Hugging Face's logo

ClarenceDan
/
a431f576-f65d-49c6-8671-6255c4c98181

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
a431f576-f65d-49c6-8671-6255c4c98181
File size: 2,976 Bytes 
c625e9b
 
 
949cf98
c625e9b
949cf98
c625e9b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e2aa981
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ff50f7e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
949cf98
 
 
 
 
 
 
c625e9b
 
 
 
 
 
 
 
 
 
 
 
 
 
949cf98
c625e9b
 
 
 
949cf98
c625e9b
 
 
 
 
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": 0.00014775031673974152,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.4775031673974151e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 1.4775031673974151e-05,
      "eval_loss": NaN,
      "eval_runtime": 480.2526,
      "eval_samples_per_second": 59.34,
      "eval_steps_per_second": 29.67,
      "step": 1
    },
    {
      "epoch": 2.9550063347948303e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 4.432509502192245e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 4.432509502192245e-05,
      "eval_loss": NaN,
      "eval_runtime": 484.0028,
      "eval_samples_per_second": 58.88,
      "eval_steps_per_second": 29.44,
      "step": 3
    },
    {
      "epoch": 5.9100126695896606e-05,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 7.387515836987076e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 8.86501900438449e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 8.86501900438449e-05,
      "eval_loss": NaN,
      "eval_runtime": 487.2274,
      "eval_samples_per_second": 58.49,
      "eval_steps_per_second": 29.245,
      "step": 6
    },
    {
      "epoch": 0.00010342522171781905,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00011820025339179321,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00013297528506576737,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00013297528506576737,
      "eval_loss": NaN,
      "eval_runtime": 482.7792,
      "eval_samples_per_second": 59.029,
      "eval_steps_per_second": 29.515,
      "step": 9
    },
    {
      "epoch": 0.00014775031673974152,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 89038163804160.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}