Hugging Face's logo

sn56b2
/
684cf3fc-9ba3-410c-972f-3fffc34cbcc3

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
684cf3fc-9ba3-410c-972f-3fffc34cbcc3
File size: 2,508 Bytes 
62edad7
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.413333333333333,
  "eval_steps": 25,
  "global_step": 8,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.4266666666666667,
      "grad_norm": 0.3771531879901886,
      "learning_rate": 9.657457896300791e-05,
      "loss": 1.5114,
      "step": 1
    },
    {
      "epoch": 0.4266666666666667,
      "eval_loss": 1.6451466083526611,
      "eval_runtime": 0.7819,
      "eval_samples_per_second": 63.947,
      "eval_steps_per_second": 16.626,
      "step": 1
    },
    {
      "epoch": 0.8533333333333334,
      "grad_norm": 0.3707238435745239,
      "learning_rate": 8.681980515339464e-05,
      "loss": 1.5309,
      "step": 2
    },
    {
      "epoch": 1.28,
      "grad_norm": 0.6229836344718933,
      "learning_rate": 7.222075445642904e-05,
      "loss": 2.5315,
      "step": 3
    },
    {
      "epoch": 1.7066666666666666,
      "grad_norm": 0.33465805649757385,
      "learning_rate": 5.500000000000001e-05,
      "loss": 1.4436,
      "step": 4
    },
    {
      "epoch": 2.1333333333333333,
      "grad_norm": 0.7068106532096863,
      "learning_rate": 3.777924554357096e-05,
      "loss": 2.3019,
      "step": 5
    },
    {
      "epoch": 2.56,
      "grad_norm": 0.3285045027732849,
      "learning_rate": 2.3180194846605367e-05,
      "loss": 1.3547,
      "step": 6
    },
    {
      "epoch": 2.986666666666667,
      "grad_norm": 0.49455106258392334,
      "learning_rate": 1.3425421036992098e-05,
      "loss": 2.0087,
      "step": 7
    },
    {
      "epoch": 3.413333333333333,
      "grad_norm": 0.29395291209220886,
      "learning_rate": 1e-05,
      "loss": 1.3329,
      "step": 8
    }
  ],
  "logging_steps": 1,
  "max_steps": 8,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 25,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.6952581662179328e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}