Hugging Face's logo

tuanna08go
/
2ef1e1a4-26ca-421b-88f2-e27390147b1d

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuanna08go commited on
Commit
faa147e
·
verified ·
1 Parent(s): 48720f5

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:a72306235e2e35f29a634e0f6e3f5453f61db68c6cb2ca894231609c69c9fb2d
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6e1a1d17c7a7aa59a5f62869bb34def62e70b2fc3e0d69e617de7560d90c51
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:020706d9f8910de4218b6c0bcc31a9b295d6dc97880a5d060667e96057a78d37
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a36b01500baa7ddb5610cb7a0a2c63c747700841023a39795937c13ae6f7c103
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:a5cba764fcb0e7f18b6d06759624dccc13afd567f3245791b3de96f9fcfce3c5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72d2123828a202521fed49695ce20694823d9999d33262dd05d88a1ab8cbe183
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": 0.02979942693409742,
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": 5.353,
38
  "eval_steps_per_second": 2.677,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 4556946677956608.0,
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": 0.05959885386819484,
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": 5.353,
38
  "eval_steps_per_second": 2.677,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.034383954154727794,
43
+ "grad_norm": 4.626423358917236,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 2.0376,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.045845272206303724,
50
+ "grad_norm": 4.920547008514404,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 1.7548,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.045845272206303724,
57
+ "eval_loss": 0.4074614942073822,
58
+ "eval_runtime": 35.1925,
59
+ "eval_samples_per_second": 5.228,
60
+ "eval_steps_per_second": 2.614,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.05730659025787966,
65
+ "grad_norm": 4.158402919769287,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 1.5327,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 9113893355913216.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null