Synth-Ecosystem commited on
Commit
7806c81
·
verified ·
1 Parent(s): d6db075

Training in progress, step 300, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20b199eb53ca5ff886ff2485160d53f7d8bc5596d61624233a192c908be7ae00
3
  size 38572808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64b76747407c4e35f82034686c204e47c073dcbd4896d28d888988234fd4be93
3
  size 38572808
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4c1645faea5f6e096fab3c17a893e77c4948be28c56b5f8e47a1d50d10d8d1f2
3
- size 39471301
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df890ec8e4a14bf7d664d8fd147f1541aec59d062ef9c7e66534fdd2527e739f
3
+ size 39471557
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3f1f932f434f44ee930de4d6150dd0c69ad010231e32e115cfbbb02bc9df0d63
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18efa3d16ff8a661446c6070fb2493803837ba9e7ee897995792e655b332ffc8
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c908bc08970231c3514b0be5cb33ab2ef9db64988e52cbff0c0c8b51985ccf2d
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90d8c8575f4efeeaec2cef3c0422fa1c701b9e4c6a42193dced73fa5ae08ddb0
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.4,
6
  "eval_steps": 500,
7
- "global_step": 250,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -258,6 +258,56 @@
258
  "mean_token_accuracy": 0.7014128029346466,
259
  "num_tokens": 607581.0,
260
  "step": 250
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
261
  }
262
  ],
263
  "logging_steps": 10,
@@ -272,12 +322,12 @@
272
  "should_evaluate": false,
273
  "should_log": false,
274
  "should_save": true,
275
- "should_training_stop": false
276
  },
277
  "attributes": {}
278
  }
279
  },
280
- "total_flos": 6715373241016320.0,
281
  "train_batch_size": 2,
282
  "trial_name": null,
283
  "trial_params": null
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.48,
6
  "eval_steps": 500,
7
+ "global_step": 300,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
258
  "mean_token_accuracy": 0.7014128029346466,
259
  "num_tokens": 607581.0,
260
  "step": 250
261
+ },
262
+ {
263
+ "entropy": 1.2327990546822547,
264
+ "epoch": 0.416,
265
+ "grad_norm": 1.640625,
266
+ "learning_rate": 2.46e-05,
267
+ "loss": 1.3629666328430177,
268
+ "mean_token_accuracy": 0.7295151136815547,
269
+ "num_tokens": 630821.0,
270
+ "step": 260
271
+ },
272
+ {
273
+ "entropy": 1.2706819713115691,
274
+ "epoch": 0.432,
275
+ "grad_norm": 1.90625,
276
+ "learning_rate": 1.86e-05,
277
+ "loss": 1.3413145065307617,
278
+ "mean_token_accuracy": 0.7252940103411675,
279
+ "num_tokens": 654722.0,
280
+ "step": 270
281
+ },
282
+ {
283
+ "entropy": 1.4314473286271094,
284
+ "epoch": 0.448,
285
+ "grad_norm": 1.7421875,
286
+ "learning_rate": 1.2600000000000001e-05,
287
+ "loss": 1.48402681350708,
288
+ "mean_token_accuracy": 0.6887813597917557,
289
+ "num_tokens": 680750.0,
290
+ "step": 280
291
+ },
292
+ {
293
+ "entropy": 1.2526817061007023,
294
+ "epoch": 0.464,
295
+ "grad_norm": 1.7421875,
296
+ "learning_rate": 6.6e-06,
297
+ "loss": 1.2900440216064453,
298
+ "mean_token_accuracy": 0.7276664525270462,
299
+ "num_tokens": 704141.0,
300
+ "step": 290
301
+ },
302
+ {
303
+ "entropy": 1.272147350013256,
304
+ "epoch": 0.48,
305
+ "grad_norm": 1.609375,
306
+ "learning_rate": 6.000000000000001e-07,
307
+ "loss": 1.3638032913208007,
308
+ "mean_token_accuracy": 0.7200124055147171,
309
+ "num_tokens": 727493.0,
310
+ "step": 300
311
  }
312
  ],
313
  "logging_steps": 10,
 
322
  "should_evaluate": false,
323
  "should_log": false,
324
  "should_save": true,
325
+ "should_training_stop": true
326
  },
327
  "attributes": {}
328
  }
329
  },
330
+ "total_flos": 8051407652167680.0,
331
  "train_batch_size": 2,
332
  "trial_name": null,
333
  "trial_params": null