Nexspear commited on
Commit
29f8969
·
verified ·
1 Parent(s): 6ffce38

Training in progress, step 40, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b83a81b8e16a8124ae18d714dbbca2b4b5f8c330d762e05c51c7166bb92fec80
3
  size 588699796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6afc61d6e986a6f2e4246eb253042da888ed950ae1ff0cb11e73d9044abbadb
3
  size 588699796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e309b0c5f20ff43b2176507b02a3769210f48a74fb3cb9b2863f868c47b7cb80
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:998b7501e9d77c4711c7f8ec32d4f375bafc5702edb1ddbd9b96da2f20091681
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
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": 0.3023758099352052,
5
  "eval_steps": 5,
6
- "global_step": 35,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -148,6 +148,28 @@
148
  "eval_samples_per_second": 4.226,
149
  "eval_steps_per_second": 0.542,
150
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
151
  }
152
  ],
153
  "logging_steps": 3,
@@ -167,7 +189,7 @@
167
  "attributes": {}
168
  }
169
  },
170
- "total_flos": 1.8221437354298573e+17,
171
  "train_batch_size": 8,
172
  "trial_name": null,
173
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.34557235421166305,
5
  "eval_steps": 5,
6
+ "global_step": 40,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
148
  "eval_samples_per_second": 4.226,
149
  "eval_steps_per_second": 0.542,
150
  "step": 35
151
+ },
152
+ {
153
+ "epoch": 0.31101511879049676,
154
+ "grad_norm": NaN,
155
+ "learning_rate": 2.7300475013022663e-05,
156
+ "loss": 0.0,
157
+ "step": 36
158
+ },
159
+ {
160
+ "epoch": 0.3369330453563715,
161
+ "grad_norm": NaN,
162
+ "learning_rate": 1.7527597583490822e-05,
163
+ "loss": 0.0,
164
+ "step": 39
165
+ },
166
+ {
167
+ "epoch": 0.34557235421166305,
168
+ "eval_loss": NaN,
169
+ "eval_runtime": 46.189,
170
+ "eval_samples_per_second": 4.222,
171
+ "eval_steps_per_second": 0.541,
172
+ "step": 40
173
  }
174
  ],
175
  "logging_steps": 3,
 
189
  "attributes": {}
190
  }
191
  },
192
+ "total_flos": 2.0862225376660685e+17,
193
  "train_batch_size": 8,
194
  "trial_name": null,
195
  "trial_params": null