rizkyjun commited on
Commit
5b1f546
1 Parent(s): e2da063

Training in progress, step 1100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34e5b714b9ad018579c0395bd88c1f526737a3a7591470f0bdcf9a363e6f9f9e
3
  size 31466288
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17eb10f2ba8233f9fb519bc8ddcb7d404ecebd35e30169ead2d077dc504c9e46
3
  size 31466288
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:27f65bc053b2ff572651b0fae1a50460b90cdac3d97fcdc7808a0375409aa015
3
  size 62950917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1371801f893c84206f187f3e31be6bf63a4e61709a38828e8f85cc17b8c7ce94
3
  size 62950917
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0f78b2562bc8727c20689e149baf87f12d40909810dc10b46acf10485d1b41a
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c36055d9fd25c4040bc7a4fdbd7b637c5d08e464796f0b68296e5cb34f28a816
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f5f3a2d7191245a70e1410d8951fd2f5c94b0b91f13bf39c3f76fe8aaf57fd4
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.8282623291015625,
3
- "best_model_checkpoint": "./outputs/checkpoint-1000",
4
- "epoch": 0.7285974499089253,
5
  "eval_steps": 100,
6
- "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -147,13 +147,27 @@
147
  "eval_samples_per_second": 11.324,
148
  "eval_steps_per_second": 1.417,
149
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
150
  }
151
  ],
152
  "logging_steps": 100,
153
  "max_steps": 4116,
154
  "num_train_epochs": 3,
155
  "save_steps": 100,
156
- "total_flos": 2.6035701176578867e+17,
157
  "trial_name": null,
158
  "trial_params": null
159
  }
 
1
  {
2
+ "best_metric": 1.7944462299346924,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1100",
4
+ "epoch": 0.8014571948998178,
5
  "eval_steps": 100,
6
+ "global_step": 1100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
147
  "eval_samples_per_second": 11.324,
148
  "eval_steps_per_second": 1.417,
149
  "step": 1000
150
+ },
151
+ {
152
+ "epoch": 0.8,
153
+ "learning_rate": 0.0002,
154
+ "loss": 1.8218,
155
+ "step": 1100
156
+ },
157
+ {
158
+ "epoch": 0.8,
159
+ "eval_loss": 1.7944462299346924,
160
+ "eval_runtime": 554.2451,
161
+ "eval_samples_per_second": 11.32,
162
+ "eval_steps_per_second": 1.416,
163
+ "step": 1100
164
  }
165
  ],
166
  "logging_steps": 100,
167
  "max_steps": 4116,
168
  "num_train_epochs": 3,
169
  "save_steps": 100,
170
+ "total_flos": 2.8630550174151475e+17,
171
  "trial_name": null,
172
  "trial_params": null
173
  }