mamung commited on
Commit
6e60f99
·
verified ·
1 Parent(s): cbdc0da

Training in progress, step 81, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98ac73fb18a717426f2d677a555ecd63e01072e96c43b7ad4e189cf99b17591a
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d6f3562e013b7d6aa36f3758845e646039f56df73f62dfd96fdc1229c893a37
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:817a9e783c17b568df71f9fb9a7ade93ccfcad0d547e2ad0a6e3242f048c8f93
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:61ac7b95a1d98d3f48c6552f063fc44de970742a4a881090ed319d953d5daf1d
3
  size 671466706
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d37f984e459ac29119d1e223e683833fa82191d86820ac8eb951dd3f4fbd981f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e0e03ffadbe83bef223059a14663bc135403d266f36c28e8c51d630e892095b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f9245597e5014ecf432f2646dbac4f88c26cbc6ab1676ee7be71281b45d826d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4967fab956f007beafd6b8bc5c5dee4d86950ea055e4ab46c9a7cdc66a69112d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.17308992562542258,
5
  "eval_steps": 9,
6
- "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -247,6 +247,35 @@
247
  "eval_samples_per_second": 8.955,
248
  "eval_steps_per_second": 4.477,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 4.2988852305985536e+17,
270
  "train_batch_size": 2,
271
  "trial_name": null,
272
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.1947261663286004,
5
  "eval_steps": 9,
6
+ "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
247
  "eval_samples_per_second": 8.955,
248
  "eval_steps_per_second": 4.477,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.18030200585981518,
253
+ "grad_norm": 1.005875587463379,
254
+ "learning_rate": 4.444297669803981e-05,
255
+ "loss": 1.0467,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.1875140860942078,
260
+ "grad_norm": 0.9949033260345459,
261
+ "learning_rate": 3.5055195166981645e-05,
262
+ "loss": 1.3012,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.1947261663286004,
267
+ "grad_norm": 0.9470193982124329,
268
+ "learning_rate": 2.6567749056431467e-05,
269
+ "loss": 1.237,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.1947261663286004,
274
+ "eval_loss": 1.070177674293518,
275
+ "eval_runtime": 156.4864,
276
+ "eval_samples_per_second": 8.959,
277
+ "eval_steps_per_second": 4.48,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 4.8360127561570714e+17,
299
  "train_batch_size": 2,
300
  "trial_name": null,
301
  "trial_params": null