Hugging Face's logo

samoline
/
fd399afe-481f-4718-8354-247be2be462

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
samoline commited on
Commit
aef664d
·
verified ·
1 Parent(s): 29a245b

Training in progress, step 2, 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 +19 -4
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9bf7c8da1a0a9bb4e13835bab8c117ab412d1abf946dbe3db105ee27e175da88
3
  size 390888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b00a5829cfa1dd2353433c295beb3712757f163ad6e2d60116e0d3d14f39594
3
  size 390888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d08eabf36135f19e82bfe300eae216099db56cb12aa33f88d6866b165ed2d31f
3
  size 819770
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d33342e81030f6c90e4555ccffd888ed5c3a11a5252c2ee1fde93fb13dfa1be
3
  size 819770
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dcf01ac002e5e1c059240ec3a55108505c59c7fc0435d3cbfc139da9dd6a344a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:764cf599d0b83c5d302be0978d09e435a466a8511dc1f7e86d5ee3704818d46f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2972d8cacb091bd0e98bfff54b2e4933301753087ce149a9bf9a205a5e2d795
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": 0.1111111111111111,
5
  "eval_steps": 1,
6
- "global_step": 1,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -22,6 +22,21 @@
22
  "eval_samples_per_second": 34.952,
23
  "eval_steps_per_second": 34.952,
24
  "step": 1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "logging_steps": 1,
@@ -36,12 +51,12 @@
36
  "should_evaluate": false,
37
  "should_log": false,
38
  "should_save": true,
39
- "should_training_stop": false
40
  },
41
  "attributes": {}
42
  }
43
  },
44
- "total_flos": 8194818048.0,
45
  "train_batch_size": 1,
46
  "trial_name": null,
47
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.2222222222222222,
5
  "eval_steps": 1,
6
+ "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
22
  "eval_samples_per_second": 34.952,
23
  "eval_steps_per_second": 34.952,
24
  "step": 1
25
+ },
26
+ {
27
+ "epoch": 0.2222222222222222,
28
+ "grad_norm": 4.1242828369140625,
29
+ "learning_rate": 4e-05,
30
+ "loss": 6.5179,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 0.2222222222222222,
35
+ "eval_loss": 6.42535924911499,
36
+ "eval_runtime": 0.028,
37
+ "eval_samples_per_second": 35.738,
38
+ "eval_steps_per_second": 35.738,
39
+ "step": 2
40
  }
41
  ],
42
  "logging_steps": 1,
 
51
  "should_evaluate": false,
52
  "should_log": false,
53
  "should_save": true,
54
+ "should_training_stop": true
55
  },
56
  "attributes": {}
57
  }
58
  },
59
+ "total_flos": 16389636096.0,
60
  "train_batch_size": 1,
61
  "trial_name": null,
62
  "trial_params": null