Hugging Face's logo

chauhoang
/
f4ceaa19-6420-4b44-a08d-f9e4b1bc8dc3

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
chauhoang commited on
Commit
21778c8
·
verified ·
1 Parent(s): c2343c9

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 sha256:57a0bcf1e955d5338d02e5c3338d6dbc8ff25407c232dfa69ccbb2329edb22a7
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0c9a09197c226fac202745db631dfc90ffe14dffa3fcc19245c057b67c10285
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f9741ee8f31d49ce70cb502125b2b9e7543e260291f5e4f2a389e8f5726b747
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a913c1f75cfe17bddd242e6512500819d31d34927cb81cc16da6d3412665ebb
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:ada9b88cecb69c9d2d8d4079789122084e4f2f601b6cf82350a60242621e3280
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d99c1d1224da0412675feecfbb86d16ad950c12e50186da4fa4c819eb75a71b9
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": 0.00022570032205699802,
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": 15.521,
38
  "eval_steps_per_second": 7.76,
39
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 5,
@@ -56,7 +85,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 2278512597663744.0,
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": 0.00045140064411399605,
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": 15.521,
38
  "eval_steps_per_second": 7.76,
39
  "step": 10
40
+ },
41
+ {
42
+ "epoch": 0.0002604234485273054,
43
+ "grad_norm": 30.663660049438477,
44
+ "learning_rate": 9.619397662556435e-05,
45
+ "loss": 7.1643,
46
+ "step": 15
47
+ },
48
+ {
49
+ "epoch": 0.00034723126470307384,
50
+ "grad_norm": 31.651548385620117,
51
+ "learning_rate": 8.535533905932738e-05,
52
+ "loss": 6.5708,
53
+ "step": 20
54
+ },
55
+ {
56
+ "epoch": 0.00034723126470307384,
57
+ "eval_loss": 1.364366888999939,
58
+ "eval_runtime": 1565.5286,
59
+ "eval_samples_per_second": 15.491,
60
+ "eval_steps_per_second": 7.746,
61
+ "step": 20
62
+ },
63
+ {
64
+ "epoch": 0.00043403908087884236,
65
+ "grad_norm": 27.65591812133789,
66
+ "learning_rate": 6.91341716182545e-05,
67
+ "loss": 5.2812,
68
+ "step": 25
69
  }
70
  ],
71
  "logging_steps": 5,
 
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 4557025195327488.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null