ardaspear commited on
Commit
9e0ec70
1 Parent(s): 3068154

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:e558c584b1ab69f81f18d064d18a1350b80e85cd5c8df719812a5c4778283a61
3
  size 402688040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e4528cf50c0a50beb452ea3f76903e1d3d35fef2f485465e26c8232e05beab4
3
  size 402688040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b14303ba15a33151cfb02c99ed03db5aae81b8b8b30bd91c12001b9beeada540
3
  size 204773716
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4c73e0681821da28f22a96fb597d551791cf369ef75a654c1efedf344eb9693
3
  size 204773716
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3dac5e06e2dfa31136d8bb374837c95dbb4ca404c2fc8aa0a6c8502696ee35d3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b98635a35f0ec402f5d6f7032d676886d8d95de144b7e58f34317d9d4654e207
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": 0.1147227533460803,
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": 14.494,
193
  "eval_steps_per_second": 1.82,
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": 3.401352046706688e+16,
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": 0.12746972594008923,
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": 14.494,
193
  "eval_steps_per_second": 1.82,
194
  "step": 45
195
+ },
196
+ {
197
+ "epoch": 0.12237093690248566,
198
+ "grad_norm": 5.9597859382629395,
199
+ "learning_rate": 6.15582970243117e-07,
200
+ "loss": 4.3533,
201
+ "step": 48
202
+ },
203
+ {
204
+ "epoch": 0.12746972594008923,
205
+ "eval_loss": 1.1204696893692017,
206
+ "eval_runtime": 45.6772,
207
+ "eval_samples_per_second": 14.471,
208
+ "eval_steps_per_second": 1.817,
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": 3.795984052125696e+16,
230
  "train_batch_size": 8,
231
  "trial_name": null,
232
  "trial_params": null