+ "epoch": 2.0677966101694913,
115
+ "grad_norm": 11.840191841125488,
116
+ "learning_rate": 1.4779874213836479e-05,
117
+ "loss": 3.6656,
118
+ "step": 130
119
+ },
120
+ {
121
+ "epoch": 2.1242937853107344,
122
+ "grad_norm": 11.563905715942383,
123
+ "learning_rate": 1.1635220125786164e-05,
124
+ "loss": 3.6074,
125
+ "step": 140
126
+ },
127
+ {
128
+ "epoch": 2.1807909604519775,
129
+ "grad_norm": 11.315864562988281,
130
+ "learning_rate": 8.49056603773585e-06,
131
+ "loss": 3.7573,
132
+ "step": 150
133
+ },
134
+ {
135
+ "epoch": 2.23728813559322,
136
+ "grad_norm": 11.722553253173828,
137
+ "learning_rate": 5.345911949685535e-06,
138
+ "loss": 3.7128,
139
+ "step": 160
140
+ },
141
+ {
142
+ "epoch": 2.2937853107344632,
143
+ "grad_norm": 11.536542892456055,
144
+ "learning_rate": 2.20125786163522e-06,
145
+ "loss": 3.6998,
146
+ "step": 170
147
+ },
148
+ {
149
+ "epoch": 2.3333333333333335,
150
+ "eval_accuracy": 0.05,
151
+ "eval_loss": 3.643190860748291,
152
+ "eval_runtime": 87.9928,
153
+ "eval_samples_per_second": 0.455,
154
+ "eval_steps_per_second": 0.227,
155
+ "step": 177
156
+ },
157
+ {
158
+ "epoch": 2.3333333333333335,
159
+ "step": 177,
160
+ "total_flos": 4.412563510866739e+17,
161
+ "train_loss": 3.8058138055316473,
162
+ "train_runtime": 1305.8999,
163
+ "train_samples_per_second": 0.271,
164
+ "train_steps_per_second": 0.136
165
+ },
166
+ {
167
+ "epoch": 2.3333333333333335,
168
+ "eval_accuracy": 0.0,
169
+ "eval_loss": 3.5820634365081787,
170
+ "eval_runtime": 2.7763,
171
+ "eval_samples_per_second": 0.36,
172
+ "eval_steps_per_second": 0.36,
173
+ "step": 177
174
+ }
175
+ ],
176
+ "logging_steps": 10,
177
+ "max_steps": 177,
178
+ "num_input_tokens_seen": 0,
179
+ "num_train_epochs": 9223372036854775807,
180
+ "save_steps": 500,
181
+ "stateful_callbacks": {
182
+ "TrainerControl": {
183
+ "args": {
184
+ "should_epoch_stop": false,
185
+ "should_evaluate": false,
186
+ "should_log": false,
187
+ "should_save": true,
188
+ "should_training_stop": true
189
+ },
190
+ "attributes": {}
191
+ }
192
+ },
193
+ "total_flos": 4.412563510866739e+17,
194
+ "train_batch_size": 2,
195
+ "trial_name": null,
196
+ "trial_params": null
197
+ }