flytech commited on
Commit
1755093
·
1 Parent(s): 7dbf165

Training in progress, step 900, 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:c53135849dc04cc65b369eb490a7a8f655dc6159ed38aea9f68b90e0ffdca490
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:329c49e7796d783682e248fd847d08da0b4e0cd68db2a66326505b187a62992e
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:05c7f1840c59b7e05079bade98860da96807471d2246d58bc57d415a5f47ca50
3
  size 20524127
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a75c176b5e2763a0b08f5829fe7b98c4b2963ebdf148196f4510bdf29df3b1f
3
  size 20524127
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9ec1259429b87ac6f4ca3569d5b0f362a16738b5286a1874d947a518fc2a2983
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9dcdb935b34c9d70ec2e1e1d92711112a2e00c391ac1e7db0021005dd1b30edb
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35b2c315e825043036cabe0b621568bd0f3b5d9852144632bacc4a8b852454d0
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c1c649bd14a49756b729525a4732fa77be1d6c78a716ad6162c210414e48318
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.488888888888889,
5
  "eval_steps": 60,
6
- "global_step": 840,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -189,13 +189,26 @@
189
  "eval_samples_per_second": 1.919,
190
  "eval_steps_per_second": 0.24,
191
  "step": 840
 
 
 
 
 
 
 
 
 
 
 
 
 
192
  }
193
  ],
194
  "logging_steps": 60,
195
  "max_steps": 1011,
196
  "num_train_epochs": 3,
197
  "save_steps": 60,
198
- "total_flos": 1.3952490902913024e+17,
199
  "trial_name": null,
200
  "trial_params": null
201
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.6666666666666665,
5
  "eval_steps": 60,
6
+ "global_step": 900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
189
  "eval_samples_per_second": 1.919,
190
  "eval_steps_per_second": 0.24,
191
  "step": 840
192
+ },
193
+ {
194
+ "epoch": 2.67,
195
+ "learning_rate": 0.0002,
196
+ "loss": 0.476,
197
+ "step": 900
198
+ },
199
+ {
200
+ "epoch": 2.67,
201
+ "eval_runtime": 312.5341,
202
+ "eval_samples_per_second": 1.92,
203
+ "eval_steps_per_second": 0.24,
204
+ "step": 900
205
  }
206
  ],
207
  "logging_steps": 60,
208
  "max_steps": 1011,
209
  "num_train_epochs": 3,
210
  "save_steps": 60,
211
+ "total_flos": 1.494909739597824e+17,
212
  "trial_name": null,
213
  "trial_params": null
214
  }