brixeus commited on
Commit
0d35263
·
verified ·
1 Parent(s): 223faca

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 sha256:5e61aa843e4037b8ee53d96d3783033834bdf2cf8de150565235aab74aed225e
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c5af4fbd708855d047ed9132348f9ade5ce636a41af46ca9a4ea0fe93e7e472
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dd54e2017c67a410abb48b02b3e58f3ee4d89a5c1dd8da26dd2b19c0b0a86820
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d015c6417a96a4e99e188f862b293740512140b5d17ff0af04d5f4ebee5d3d7c
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:14719ed3112f3e5b130f8afa264745103a34f5c0bb6a80b06bc68acfa79da1b2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b976fcea21ecae35d2f32d796d38bd98366e20e84ccdb0d2228cd4768022150
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": 1.1842105263157894,
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": 14.028,
161
  "eval_steps_per_second": 1.753,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 6.297410785089946e+16,
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": 1.4210526315789473,
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": 14.028,
161
  "eval_steps_per_second": 1.753,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 1.263157894736842,
166
+ "grad_norm": 7.848536014556885,
167
+ "learning_rate": 6.209609477998338e-05,
168
+ "loss": 2.4708,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 1.3421052631578947,
173
+ "grad_norm": 8.303677558898926,
174
+ "learning_rate": 5.695865504800327e-05,
175
+ "loss": 2.6233,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 1.4210526315789473,
180
+ "grad_norm": 8.685861587524414,
181
+ "learning_rate": 5.174497483512506e-05,
182
+ "loss": 2.6195,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 1.4210526315789473,
187
+ "eval_loss": 0.765683650970459,
188
+ "eval_runtime": 4.5582,
189
+ "eval_samples_per_second": 14.041,
190
+ "eval_steps_per_second": 1.755,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 7.563045332267827e+16,
212
  "train_batch_size": 8,
213
  "trial_name": null,
214
  "trial_params": null