Synth-Ecosystem commited on
Commit
4ee878b
·
verified ·
1 Parent(s): 7a13956

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 sha256:8852b85cef25e842029e84fa550137a9954e7fe36f5e1c712e2e4b250466409d
3
  size 38572808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:459e122a689beac2a1be19d8a0a24781d6b8be64bd1ee7428cd560f55a117b52
3
  size 38572808
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8835ed0f78a2181cf2d0babc8d207814ddf2d4c59367bf6150fff6b64eb75a65
3
  size 39471301
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:900a6841ae4a027ec8522ddae8ef4cf8b9fd10918d7d3c80a86d90b4e20b7e8d
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:f556552f745af78d3e9bfc8ea5c16b9ac5253c3b2307c3bdd26a95ce9f3503a4
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2e24aabf1139e9fbd6b7ac33791e96a821e133fb6fe12fe112d862fedf74fad
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f950059b88d91cb60534020a6eb09c701e2d39d53caebb93d7d33fe09801996f
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2bd8e1135e64279cbd8d617b19e2756f9e38491215b79513139274a6daff350
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": 0.24,
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": 0.6773946091532708,
159
  "num_tokens": 366204.0,
160
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
161
  }
162
  ],
163
  "logging_steps": 10,
@@ -177,7 +227,7 @@
177
  "attributes": {}
178
  }
179
  },
180
- "total_flos": 4072403110748160.0,
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": 0.32,
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": 0.6773946091532708,
159
  "num_tokens": 366204.0,
160
  "step": 150
161
+ },
162
+ {
163
+ "entropy": 1.4623933732509613,
164
+ "epoch": 0.256,
165
+ "grad_norm": 2.296875,
166
+ "learning_rate": 8.46e-05,
167
+ "loss": 1.5432461738586425,
168
+ "mean_token_accuracy": 0.6877943009138108,
169
+ "num_tokens": 390253.0,
170
+ "step": 160
171
+ },
172
+ {
173
+ "entropy": 1.4584963083267213,
174
+ "epoch": 0.272,
175
+ "grad_norm": 1.7578125,
176
+ "learning_rate": 7.86e-05,
177
+ "loss": 1.5031940460205078,
178
+ "mean_token_accuracy": 0.6966861024498939,
179
+ "num_tokens": 414662.0,
180
+ "step": 170
181
+ },
182
+ {
183
+ "entropy": 1.2456398598849774,
184
+ "epoch": 0.288,
185
+ "grad_norm": 1.9921875,
186
+ "learning_rate": 7.26e-05,
187
+ "loss": 1.378309154510498,
188
+ "mean_token_accuracy": 0.726311057806015,
189
+ "num_tokens": 437835.0,
190
+ "step": 180
191
+ },
192
+ {
193
+ "entropy": 1.2711421206593514,
194
+ "epoch": 0.304,
195
+ "grad_norm": 2.4375,
196
+ "learning_rate": 6.66e-05,
197
+ "loss": 1.3943452835083008,
198
+ "mean_token_accuracy": 0.7222944989800453,
199
+ "num_tokens": 462225.0,
200
+ "step": 190
201
+ },
202
+ {
203
+ "entropy": 1.3176883950829505,
204
+ "epoch": 0.32,
205
+ "grad_norm": 1.9765625,
206
+ "learning_rate": 6.06e-05,
207
+ "loss": 1.3720195770263672,
208
+ "mean_token_accuracy": 0.7194708675146103,
209
+ "num_tokens": 485468.0,
210
+ "step": 200
211
  }
212
  ],
213
  "logging_steps": 10,
 
227
  "attributes": {}
228
  }
229
  },
230
+ "total_flos": 5385244468469760.0,
231
  "train_batch_size": 2,
232
  "trial_name": null,
233
  "trial_params": null