eeeebbb2 commited on
Commit
5dcc40f
1 Parent(s): b0036dd

Training in progress, step 35, 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:eaec4fcd1a66529f5088d9c7f9956928cf6806d614379191dc5b9984ce99a865
3
  size 97728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77769997b4b7eeb8fedbea1b5d236b1433920d6708f6f5b7695f43b712e8fd2c
3
  size 97728
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39c26b73113849810a665cca8a02fd146b721e315108ca13c92590f345ec336d
3
  size 212298
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70c581add322d7c99dd2647c25c2168d52a5b41c4c22781e2ae6b4f8c3941a4
3
  size 212298
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0fe7efa965d09f457d8607ce6319310a67bfec8288cfcfe1013d29104389cad1
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a79e32f79c3cffc7628032a84d74a93a3c69e6c71da47abf273b04c6ba25f52
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4a67c6acc20c94d6d427feee33b12a3dfe1e81dd63d62d115a1f0873814e7422
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8fc04ed93061945918d1105d5066ae770509a429c209a9d76c0db07bb304c5fc
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16fb5ef7b99fc44900050cadede912925074ca0efa199f37c81b8c4d776db404
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e4122cf807d87a2e6241c4996e363137addc582695d808c96fe757be71d790c
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15d8307f63ed893c3583f9dbf157541d06f944914144ecafb13a8ca15d83ace4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c976290ee7b8505e06e1987f5b8eee06e1e0f6d494861f242b71f0d8b5034ed
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c09031e244e5c89e52b3c3bb662b54db8a85996e54bd9c77222030648f1c7db3
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93ce236cdfc3570e60fc168a599f38d18a8345a454926b769bf6e4e2c224361f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 11.732924461364746,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
- "epoch": 2.1739130434782608,
5
  "eval_steps": 25,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -198,6 +198,76 @@
198
  "eval_samples_per_second": 329.244,
199
  "eval_steps_per_second": 85.603,
200
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
201
  }
202
  ],
203
  "logging_steps": 1,
@@ -221,12 +291,12 @@
221
  "should_evaluate": false,
222
  "should_log": false,
223
  "should_save": true,
224
- "should_training_stop": false
225
  },
226
  "attributes": {}
227
  }
228
  },
229
- "total_flos": 81943068672000.0,
230
  "train_batch_size": 2,
231
  "trial_name": null,
232
  "trial_params": null
 
1
  {
2
  "best_metric": 11.732924461364746,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-25",
4
+ "epoch": 3.0434782608695654,
5
  "eval_steps": 25,
6
+ "global_step": 35,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
198
  "eval_samples_per_second": 329.244,
199
  "eval_steps_per_second": 85.603,
200
  "step": 25
201
+ },
202
+ {
203
+ "epoch": 2.260869565217391,
204
+ "grad_norm": 0.41943472623825073,
205
+ "learning_rate": 2.5531266972462177e-05,
206
+ "loss": 11.727,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 2.3478260869565215,
211
+ "grad_norm": 0.30778226256370544,
212
+ "learning_rate": 2.2431968285271844e-05,
213
+ "loss": 11.7349,
214
+ "step": 27
215
+ },
216
+ {
217
+ "epoch": 2.4347826086956523,
218
+ "grad_norm": 0.41284406185150146,
219
+ "learning_rate": 1.9627610736574575e-05,
220
+ "loss": 11.7235,
221
+ "step": 28
222
+ },
223
+ {
224
+ "epoch": 2.5217391304347827,
225
+ "grad_norm": 0.3407394289970398,
226
+ "learning_rate": 1.7143591022596845e-05,
227
+ "loss": 11.7292,
228
+ "step": 29
229
+ },
230
+ {
231
+ "epoch": 2.608695652173913,
232
+ "grad_norm": 0.3608567416667938,
233
+ "learning_rate": 1.5002404810528451e-05,
234
+ "loss": 11.7284,
235
+ "step": 30
236
+ },
237
+ {
238
+ "epoch": 2.6956521739130435,
239
+ "grad_norm": 0.45119020342826843,
240
+ "learning_rate": 1.3223443014276737e-05,
241
+ "loss": 11.7181,
242
+ "step": 31
243
+ },
244
+ {
245
+ "epoch": 2.782608695652174,
246
+ "grad_norm": 0.2931600511074066,
247
+ "learning_rate": 1.1822816187347623e-05,
248
+ "loss": 11.7303,
249
+ "step": 32
250
+ },
251
+ {
252
+ "epoch": 2.869565217391304,
253
+ "grad_norm": 0.37363865971565247,
254
+ "learning_rate": 1.08132086231782e-05,
255
+ "loss": 11.7227,
256
+ "step": 33
257
+ },
258
+ {
259
+ "epoch": 2.9565217391304346,
260
+ "grad_norm": 0.4954981505870819,
261
+ "learning_rate": 1.0203763484211195e-05,
262
+ "loss": 11.7118,
263
+ "step": 34
264
+ },
265
+ {
266
+ "epoch": 3.0434782608695654,
267
+ "grad_norm": 0.5208255052566528,
268
+ "learning_rate": 1e-05,
269
+ "loss": 17.5469,
270
+ "step": 35
271
  }
272
  ],
273
  "logging_steps": 1,
 
291
  "should_evaluate": false,
292
  "should_log": false,
293
  "should_save": true,
294
+ "should_training_stop": true
295
  },
296
  "attributes": {}
297
  }
298
  },
299
+ "total_flos": 114720296140800.0,
300
  "train_batch_size": 2,
301
  "trial_name": null,
302
  "trial_params": null