mayaram commited on
Commit
0e32756
·
1 Parent(s): bfc99b8

Upload 6 files

Browse files
Files changed (3) hide show
  1. rng_state.pth +1 -1
  2. scheduler.pt +1 -1
  3. trainer_state.json +3 -53
rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4387073d5cd79b938534425d0aa69cce8f595db74ecffbf675f6722c658c7047
3
  size 13553
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a24023cc6c46dd166b1fdbd0c2279c2ac131964234801d28f0e5db34de8a7535
3
  size 13553
scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cde0284e691744cab21aa0a7258284d8a47c7dd85f1dc68f2c3313211592bd3f
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:620a2c6044c4ec2a4dcd175f5fe80f8acb66bb949178847e0257327ae79e1185
3
  size 627
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": 3.395401954650879,
3
  "best_model_checkpoint": "/content/drive/MyDrive/ICModel/arabertVit/checkpoint-726",
4
- "epoch": 3.0,
5
- "global_step": 1089,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -106,61 +106,11 @@
106
  "eval_samples_per_second": 5.563,
107
  "eval_steps_per_second": 0.088,
108
  "step": 726
109
- },
110
- {
111
- "epoch": 2.07,
112
- "learning_rate": 2.4173553719008264e-05,
113
- "loss": 3.0104,
114
- "step": 750
115
- },
116
- {
117
- "epoch": 2.2,
118
- "learning_rate": 2.2451790633608817e-05,
119
- "loss": 2.8998,
120
- "step": 800
121
- },
122
- {
123
- "epoch": 2.34,
124
- "learning_rate": 2.073002754820937e-05,
125
- "loss": 2.8714,
126
- "step": 850
127
- },
128
- {
129
- "epoch": 2.48,
130
- "learning_rate": 1.900826446280992e-05,
131
- "loss": 2.8648,
132
- "step": 900
133
- },
134
- {
135
- "epoch": 2.62,
136
- "learning_rate": 1.728650137741047e-05,
137
- "loss": 2.8893,
138
- "step": 950
139
- },
140
- {
141
- "epoch": 2.75,
142
- "learning_rate": 1.5564738292011018e-05,
143
- "loss": 2.8479,
144
- "step": 1000
145
- },
146
- {
147
- "epoch": 2.89,
148
- "learning_rate": 1.3842975206611573e-05,
149
- "loss": 2.8732,
150
- "step": 1050
151
- },
152
- {
153
- "epoch": 3.0,
154
- "eval_loss": 3.4181885719299316,
155
- "eval_runtime": 474.579,
156
- "eval_samples_per_second": 5.441,
157
- "eval_steps_per_second": 0.086,
158
- "step": 1089
159
  }
160
  ],
161
  "max_steps": 1452,
162
  "num_train_epochs": 4,
163
- "total_flos": 1.2617826435024814e+19,
164
  "trial_name": null,
165
  "trial_params": null
166
  }
 
1
  {
2
  "best_metric": 3.395401954650879,
3
  "best_model_checkpoint": "/content/drive/MyDrive/ICModel/arabertVit/checkpoint-726",
4
+ "epoch": 2.0,
5
+ "global_step": 726,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
106
  "eval_samples_per_second": 5.563,
107
  "eval_steps_per_second": 0.088,
108
  "step": 726
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
109
  }
110
  ],
111
  "max_steps": 1452,
112
  "num_train_epochs": 4,
113
+ "total_flos": 8.411884290016543e+18,
114
  "trial_name": null,
115
  "trial_params": null
116
  }