ardaspear commited on
Commit
768718c
·
verified ·
1 Parent(s): 0762ac6

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:e4e3163f3899145e0f0e28f2932b67f5ab953c710aa461c467cdefccad1a9b84
3
  size 1001465824
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2b7dd8e5afc9aa29c4a2b764862f3893ae76079f20a93f9d4a3f967dd8baa89
3
  size 1001465824
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bdb21c9c263ef113295dc9fdf36f0a74b25669fe25ed8b567eced058980334c4
3
  size 509176980
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa4f561ad8ffcb5c869231ed6b4c6edc500358ffa70c05639ae1958d851cecad
3
  size 509176980
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b0e17f1b3f4c88dd025eb12291194693982d72306ba4cc4b2b5b44dba1dd344
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76a7af8e7dc9db0611d7e02b5036ec494dcb2bc08691bb86341ddba3da8bce4f
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": 0.39823008849557523,
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": 7.772,
161
  "eval_steps_per_second": 1.963,
162
  "step": 45
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
163
  }
164
  ],
165
  "logging_steps": 3,
@@ -179,7 +208,7 @@
179
  "attributes": {}
180
  }
181
  },
182
- "total_flos": 6.407917481754624e+16,
183
  "train_batch_size": 4,
184
  "trial_name": null,
185
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.4778761061946903,
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": 7.772,
161
  "eval_steps_per_second": 1.963,
162
  "step": 45
163
+ },
164
+ {
165
+ "epoch": 0.4247787610619469,
166
+ "grad_norm": 0.00013267536996863782,
167
+ "learning_rate": 6.209609477998338e-05,
168
+ "loss": 0.0005,
169
+ "step": 48
170
+ },
171
+ {
172
+ "epoch": 0.45132743362831856,
173
+ "grad_norm": 0.00011587361223064363,
174
+ "learning_rate": 5.695865504800327e-05,
175
+ "loss": 0.0,
176
+ "step": 51
177
+ },
178
+ {
179
+ "epoch": 0.4778761061946903,
180
+ "grad_norm": 6.926426431164145e-05,
181
+ "learning_rate": 5.174497483512506e-05,
182
+ "loss": 0.0,
183
+ "step": 54
184
+ },
185
+ {
186
+ "epoch": 0.4778761061946903,
187
+ "eval_loss": 2.020281613113184e-07,
188
+ "eval_runtime": 12.2268,
189
+ "eval_samples_per_second": 7.77,
190
+ "eval_steps_per_second": 1.963,
191
+ "step": 54
192
  }
193
  ],
194
  "logging_steps": 3,
 
208
  "attributes": {}
209
  }
210
  },
211
+ "total_flos": 7.856944047980544e+16,
212
  "train_batch_size": 4,
213
  "trial_name": null,
214
  "trial_params": null