Hugging Face's logo

tuanna08go
/
b8cb340e-08f1-47b2-95b1-11e201efd0fd

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
b8cb340e-08f1-47b2-95b1-11e201efd0fd
File size: 2,056 Bytes 
799285a
 
 
e0538c6
db6b6b8
e0538c6
799285a
 
 
 
 
 
 
db6b6b8
 
 
799285a
db6b6b8
 
 
 
 
 
 
 
334dce4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3ffad17
 
 
 
 
 
 
 
e0538c6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
799285a
 
 
db6b6b8
799285a
db6b6b8
 
799285a
 
 
 
 
 
 
e0538c6
799285a
 
 
 
e0538c6
799285a
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0114285714285713,
  "eval_steps": 5,
  "global_step": 22,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.045714285714285714,
      "eval_loss": NaN,
      "eval_runtime": 3.8417,
      "eval_samples_per_second": 38.524,
      "eval_steps_per_second": 4.946,
      "step": 1
    },
    {
      "epoch": 0.22857142857142856,
      "eval_loss": NaN,
      "eval_runtime": 2.8524,
      "eval_samples_per_second": 51.886,
      "eval_steps_per_second": 6.661,
      "step": 5
    },
    {
      "epoch": 0.45714285714285713,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 10
    },
    {
      "epoch": 0.45714285714285713,
      "eval_loss": NaN,
      "eval_runtime": 2.9025,
      "eval_samples_per_second": 50.991,
      "eval_steps_per_second": 6.546,
      "step": 10
    },
    {
      "epoch": 0.6857142857142857,
      "eval_loss": NaN,
      "eval_runtime": 2.8482,
      "eval_samples_per_second": 51.962,
      "eval_steps_per_second": 6.671,
      "step": 15
    },
    {
      "epoch": 0.9142857142857143,
      "grad_norm": NaN,
      "learning_rate": 2.4471741852423237e-06,
      "loss": 0.0,
      "step": 20
    },
    {
      "epoch": 0.9142857142857143,
      "eval_loss": NaN,
      "eval_runtime": 2.8362,
      "eval_samples_per_second": 52.183,
      "eval_steps_per_second": 6.699,
      "step": 20
    }
  ],
  "logging_steps": 10,
  "max_steps": 22,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 6,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.1415298699689984e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}