Hugging Face's logo

VERSIL91
/
f4cb19e1-6284-4dfd-bfad-aeb02145971b

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
VERSIL91 commited on
Commit
3df3dfc
·
verified ·
1 Parent(s): f752b4b

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:a63c866be78a5507838cf9ed6d2370939f5285aa8025fcf4f7fc1303f1f9b39d
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e5add5e4e8e810358983998a93d6cf82a5e333a92b46e1d7b5b9870639f8b0
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6afe930a667f88ffc18bf5b2a8d88dbdc328b2d8a6a98a8343c8e7a509e9e7e
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:474a1acb573ccb61e74c5b8e5bb189c8648d515fa64ba9793e4bc66d14869435
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": 0.01161524500907441,
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": 9.1,
38
  "eval_steps_per_second": 4.55,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 2450672628793344.0,
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": 0.02323049001814882,
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": 9.1,
38
  "eval_steps_per_second": 4.55,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.017422867513611617,
43
+ "grad_norm": 0.2661491930484772,
44
+ "learning_rate": 3e-05,
45
+ "loss": 0.1341,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.02323049001814882,
50
+ "grad_norm": 0.29491162300109863,
51
+ "learning_rate": 4e-05,
52
+ "loss": 0.1437,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.02323049001814882,
57
+ "eval_loss": 0.16717557609081268,
58
+ "eval_runtime": 33.6736,
59
+ "eval_samples_per_second": 8.612,
60
+ "eval_steps_per_second": 4.306,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 4808867045179392.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null