ardaspear commited on
Commit
19c9787
·
verified ·
1 Parent(s): c80ed8d

Training in progress, step 45, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9ca2f6171dc7730ecf8c08fbc975040570ae9017ca86af36aec82bf0683c124
3
  size 150486964
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:15c226711d5a4255357daa82ae86f564589e74707047889b9b59b0b6649f63e7
3
  size 150486964
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5f4f0e8dad369bc7bb59d5e7f497c51f10df0b55006fce373720fb706b727122
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05de074c39f85666a0a560cfe9d1a3cb4d0dea668ee250ea7d270dcd0130b7ff
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.3185840707964602,
5
  "eval_steps": 9,
6
- "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -131,6 +131,35 @@
131
  "eval_samples_per_second": 36.177,
132
  "eval_steps_per_second": 4.57,
133
  "step": 36
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
134
  }
135
  ],
136
  "logging_steps": 3,
@@ -150,7 +179,7 @@
150
  "attributes": {}
151
  }
152
  },
153
- "total_flos": 9797210304675840.0,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.39823008849557523,
5
  "eval_steps": 9,
6
+ "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
131
  "eval_samples_per_second": 36.177,
132
  "eval_steps_per_second": 4.57,
133
  "step": 36
134
+ },
135
+ {
136
+ "epoch": 0.34513274336283184,
137
+ "grad_norm": NaN,
138
+ "learning_rate": 7.649596321166024e-05,
139
+ "loss": 0.0,
140
+ "step": 39
141
+ },
142
+ {
143
+ "epoch": 0.37168141592920356,
144
+ "grad_norm": NaN,
145
+ "learning_rate": 7.191855733945387e-05,
146
+ "loss": 0.0,
147
+ "step": 42
148
+ },
149
+ {
150
+ "epoch": 0.39823008849557523,
151
+ "grad_norm": NaN,
152
+ "learning_rate": 6.710100716628344e-05,
153
+ "loss": 0.0,
154
+ "step": 45
155
+ },
156
+ {
157
+ "epoch": 0.39823008849557523,
158
+ "eval_loss": NaN,
159
+ "eval_runtime": 5.2469,
160
+ "eval_samples_per_second": 36.212,
161
+ "eval_steps_per_second": 4.574,
162
+ "step": 45
163
  }
164
  ],
165
  "logging_steps": 3,
 
179
  "attributes": {}
180
  }
181
  },
182
+ "total_flos": 1.22465128808448e+16,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null