Hugging Face's logo

VERSIL91
/
51f29004-8b85-486d-bd75-d545b853ac63

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
51f29004-8b85-486d-bd75-d545b853ac63
File size: 2,185 Bytes 
63edc10
 
 
c75bd03
63edc10
c75bd03
63edc10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7cf782d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c75bd03
 
 
 
 
 
 
63edc10
 
 
 
 
 
 
 
 
 
 
 
 
 
c75bd03
63edc10
 
 
 
c75bd03
63edc10
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002373675933893125,
  "eval_steps": 2,
  "global_step": 5,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00047473518677862507,
      "grad_norm": 0.6019813418388367,
      "learning_rate": 1e-05,
      "loss": 1.0139,
      "step": 1
    },
    {
      "epoch": 0.00047473518677862507,
      "eval_loss": 1.0513094663619995,
      "eval_runtime": 739.5377,
      "eval_samples_per_second": 4.798,
      "eval_steps_per_second": 2.399,
      "step": 1
    },
    {
      "epoch": 0.0009494703735572501,
      "grad_norm": 0.6246649622917175,
      "learning_rate": 2e-05,
      "loss": 1.15,
      "step": 2
    },
    {
      "epoch": 0.0009494703735572501,
      "eval_loss": 1.028988003730774,
      "eval_runtime": 352.9218,
      "eval_samples_per_second": 10.053,
      "eval_steps_per_second": 5.027,
      "step": 2
    },
    {
      "epoch": 0.0014242055603358751,
      "grad_norm": 0.631195068359375,
      "learning_rate": 3e-05,
      "loss": 1.1129,
      "step": 3
    },
    {
      "epoch": 0.0018989407471145003,
      "grad_norm": 0.6286895275115967,
      "learning_rate": 4e-05,
      "loss": 1.044,
      "step": 4
    },
    {
      "epoch": 0.0018989407471145003,
      "eval_loss": 1.0063300132751465,
      "eval_runtime": 319.2481,
      "eval_samples_per_second": 11.114,
      "eval_steps_per_second": 5.557,
      "step": 4
    },
    {
      "epoch": 0.002373675933893125,
      "grad_norm": 0.6102349162101746,
      "learning_rate": 5e-05,
      "loss": 1.0684,
      "step": 5
    }
  ],
  "logging_steps": 1,
  "max_steps": 5,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 2,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3485272092180480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}