rizkyjun commited on
Commit
a584cb5
1 Parent(s): ccdc925

Training in progress, step 1300, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8e9b60b46d6655524ebe893896e1a89b069569a414e973a66514262099a41ffb
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:302674248e09d8ee0a26f858a754e03f6d4cedf67e3ad45bbc5f77036bb2bae3
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:582da9965d338b2ad57b32bc2ab00fb98cbb9e87f6c64b368e06a09f418257e7
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf9491cc45e14a2261ea7b7f15e2645cd0fc5cb9db64501745caee56e4d5028c
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c24a5519079f5affefa77bc221612f519ec2d7b465daf634e60b03336ade4e2c
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:957113e67ab11c2af45eb4aad3a4067ef1fc77a018bd85c77d56e6d10186026f
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.3195290565490723,
3
- "best_model_checkpoint": "./outputs/checkpoint-1200",
4
- "epoch": 0.8743169398907104,
5
  "eval_steps": 100,
6
- "global_step": 1200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -175,13 +175,27 @@
175
  "eval_samples_per_second": 30.478,
176
  "eval_steps_per_second": 3.813,
177
  "step": 1200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
178
  }
179
  ],
180
  "logging_steps": 100,
181
  "max_steps": 4116,
182
  "num_train_epochs": 3,
183
  "save_steps": 100,
184
- "total_flos": 3.523768039636992e+16,
185
  "trial_name": null,
186
  "trial_params": null
187
  }
 
1
  {
2
+ "best_metric": 2.3028838634490967,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1300",
4
+ "epoch": 0.9471766848816029,
5
  "eval_steps": 100,
6
+ "global_step": 1300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
175
  "eval_samples_per_second": 30.478,
176
  "eval_steps_per_second": 3.813,
177
  "step": 1200
178
+ },
179
+ {
180
+ "epoch": 0.95,
181
+ "learning_rate": 0.0002,
182
+ "loss": 2.3264,
183
+ "step": 1300
184
+ },
185
+ {
186
+ "epoch": 0.95,
187
+ "eval_loss": 2.3028838634490967,
188
+ "eval_runtime": 205.7996,
189
+ "eval_samples_per_second": 30.486,
190
+ "eval_steps_per_second": 3.814,
191
+ "step": 1300
192
  }
193
  ],
194
  "logging_steps": 100,
195
  "max_steps": 4116,
196
  "num_train_epochs": 3,
197
  "save_steps": 100,
198
+ "total_flos": 3.817057293729792e+16,
199
  "trial_name": null,
200
  "trial_params": null
201
  }