Hugging Face's logo

samoline
/
5d16dea4-0644-4f19-adb1-a08169142bc0

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
samoline commited on
Commit
3d26e5f
·
verified ·
1 Parent(s): 29617ff

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 sha256:6feb44892c57caba3ea49d51ae909f218d2bbf2506df56a50072dbdcce6ec517
3
  size 42002136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9baeb121046f4115343d35df39685cd69c2a68287e0c7173e824ce329ba6192b
3
  size 42002136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03ebaec0e136d670224c03be8c578a93a922216208480715707dfb51e2697995
3
  size 21822612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90a7e4af1b13ab92cdbc5802e5558634049001fbd3ab7cbcea39f9accf1617d4
3
  size 21822612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9131d73ce3e2071bf25b4ab32d9c084759e2eb8b9163e4aa04f0a79d9c8484f3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca292942a33fa15be81e314818ff2851b6484a4703be8f6939dc3d3e46daa1ae
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": 7.989390089960533e-06,
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": 11.095,
23
  "eval_steps_per_second": 11.095,
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": 23087743500288.0,
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": 1.5978780179921066e-05,
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": 11.095,
23
  "eval_steps_per_second": 11.095,
24
  "step": 1
25
+ },
26
+ {
27
+ "epoch": 1.5978780179921066e-05,
28
+ "grad_norm": 0.5756686925888062,
29
+ "learning_rate": 4e-05,
30
+ "loss": 0.9937,
31
+ "step": 2
32
+ },
33
+ {
34
+ "epoch": 1.5978780179921066e-05,
35
+ "eval_loss": 1.1072341203689575,
36
+ "eval_runtime": 595.0635,
37
+ "eval_samples_per_second": 11.071,
38
+ "eval_steps_per_second": 11.071,
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": 46175487000576.0,
60
  "train_batch_size": 1,
61
  "trial_name": null,
62
  "trial_params": null