clarxus commited on
Commit
8957e7d
·
verified ·
1 Parent(s): b346465

Training in progress, step 99, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ef19d9f243399c3d2c941fc985949d6a3e2e61a1246433bd2697e170137baca
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:622b0e2f78e992b50e3b5a6e3cb3294baa5fa205cfbe51d5dbd42313d5d40911
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:930d3e468372e83b6d0bb5b88765915033ac06b5fe0ca618a2a79ddd3e4ea9f4
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b9368481a48160f0cbb1323e02572df9e86b9aacdf8ef842642ec8afda59e11
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5051a0e31a9165b3b43ecaf91c64aba598ba8800af01edf71cd1ee48db7cb7f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f0195db21e9fddf5284f51a9c8408cef27c5c73fc46fcd57d4fff9429d9abe3
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
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": 0.04920049200492005,
5
  "eval_steps": 9,
6
- "global_step": 90,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -305,6 +305,35 @@
305
  "eval_samples_per_second": 7.29,
306
  "eval_steps_per_second": 0.913,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 2.3568005266931712e+17,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.05412054120541206,
5
  "eval_steps": 9,
6
+ "global_step": 99,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
305
  "eval_samples_per_second": 7.29,
306
  "eval_steps_per_second": 0.913,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.05084050840508405,
311
+ "grad_norm": 0.1621209979057312,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 0.6047,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.05248052480524805,
318
+ "grad_norm": 0.2111944705247879,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 0.6373,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.05412054120541206,
325
+ "grad_norm": 0.21620243787765503,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 0.6462,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.05412054120541206,
332
+ "eval_loss": 0.6008464694023132,
333
+ "eval_runtime": 422.5542,
334
+ "eval_samples_per_second": 7.291,
335
+ "eval_steps_per_second": 0.913,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 2.594794408771584e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null