Nexspear commited on
Commit
d79f0ad
·
verified ·
1 Parent(s): 2385b56

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:800397f46f49cc1d9a60b7efbd090a7b4831db4ef2d92075e339a7555b502643
3
  size 671149168
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc342d1a5074b986eef2742d8c9b332d8717aec88aaf0697335ac22c5f02a1d3
3
  size 671149168
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ccaddec401f25d7a60e95ed6cca5551e7acc037bbe1e1705f974af92e0f5d650
3
  size 341314196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a847760654b3735cc001c841b3f734fb81ed6d2c65fb1a9b5fc20eb776475eb
3
  size 341314196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c8969108774412257f3bec7d27805c014858246b2ae2cafcc98af96054f2f98
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68ad396e7290d38bd554625382b7db985ea23706407cb5f754ffd358d6a145c5
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ec0bb6efeeb25000ef7426abb9d88265daa212fa2a170e1fb3f58996efa27f6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
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": 0.5373134328358209,
5
  "eval_steps": 5,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -192,6 +192,21 @@
192
  "eval_samples_per_second": 4.167,
193
  "eval_steps_per_second": 0.532,
194
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
195
  }
196
  ],
197
  "logging_steps": 3,
@@ -206,12 +221,12 @@
206
  "should_evaluate": false,
207
  "should_log": false,
208
  "should_save": true,
209
- "should_training_stop": false
210
  },
211
  "attributes": {}
212
  }
213
  },
214
- "total_flos": 1.2878982080888832e+17,
215
  "train_batch_size": 8,
216
  "trial_name": null,
217
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.5970149253731343,
5
  "eval_steps": 5,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
192
  "eval_samples_per_second": 4.167,
193
  "eval_steps_per_second": 0.532,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.573134328358209,
198
+ "grad_norm": 2.71305251121521,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 5.3342,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.5970149253731343,
205
+ "eval_loss": 1.3329530954360962,
206
+ "eval_runtime": 33.8044,
207
+ "eval_samples_per_second": 4.171,
208
+ "eval_steps_per_second": 0.532,
209
+ "step": 50
210
  }
211
  ],
212
  "logging_steps": 3,
 
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
+ "should_training_stop": true
225
  },
226
  "attributes": {}
227
  }
228
  },
229
+ "total_flos": 1.430998008987648e+17,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null