lesso commited on
Commit
7bb47c4
·
verified ·
1 Parent(s): dc82d72

Training in progress, step 500, 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:d876da443527d34e56cfe30ce0c1a0c9fce151b3631923fd946e1bea502286bb
3
  size 94412008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11716d3d569d110c2c5d12c412c12c762f5b3f6141135d0d553bd7a50bc11019
3
  size 94412008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c88bff41e9cc4547eaaf6800036bab69d8562266d5ad2b76d8c123a4a3409466
3
  size 48261076
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f6661877ea41b1255b679895e148282c4e09690123d53c0bb71076fe8f51e4f
3
  size 48261076
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2406f6aa64107b3a72d51f2b2e53f78d4212fd3833aeadad4bcb018c2c3bc364
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f59d2dbe327d7a56844aaf160917f62626c439513fe46657bd946eb0a339bfb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71a96715f430c2eb0d6104363f54769b2c1bdb005671dc81f0d67833a84ba743
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.9104011058807373,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-450",
4
- "epoch": 0.02701566908807108,
5
  "eval_steps": 50,
6
- "global_step": 450,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -150,6 +150,21 @@
150
  "eval_samples_per_second": 16.53,
151
  "eval_steps_per_second": 4.134,
152
  "step": 450
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
153
  }
154
  ],
155
  "logging_steps": 50,
@@ -173,12 +188,12 @@
173
  "should_evaluate": false,
174
  "should_log": false,
175
  "should_save": true,
176
- "should_training_stop": false
177
  },
178
  "attributes": {}
179
  }
180
  },
181
- "total_flos": 2.3863716822908928e+17,
182
  "train_batch_size": 4,
183
  "trial_name": null,
184
  "trial_params": null
 
1
  {
2
+ "best_metric": 2.908254384994507,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-500",
4
+ "epoch": 0.030017410097856755,
5
  "eval_steps": 50,
6
+ "global_step": 500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
150
  "eval_samples_per_second": 16.53,
151
  "eval_steps_per_second": 4.134,
152
  "step": 450
153
+ },
154
+ {
155
+ "epoch": 0.030017410097856755,
156
+ "grad_norm": 2.6529409885406494,
157
+ "learning_rate": 0.0,
158
+ "loss": 5.913,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 0.030017410097856755,
163
+ "eval_loss": 2.908254384994507,
164
+ "eval_runtime": 422.7427,
165
+ "eval_samples_per_second": 16.592,
166
+ "eval_steps_per_second": 4.149,
167
+ "step": 500
168
  }
169
  ],
170
  "logging_steps": 50,
 
188
  "should_evaluate": false,
189
  "should_log": false,
190
  "should_save": true,
191
+ "should_training_stop": true
192
  },
193
  "attributes": {}
194
  }
195
  },
196
+ "total_flos": 2.6545353859792896e+17,
197
  "train_batch_size": 4,
198
  "trial_name": null,
199
  "trial_params": null