Hanzalwi commited on
Commit
680a405
1 Parent(s): f977a19

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 sha256:80dbec0243c194cd90b8576265039941c36c0b75147591bf82d189ac76481672
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1f1153548a08abc38cd3b5f63054427db73fd12659b0e43adfbb4d8c133d807
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f2e65bcccf1d2e603e1f7e5390104b5b9d1238e90d064ad2054af82da00dde8d
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b957375b650b204e121bc8b5b10777228d046d712dfb9af475d5cc5f96ecd93a
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:cf0d1b378492ec4e150da1c9feeca26eae7c30c21199e70dec7f166a03613c3d
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0704dd557dce4febe99f56d14200e6282ff3f71d203ef70d72c678236f04eb88
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": 1.4297349452972412,
3
- "best_model_checkpoint": "./outputs/checkpoint-1000",
4
- "epoch": 1.3333333333333333,
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,
@@ -147,6 +147,20 @@
147
  "eval_samples_per_second": 15.533,
148
  "eval_steps_per_second": 1.948,
149
  "step": 1000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
150
  }
151
  ],
152
  "logging_steps": 100,
@@ -154,7 +168,7 @@
154
  "num_input_tokens_seen": 0,
155
  "num_train_epochs": 3,
156
  "save_steps": 100,
157
- "total_flos": 5.844782394372096e+16,
158
  "trial_name": null,
159
  "trial_params": null
160
  }
 
1
  {
2
+ "best_metric": 1.4200090169906616,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1100",
4
+ "epoch": 1.4666666666666668,
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": 15.533,
148
  "eval_steps_per_second": 1.948,
149
  "step": 1000
150
+ },
151
+ {
152
+ "epoch": 1.47,
153
+ "learning_rate": 0.0002,
154
+ "loss": 1.1846,
155
+ "step": 1100
156
+ },
157
+ {
158
+ "epoch": 1.47,
159
+ "eval_loss": 1.4200090169906616,
160
+ "eval_runtime": 93.3115,
161
+ "eval_samples_per_second": 15.55,
162
+ "eval_steps_per_second": 1.95,
163
+ "step": 1100
164
  }
165
  ],
166
  "logging_steps": 100,
 
168
  "num_input_tokens_seen": 0,
169
  "num_train_epochs": 3,
170
  "save_steps": 100,
171
+ "total_flos": 6.43012944795648e+16,
172
  "trial_name": null,
173
  "trial_params": null
174
  }