Hugging Face's logo

phungkhaccuong
/
003a17bd-999b-df7b-8f1c-ae6ee5673233

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
phungkhaccuong commited on
Commit
df03a34
·
verified ·
1 Parent(s): 3478588

Training in progress, step 26, 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 +32 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4f7c5f58a6468d1e4bd819ad3d8ea3fbc7ad2ea24833718589729e962b137319
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e5bc2f427dcef3d166ea8919861d490ce33a9af695fb6e68d7dcd28d69f477f
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:69c1041e5acf0b24da8066a88ae71ee68e52608cf7ae959de9e46626fb390739
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:538a130181ff2c56412a871710c36a771faa21e9741dc97b206296d6d1d4b91a
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:b798e6662462d638e0866d22f0d0054842d13e4feb4f531aad31c838c917bd3b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67732d0b1b140745be2576405ceacad957f7f919a2a6293474020ef9f1c67c81
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
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": 0.036011080332409975,
5
  "eval_steps": 10,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,35 @@
37
  "eval_samples_per_second": 13.449,
38
  "eval_steps_per_second": 6.769,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 2959302797033472.0,
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": 0.07202216066481995,
5
  "eval_steps": 10,
6
+ "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
37
  "eval_samples_per_second": 13.449,
38
  "eval_steps_per_second": 6.769,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.04155124653739612,
43
+ "grad_norm": 0.6403104662895203,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 0.6981,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.055401662049861494,
50
+ "grad_norm": 0.5902954339981079,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 0.6614,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.055401662049861494,
57
+ "eval_loss": 0.763834536075592,
58
+ "eval_runtime": 11.7356,
59
+ "eval_samples_per_second": 13.037,
60
+ "eval_steps_per_second": 6.561,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.06925207756232687,
65
+ "grad_norm": 0.5696752071380615,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 0.6615,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 5872366487863296.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null