Hugging Face's logo

tuanna08go
/
8d71750f-4381-4439-b4c9-b191859e6304

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
8d71750f-4381-4439-b4c9-b191859e6304
File size: 2,631 Bytes 
3483411
 
 
d4301c8
183f24c
d4301c8
3483411
 
 
 
 
 
 
183f24c
 
 
3483411
183f24c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
535d009
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4636ff2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d4301c8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3483411
 
 
183f24c
3483411
 
183f24c
3483411
 
 
 
 
 
 
d4301c8
3483411
 
 
 
d4301c8
3483411
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 9,
  "global_step": 45,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022222222222222223,
      "eval_loss": 1.8410741090774536,
      "eval_runtime": 16.746,
      "eval_samples_per_second": 18.094,
      "eval_steps_per_second": 2.269,
      "step": 1
    },
    {
      "epoch": 0.2,
      "eval_loss": 1.0834723711013794,
      "eval_runtime": 15.6719,
      "eval_samples_per_second": 19.334,
      "eval_steps_per_second": 2.425,
      "step": 9
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 1.0347282886505127,
      "learning_rate": 9.16998908944939e-05,
      "loss": 1.536,
      "step": 10
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.5606896281242371,
      "eval_runtime": 15.6642,
      "eval_samples_per_second": 19.343,
      "eval_steps_per_second": 2.426,
      "step": 18
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.5371178388595581,
      "learning_rate": 6.264666911958404e-05,
      "loss": 0.689,
      "step": 20
    },
    {
      "epoch": 0.6,
      "eval_loss": 0.47360849380493164,
      "eval_runtime": 15.691,
      "eval_samples_per_second": 19.31,
      "eval_steps_per_second": 2.422,
      "step": 27
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.3193366229534149,
      "learning_rate": 2.7137883834768073e-05,
      "loss": 0.4522,
      "step": 30
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.4535110592842102,
      "eval_runtime": 15.7131,
      "eval_samples_per_second": 19.283,
      "eval_steps_per_second": 2.418,
      "step": 36
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.3237155079841614,
      "learning_rate": 3.299194563372604e-06,
      "loss": 0.443,
      "step": 40
    },
    {
      "epoch": 1.0,
      "eval_loss": 0.4497634768486023,
      "eval_runtime": 15.6856,
      "eval_samples_per_second": 19.317,
      "eval_steps_per_second": 2.423,
      "step": 45
    }
  ],
  "logging_steps": 10,
  "max_steps": 45,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 12,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.254044464667689e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}