Hugging Face's logo

VERSIL91
/
a73cd65f-c4ea-44cd-99e5-2c6543d25c0a

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
VERSIL91 commited on
Commit
c5f8af9
·
verified ·
1 Parent(s): daf07be

Training in progress, step 4, 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 +25 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1e6dc718d6d658f7f7140484cbe76aff4490a579e0e0002161e76f580913bc9
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93cdd6a9573725d23a5fb1307a021fd563ab08afac32286f1a6a54a1c0e5bc2d
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:803c8618cc312b461a00977cc1ae9e7232cdeec2c3bc66c9efd3fbdab4b696b3
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f26a9002258b894524abdf51b9d4401c9ec4c183bd066cd6c157da382a7bfb51
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4bbba064701c6c5641a803b1cc6ad3663ec5a37b46a361f1a3f2ad360548d26
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39dd70f78833b407302ec7a08a5ddbe1954a321879cf7446f5acb83d55b840c1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
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": 0.0024330900243309003,
5
  "eval_steps": 2,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,28 @@
37
  "eval_samples_per_second": 12.735,
38
  "eval_steps_per_second": 6.372,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 2959354336641024.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.004866180048661801,
5
  "eval_steps": 2,
6
+ "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 12.735,
38
  "eval_steps_per_second": 6.372,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0036496350364963502,
43
+ "grad_norm": 5.465456008911133,
44
+ "learning_rate": 3e-05,
45
+ "loss": 6.5394,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.004866180048661801,
50
+ "grad_norm": 5.515636444091797,
51
+ "learning_rate": 4e-05,
52
+ "loss": 6.0983,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.004866180048661801,
57
+ "eval_loss": 6.56418514251709,
58
+ "eval_runtime": 90.214,
59
+ "eval_samples_per_second": 15.352,
60
+ "eval_steps_per_second": 7.682,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 5918708673282048.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null