ccore commited on
Commit
d050c93
·
verified ·
1 Parent(s): 605f2a4

Training in progress, epoch 17, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2d3a577e65845eb010e1c16ec7fa32ad36897f7e449c26ac8dfb9529a0f69423
3
  size 500979600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e17c1b54e6213a55c53215444b25ee79cc33e9ad7702a6cbb6e16edb930d80d
3
  size 500979600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de2450c6993e9a56e7dc9145137de8e225a8a9120841cbf3c0dfa256a5593dcc
3
  size 1002078330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be4183eebbd4d3837bb0ce569467624969618a02d0e02d3d700c44c4caf20c7e
3
  size 1002078330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dacd9ceced445683b429d8048de3408ac5db4d13805bc178931c8c7bec632745
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e01898925b7af5f5ba289c8fef21f79a7a00ffbf1a0745625b200f27c799885
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:32c36238a16299a3ca7723d304d049d1e0393d69d7c985f0021c667d4adf33a6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0295287d39e8a510b3de0550fdcbbb67b482b2d7bf41ccc76c3e4cfea285df7d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.9877104163169861,
3
  "best_model_checkpoint": "./opt_trained/checkpoint-3216",
4
- "epoch": 16.0,
5
  "eval_steps": 500,
6
- "global_step": 3216,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -177,6 +177,14 @@
177
  "eval_samples_per_second": 37.08,
178
  "eval_steps_per_second": 9.27,
179
  "step": 3216
 
 
 
 
 
 
 
 
180
  }
181
  ],
182
  "logging_steps": 500,
@@ -196,7 +204,7 @@
196
  "attributes": {}
197
  }
198
  },
199
- "total_flos": 1.0826161754112e+17,
200
  "train_batch_size": 16,
201
  "trial_name": null,
202
  "trial_params": null
 
1
  {
2
  "best_metric": 0.9877104163169861,
3
  "best_model_checkpoint": "./opt_trained/checkpoint-3216",
4
+ "epoch": 17.0,
5
  "eval_steps": 500,
6
+ "global_step": 3417,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
177
  "eval_samples_per_second": 37.08,
178
  "eval_steps_per_second": 9.27,
179
  "step": 3216
180
+ },
181
+ {
182
+ "epoch": 17.0,
183
+ "eval_loss": 0.9905799031257629,
184
+ "eval_runtime": 76.8333,
185
+ "eval_samples_per_second": 37.171,
186
+ "eval_steps_per_second": 9.293,
187
+ "step": 3417
188
  }
189
  ],
190
  "logging_steps": 500,
 
204
  "attributes": {}
205
  }
206
  },
207
+ "total_flos": 1.1502796863744e+17,
208
  "train_batch_size": 16,
209
  "trial_name": null,
210
  "trial_params": null