ccore commited on
Commit
14f77eb
·
verified ·
1 Parent(s): f4d5dbe

Training in progress, epoch 18, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f2ac1e7e990aff3af0a15d1835576aa2aebb5b9ee90647359719d3fd0134b8d
3
  size 500979600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66ebe755272c833ee429575beb043faa3e540a96844030cdd1171fc4cd696f08
3
  size 500979600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0c963f45c1bd5ae5ff9658232185d3b067942933ba18628c76240dda57365c1
3
  size 1002078330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:478c5c1c638d5d04267266ca64ac6928b413e616bc8f0af07f92f078e9ef68f5
3
  size 1002078330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25a1346ff38ded6949f1c63ea9bed0f00deec534050210f1999680410c965b05
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0b277510b0f644161ded5131086288f4993c9942ee7f089d0da5ae42603c16a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5ac85153b9d8c1365faf7f0479f8e838f8c32f294048b97d718e681ea322699
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9c5a65300f8eb23ec040f2b45a372e7e707ff9400c5124bc4c052823f307128
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.31853449344635,
3
- "best_model_checkpoint": "./opt_trained/checkpoint-374",
4
- "epoch": 17.0,
5
  "eval_steps": 500,
6
- "global_step": 374,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -143,6 +143,14 @@
143
  "eval_samples_per_second": 36.939,
144
  "eval_steps_per_second": 9.235,
145
  "step": 374
 
 
 
 
 
 
 
 
146
  }
147
  ],
148
  "logging_steps": 500,
@@ -162,7 +170,7 @@
162
  "attributes": {}
163
  }
164
  },
165
- "total_flos": 1.2060141954048e+16,
166
  "train_batch_size": 16,
167
  "trial_name": null,
168
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3142348527908325,
3
+ "best_model_checkpoint": "./opt_trained/checkpoint-396",
4
+ "epoch": 18.0,
5
  "eval_steps": 500,
6
+ "global_step": 396,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
143
  "eval_samples_per_second": 36.939,
144
  "eval_steps_per_second": 9.235,
145
  "step": 374
146
+ },
147
+ {
148
+ "epoch": 18.0,
149
+ "eval_loss": 1.3142348527908325,
150
+ "eval_runtime": 8.1317,
151
+ "eval_samples_per_second": 36.893,
152
+ "eval_steps_per_second": 9.223,
153
+ "step": 396
154
  }
155
  ],
156
  "logging_steps": 500,
 
170
  "attributes": {}
171
  }
172
  },
173
+ "total_flos": 1.2769562068992e+16,
174
  "train_batch_size": 16,
175
  "trial_name": null,
176
  "trial_params": null