Hugging Face's logo

tuanna08go
/
5b696ec5-83dd-4e5b-95fe-208381ca4316

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
5b696ec5-83dd-4e5b-95fe-208381ca4316
File size: 2,717 Bytes 
a15104b
 
 
31e495b
e62b0f6
31e495b
a15104b
 
 
 
 
 
 
e62b0f6
 
 
a15104b
e62b0f6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
df9f689
 
 
 
 
 
 
 
 
 
 
 
 
 
 
23e21da
 
 
 
 
 
 
 
 
 
 
 
 
 
 
31e495b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a15104b
 
 
e62b0f6
a15104b
 
e62b0f6
a15104b
 
 
 
 
 
 
31e495b
a15104b
 
 
 
31e495b
a15104b
 
 
 
 
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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.13018714401952808,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026037428803905613,
      "eval_loss": NaN,
      "eval_runtime": 51.0838,
      "eval_samples_per_second": 50.662,
      "eval_steps_per_second": 6.343,
      "step": 1
    },
    {
      "epoch": 0.026037428803905614,
      "grad_norm": NaN,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.026037428803905614,
      "eval_loss": NaN,
      "eval_runtime": 49.7181,
      "eval_samples_per_second": 52.053,
      "eval_steps_per_second": 6.517,
      "step": 10
    },
    {
      "epoch": 0.05207485760781123,
      "grad_norm": NaN,
      "learning_rate": 6.91341716182545e-05,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.05207485760781123,
      "eval_loss": NaN,
      "eval_runtime": 49.7341,
      "eval_samples_per_second": 52.037,
      "eval_steps_per_second": 6.515,
      "step": 20
    },
    {
      "epoch": 0.07811228641171684,
      "grad_norm": NaN,
      "learning_rate": 3.705904774487396e-05,
      "loss": 0.0,
      "step": 30
    },
    {
      "epoch": 0.07811228641171684,
      "eval_loss": NaN,
      "eval_runtime": 49.3999,
      "eval_samples_per_second": 52.389,
      "eval_steps_per_second": 6.559,
      "step": 30
    },
    {
      "epoch": 0.10414971521562245,
      "grad_norm": NaN,
      "learning_rate": 1.0332332985438248e-05,
      "loss": 0.0,
      "step": 40
    },
    {
      "epoch": 0.10414971521562245,
      "eval_loss": NaN,
      "eval_runtime": 49.4279,
      "eval_samples_per_second": 52.359,
      "eval_steps_per_second": 6.555,
      "step": 40
    },
    {
      "epoch": 0.13018714401952808,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 50
    },
    {
      "epoch": 0.13018714401952808,
      "eval_loss": NaN,
      "eval_runtime": 49.4849,
      "eval_samples_per_second": 52.299,
      "eval_steps_per_second": 6.547,
      "step": 50
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.6041150158667776e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}