Synth-Ecosystem commited on
Commit
cfbf5cf
·
verified ·
1 Parent(s): 26cb7b0

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 sha256:8feb84eacadaeaf8e98e8a7c1a838e5662b2b69593f5240e5b8330556cc9ff1b
3
  size 38572808
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ce8fb85b2d6d6dca2a7b20907f6d46f5c3d26b039f334039ac39c891c807b86
3
  size 38572808
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2ab715bbce146624b867a93412355eae1c9c01ab846953f4599861c0ddd4d83
3
- size 39471301
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7afc72d5ad1e6d034ab71347c3a6bd936da301f43a3e3d963f266eefd4a4f699
3
+ size 39471557
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:23c3bda91e6b5838f4b6551fd4664b7f59653d4b01391f80f2d451cccd9e9f7d
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b97fef9c45b91e414e5a6a20ca9c347eb1ec422c16342c1d064be5af1646dcc2
3
  size 14645
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4126303594c6410c313b8443df73e03152401f5942b059caacb2dbe69b5f5476
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d15d3d1b8bb19162d239033d431d77f4eba28beb04ec2c0ba04b41fbc223a133
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": 0.3333333333333333,
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": 0.6569280102849007,
259
  "num_tokens": 611997.0,
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": 6724518032916480.0,
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": 0.4,
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": 0.6569280102849007,
259
  "num_tokens": 611997.0,
260
  "step": 250
261
+ },
262
+ {
263
+ "entropy": 1.575335244834423,
264
+ "epoch": 0.3466666666666667,
265
+ "grad_norm": 1.9140625,
266
+ "learning_rate": 9.076389095293148e-06,
267
+ "loss": 1.661993408203125,
268
+ "mean_token_accuracy": 0.6791604168713092,
269
+ "num_tokens": 635738.0,
270
+ "step": 260
271
+ },
272
+ {
273
+ "entropy": 1.5568553388118744,
274
+ "epoch": 0.36,
275
+ "grad_norm": 1.9609375,
276
+ "learning_rate": 5.223158999041444e-06,
277
+ "loss": 1.647868537902832,
278
+ "mean_token_accuracy": 0.6698598384857177,
279
+ "num_tokens": 661213.0,
280
+ "step": 270
281
+ },
282
+ {
283
+ "entropy": 1.6810176253318787,
284
+ "epoch": 0.37333333333333335,
285
+ "grad_norm": 1.8125,
286
+ "learning_rate": 2.4083238061252567e-06,
287
+ "loss": 1.7396528244018554,
288
+ "mean_token_accuracy": 0.6562017723917961,
289
+ "num_tokens": 687385.0,
290
+ "step": 280
291
+ },
292
+ {
293
+ "entropy": 1.4571127824485302,
294
+ "epoch": 0.38666666666666666,
295
+ "grad_norm": 1.9765625,
296
+ "learning_rate": 6.627234399603555e-07,
297
+ "loss": 1.5080466270446777,
298
+ "mean_token_accuracy": 0.7004829131066799,
299
+ "num_tokens": 710784.0,
300
+ "step": 290
301
+ },
302
+ {
303
+ "entropy": 1.5088843926787376,
304
+ "epoch": 0.4,
305
+ "grad_norm": 1.3515625,
306
+ "learning_rate": 5.483063448785686e-09,
307
+ "loss": 1.5843584060668945,
308
+ "mean_token_accuracy": 0.6871048331260681,
309
+ "num_tokens": 734496.0,
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": 8071307864678400.0,
331
  "train_batch_size": 2,
332
  "trial_name": null,
333
  "trial_params": null