Hugging Face's logo

jssky
/
238ec547-f0ea-41ec-8698-c226d400b415

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
238ec547-f0ea-41ec-8698-c226d400b415
File size: 3,215 Bytes 
cdf9eb0
 
 
29968e0
cdf9eb0
29968e0
cdf9eb0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0e3b11f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e0354bf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
29968e0
 
 
 
 
 
 
cdf9eb0
 
 
 
 
 
 
 
 
 
 
 
 
 
29968e0
cdf9eb0
 
 
 
29968e0
cdf9eb0
 
 
 
 
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
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0003880669415474169,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.880669415474169e-05,
      "grad_norm": 0.5085901021957397,
      "learning_rate": 2e-05,
      "loss": 1.3977,
      "step": 1
    },
    {
      "epoch": 3.880669415474169e-05,
      "eval_loss": 1.444132685661316,
      "eval_runtime": 490.6111,
      "eval_samples_per_second": 11.06,
      "eval_steps_per_second": 11.06,
      "step": 1
    },
    {
      "epoch": 7.761338830948338e-05,
      "grad_norm": 0.9531174302101135,
      "learning_rate": 4e-05,
      "loss": 1.2155,
      "step": 2
    },
    {
      "epoch": 0.00011642008246422508,
      "grad_norm": 0.7220588326454163,
      "learning_rate": 6e-05,
      "loss": 1.1571,
      "step": 3
    },
    {
      "epoch": 0.00011642008246422508,
      "eval_loss": 1.4257819652557373,
      "eval_runtime": 489.878,
      "eval_samples_per_second": 11.076,
      "eval_steps_per_second": 11.076,
      "step": 3
    },
    {
      "epoch": 0.00015522677661896676,
      "grad_norm": 1.264121413230896,
      "learning_rate": 8e-05,
      "loss": 1.1042,
      "step": 4
    },
    {
      "epoch": 0.00019403347077370846,
      "grad_norm": 0.9557339549064636,
      "learning_rate": 0.0001,
      "loss": 1.25,
      "step": 5
    },
    {
      "epoch": 0.00023284016492845016,
      "grad_norm": 0.6429188847541809,
      "learning_rate": 0.00012,
      "loss": 1.2236,
      "step": 6
    },
    {
      "epoch": 0.00023284016492845016,
      "eval_loss": 1.3257832527160645,
      "eval_runtime": 489.9181,
      "eval_samples_per_second": 11.075,
      "eval_steps_per_second": 11.075,
      "step": 6
    },
    {
      "epoch": 0.00027164685908319185,
      "grad_norm": 0.8257654905319214,
      "learning_rate": 0.00014,
      "loss": 1.1723,
      "step": 7
    },
    {
      "epoch": 0.0003104535532379335,
      "grad_norm": 0.8499470353126526,
      "learning_rate": 0.00016,
      "loss": 1.1895,
      "step": 8
    },
    {
      "epoch": 0.00034926024739267525,
      "grad_norm": 1.2237374782562256,
      "learning_rate": 0.00018,
      "loss": 1.2761,
      "step": 9
    },
    {
      "epoch": 0.00034926024739267525,
      "eval_loss": 1.176152229309082,
      "eval_runtime": 490.047,
      "eval_samples_per_second": 11.072,
      "eval_steps_per_second": 11.072,
      "step": 9
    },
    {
      "epoch": 0.0003880669415474169,
      "grad_norm": 0.6154380440711975,
      "learning_rate": 0.0002,
      "loss": 0.7538,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1306268836823040.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}