mamung commited on
Commit
f96b6fc
·
verified ·
1 Parent(s): f9bd897

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 sha256:40974cab0de6178b973d6db2238ad1f7121950e70c1105076c288d3d9a0bd462
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4018e222ba654e7389dc391c433c701d4f5838c682c4f25b82a40ce4e8b61dcd
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0404713a0a930e9515d4c628b6c342ddec7babea60696ba0d8f9aa6f28699ee
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab86eba0b2832a7e95ae63ef7f153a72efc20d119164fd6e60abb894e2d0875
3
  size 671466706
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7c3f467354144d04fe960925097d526d5d43d174e118f789bb747d3e1621b26e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44c16b24865a63961b775a7107dc272a0c419a6935a35e7609e0a4f3bf916ee3
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": 1.3763440860215055,
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": 8.963,
248
  "eval_steps_per_second": 4.507,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 4.297020204468142e+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": 1.5483870967741935,
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": 8.963,
248
  "eval_steps_per_second": 4.507,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 1.4336917562724014,
253
+ "grad_norm": 1.6304519176483154,
254
+ "learning_rate": 4.444297669803981e-05,
255
+ "loss": 1.3729,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 1.4910394265232976,
260
+ "grad_norm": 1.690694808959961,
261
+ "learning_rate": 3.5055195166981645e-05,
262
+ "loss": 1.3019,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 1.5483870967741935,
267
+ "grad_norm": 1.8786835670471191,
268
+ "learning_rate": 2.6567749056431467e-05,
269
+ "loss": 1.3178,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 1.5483870967741935,
274
+ "eval_loss": 1.8405394554138184,
275
+ "eval_runtime": 19.7363,
276
+ "eval_samples_per_second": 8.968,
277
+ "eval_steps_per_second": 4.509,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 4.83414773002666e+17,
299
  "train_batch_size": 2,
300
  "trial_name": null,
301
  "trial_params": null