Hugging Face's logo

tuanna08go
/
8df55108-f0a4-4ba4-9a4a-ef3372f21615

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
8df55108-f0a4-4ba4-9a4a-ef3372f21615
File size: 2,792 Bytes 
5a63465
 
 
ce54c04
449f5f1
ce54c04
5a63465
 
 
 
 
 
 
449f5f1
 
 
5a63465
449f5f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
381645d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ce54c04
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5a63465
 
 
449f5f1
5a63465
 
449f5f1
5a63465
 
 
 
 
 
 
449f5f1
5a63465
 
 
 
ce54c04
5a63465
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07858942065491184,
  "eval_steps": 10,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0020151133501259445,
      "eval_loss": 11.928855895996094,
      "eval_runtime": 2.8749,
      "eval_samples_per_second": 72.699,
      "eval_steps_per_second": 36.523,
      "step": 1
    },
    {
      "epoch": 0.010075566750629723,
      "grad_norm": 0.01261623203754425,
      "learning_rate": 5e-05,
      "loss": 11.9283,
      "step": 5
    },
    {
      "epoch": 0.020151133501259445,
      "grad_norm": 0.008780092932283878,
      "learning_rate": 0.0001,
      "loss": 11.9228,
      "step": 10
    },
    {
      "epoch": 0.020151133501259445,
      "eval_loss": 11.928825378417969,
      "eval_runtime": 2.8934,
      "eval_samples_per_second": 72.232,
      "eval_steps_per_second": 36.289,
      "step": 10
    },
    {
      "epoch": 0.030226700251889168,
      "grad_norm": 0.01207203883677721,
      "learning_rate": 9.619397662556435e-05,
      "loss": 11.9282,
      "step": 15
    },
    {
      "epoch": 0.04030226700251889,
      "grad_norm": 0.006873443257063627,
      "learning_rate": 8.535533905932738e-05,
      "loss": 11.9286,
      "step": 20
    },
    {
      "epoch": 0.04030226700251889,
      "eval_loss": 11.92874813079834,
      "eval_runtime": 2.9679,
      "eval_samples_per_second": 70.421,
      "eval_steps_per_second": 35.379,
      "step": 20
    },
    {
      "epoch": 0.05037783375314862,
      "grad_norm": 0.007669125683605671,
      "learning_rate": 6.91341716182545e-05,
      "loss": 11.9293,
      "step": 25
    },
    {
      "epoch": 0.060453400503778336,
      "grad_norm": 0.008746370673179626,
      "learning_rate": 5e-05,
      "loss": 11.929,
      "step": 30
    },
    {
      "epoch": 0.060453400503778336,
      "eval_loss": 11.928698539733887,
      "eval_runtime": 2.928,
      "eval_samples_per_second": 71.381,
      "eval_steps_per_second": 35.861,
      "step": 30
    },
    {
      "epoch": 0.07052896725440806,
      "grad_norm": 0.004675919655710459,
      "learning_rate": 3.086582838174551e-05,
      "loss": 11.9269,
      "step": 35
    }
  ],
  "logging_steps": 5,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8743944192.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}