Hugging Face's logo

tryingpro
/
fff4bb41-fbd1-4606-80cd-29d5047ddf58

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
tryingpro commited on
Commit
e58d6bd
·
verified ·
1 Parent(s): fddbc29

Training in progress, step 90, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +11 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:768db4d21385826b525ded38563713ad67afaf060bd313b935d5d55d323538b6
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d51d01cd28ffffede4d67315a70f36cbf6dd8bc654acc19109ddd440ae49e2c4
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cd2ee98ef0299a10a7e1bd426de675a5958b0827775c524e33f14b14fcebb01
3
  size 671466706
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f50012ef35e237fa090e9f634f291bea9439f689f6be04207fc58eed5f7d1f71
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:fd0f16ba53ff18dd96e0c7bcdd0d6d91883558662e2adf70806364bb3a367ccc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:66640f67e35401b61394a4774320637b5a5845978a7e68acd58191912f1779a1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01a4e7013bdf0cfef44b18348c4082377d680816016af2638e8995bf0bb3c8d9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf6a9a1e39c0655c6941309388d2a028b5b8dbbca031ca2500bdfcdc9f2c01aa
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": 1.0703154694032686,
5
  "eval_steps": 8,
6
- "global_step": 88,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -306,6 +306,13 @@
306
  "eval_samples_per_second": 7.51,
307
  "eval_steps_per_second": 3.769,
308
  "step": 88
 
 
 
 
 
 
 
309
  }
310
  ],
311
  "logging_steps": 3,
@@ -320,12 +327,12 @@
320
  "should_evaluate": false,
321
  "should_log": false,
322
  "should_save": true,
323
- "should_training_stop": false
324
  },
325
  "attributes": {}
326
  }
327
  },
328
- "total_flos": 6.141531047445135e+17,
329
  "train_batch_size": 2,
330
  "trial_name": null,
331
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0946408209806158,
5
  "eval_steps": 8,
6
+ "global_step": 90,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
306
  "eval_samples_per_second": 7.51,
307
  "eval_steps_per_second": 3.769,
308
  "step": 88
309
+ },
310
+ {
311
+ "epoch": 1.0946408209806158,
312
+ "grad_norm": 0.5633111000061035,
313
+ "learning_rate": 0.0,
314
+ "loss": 1.0277,
315
+ "step": 90
316
  }
317
  ],
318
  "logging_steps": 3,
 
327
  "should_evaluate": false,
328
  "should_log": false,
329
  "should_save": true,
330
+ "should_training_stop": true
331
  },
332
  "attributes": {}
333
  }
334
  },
335
+ "total_flos": 6.275812928834765e+17,
336
  "train_batch_size": 2,
337
  "trial_name": null,
338
  "trial_params": null