Hugging Face's logo

ClarenceDan
/
0d8acc6b-fc94-459a-97ae-9c06637df258

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
0d8acc6b-fc94-459a-97ae-9c06637df258
File size: 2,345 Bytes 
863c3bb
 
 
6082ae1
863c3bb
6082ae1
863c3bb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6082ae1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
863c3bb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6082ae1
863c3bb
 
 
 
 
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
94
95
96
97
98
99
100
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0031809145129224653,
  "eval_steps": 3,
  "global_step": 6,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0005301524188204108,
      "grad_norm": 0.539082407951355,
      "learning_rate": 2e-05,
      "loss": 1.4404,
      "step": 1
    },
    {
      "epoch": 0.0005301524188204108,
      "eval_loss": 1.6137040853500366,
      "eval_runtime": 70.4487,
      "eval_samples_per_second": 11.285,
      "eval_steps_per_second": 5.65,
      "step": 1
    },
    {
      "epoch": 0.0010603048376408217,
      "grad_norm": 0.5260076522827148,
      "learning_rate": 4e-05,
      "loss": 1.4584,
      "step": 2
    },
    {
      "epoch": 0.0015904572564612327,
      "grad_norm": 0.522720217704773,
      "learning_rate": 6e-05,
      "loss": 1.5979,
      "step": 3
    },
    {
      "epoch": 0.0015904572564612327,
      "eval_loss": 1.6069713830947876,
      "eval_runtime": 66.2061,
      "eval_samples_per_second": 12.008,
      "eval_steps_per_second": 6.012,
      "step": 3
    },
    {
      "epoch": 0.0021206096752816434,
      "grad_norm": 0.6277130842208862,
      "learning_rate": 8e-05,
      "loss": 1.666,
      "step": 4
    },
    {
      "epoch": 0.0026507620941020544,
      "grad_norm": 0.7468717694282532,
      "learning_rate": 0.0001,
      "loss": 1.6473,
      "step": 5
    },
    {
      "epoch": 0.0031809145129224653,
      "grad_norm": 1.006897211074829,
      "learning_rate": 0.00012,
      "loss": 1.7221,
      "step": 6
    },
    {
      "epoch": 0.0031809145129224653,
      "eval_loss": 1.4851133823394775,
      "eval_runtime": 66.272,
      "eval_samples_per_second": 11.996,
      "eval_steps_per_second": 6.006,
      "step": 6
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3462976744980480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}