Synth-Ecosystem commited on
Commit
f15feba
·
verified ·
1 Parent(s): 51a2e0e

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2762a7c98521bb775714596b9797f764fe0ae5d86f7a3d18c463a3fa245153bc
3
  size 38572808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a743fcab805e85e0683b5135059dfc633d6003b70e8619591a8dbd2f149442f4
3
  size 38572808
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:08e3d226b869c08ed07e5ce3ba06cae36926e24eaef974d2381ad0ea66c47deb
3
  size 39471301
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ad027edbd0675111ba6f174279dc824f426a99d39abf6d22332f4202304e255
3
  size 39471301
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9f61cf452a4e2a8b8645bbfbecde6e74e8b526a5674a38001e6f8e31d1ae89a
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6581ad83e18f122d921e1fe6af1ff3974f91f01c264d8b9cdba8228fe7148618
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1f5d15dfdf0bae35e489e07f19ab2ec727f69de5711cec803f468caeccac964
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c6a87496ef295679f7f1203b462d3dbb1b506bde8c44fb9df0612f4855c89e25
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.2,
6
  "eval_steps": 500,
7
- "global_step": 150,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -158,6 +158,56 @@
158
  "mean_token_accuracy": 0.6929229475557804,
159
  "num_tokens": 369639.0,
160
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
161
  }
162
  ],
163
  "logging_steps": 10,
@@ -177,7 +227,7 @@
177
  "attributes": {}
178
  }
179
  },
180
- "total_flos": 4060359187169280.0,
181
  "train_batch_size": 2,
182
  "trial_name": null,
183
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.26666666666666666,
6
  "eval_steps": 500,
7
+ "global_step": 200,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
158
  "mean_token_accuracy": 0.6929229475557804,
159
  "num_tokens": 369639.0,
160
  "step": 150
161
+ },
162
+ {
163
+ "entropy": 1.7040874853730201,
164
+ "epoch": 0.21333333333333335,
165
+ "grad_norm": 1.765625,
166
+ "learning_rate": 9.058916866814858e-05,
167
+ "loss": 1.8626722335815429,
168
+ "mean_token_accuracy": 0.6536142930388451,
169
+ "num_tokens": 393573.0,
170
+ "step": 160
171
+ },
172
+ {
173
+ "entropy": 1.8077140614390372,
174
+ "epoch": 0.22666666666666666,
175
+ "grad_norm": 1.796875,
176
+ "learning_rate": 8.023426596208739e-05,
177
+ "loss": 1.8430540084838867,
178
+ "mean_token_accuracy": 0.6397245928645134,
179
+ "num_tokens": 417577.0,
180
+ "step": 170
181
+ },
182
+ {
183
+ "entropy": 1.821508213877678,
184
+ "epoch": 0.24,
185
+ "grad_norm": 1.6328125,
186
+ "learning_rate": 7.009592077439134e-05,
187
+ "loss": 1.9114587783813477,
188
+ "mean_token_accuracy": 0.6204724945127964,
189
+ "num_tokens": 444808.0,
190
+ "step": 180
191
+ },
192
+ {
193
+ "entropy": 1.5762236014008522,
194
+ "epoch": 0.25333333333333335,
195
+ "grad_norm": 1.578125,
196
+ "learning_rate": 6.0285210936521955e-05,
197
+ "loss": 1.7089605331420898,
198
+ "mean_token_accuracy": 0.6695762172341346,
199
+ "num_tokens": 468853.0,
200
+ "step": 190
201
+ },
202
+ {
203
+ "entropy": 1.615697766840458,
204
+ "epoch": 0.26666666666666666,
205
+ "grad_norm": 1.53125,
206
+ "learning_rate": 5.090962463848592e-05,
207
+ "loss": 1.7255016326904298,
208
+ "mean_token_accuracy": 0.6663483455777168,
209
+ "num_tokens": 492452.0,
210
+ "step": 200
211
  }
212
  ],
213
  "logging_steps": 10,
 
227
  "attributes": {}
228
  }
229
  },
230
+ "total_flos": 5406630038568960.0,
231
  "train_batch_size": 2,
232
  "trial_name": null,
233
  "trial_params": null