dixedus commited on
Commit
9198791
·
verified ·
1 Parent(s): 436f472

Training in progress, step 54, 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:c6053bf147bc20ef8b243585537a70e77a866778db9b912a3984f5246acdad46
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe3889629b7ac034dc0bd1e143b29826e3d014bbb852362b6232cb84a3388bef
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1c35e6b7b33d019ee2bb02ff2e1c45df37d344660949d021c2de9bb86676851
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:985d1cbab1067c1f24801f1ae8bc1238148bd7bcb6ecc81a2714d3b6309e6faa
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3295d9b8e6727a0572a17fcd9e9c0c197ca020ea3fd15f4c9bf4d70bd654e602
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92b963127b22ddeab5c967c77cf61654178062a733d4a71d3b34be157aad97ad
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
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": 0.004861842638359939,
5
  "eval_steps": 9,
6
- "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -160,6 +160,35 @@
160
  "eval_samples_per_second": 6.929,
161
  "eval_steps_per_second": 0.866,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 1.1866158730838016e+17,
183
  "train_batch_size": 8,
184
  "trial_name": null,
185
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.005834211166031926,
5
  "eval_steps": 9,
6
+ "global_step": 54,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
160
  "eval_samples_per_second": 6.929,
161
  "eval_steps_per_second": 0.866,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.005185965480917268,
166
+ "grad_norm": 0.8616397976875305,
167
+ "learning_rate": 6.209609477998338e-05,
168
+ "loss": 1.9082,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.005510088323474597,
173
+ "grad_norm": 0.7725919485092163,
174
+ "learning_rate": 5.695865504800327e-05,
175
+ "loss": 1.7656,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.005834211166031926,
180
+ "grad_norm": 0.819065511226654,
181
+ "learning_rate": 5.174497483512506e-05,
182
+ "loss": 1.7582,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.005834211166031926,
187
+ "eval_loss": 1.81401526927948,
188
+ "eval_runtime": 2248.0076,
189
+ "eval_samples_per_second": 6.935,
190
+ "eval_steps_per_second": 0.867,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 1.423939047700562e+17,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null