Hugging Face's logo

dimasik87
/
7e2b7022-0bfa-480d-b146-b5e0c308b56e

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
7e2b7022-0bfa-480d-b146-b5e0c308b56e
File size: 2,981 Bytes 
6e80129
 
 
dc8c7ca
6e80129
dc8c7ca
6e80129
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7905a5f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bf2a4a0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dc8c7ca
 
 
 
 
 
 
6e80129
 
 
 
 
 
 
 
 
 
 
 
 
 
dc8c7ca
6e80129
 
 
 
dc8c7ca
6e80129
 
 
 
 
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": 0.0004279035933204249,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.279035933204249e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 4.279035933204249e-05,
      "eval_loss": NaN,
      "eval_runtime": 443.5808,
      "eval_samples_per_second": 22.183,
      "eval_steps_per_second": 11.092,
      "step": 1
    },
    {
      "epoch": 8.558071866408498e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.00012837107799612747,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.00012837107799612747,
      "eval_loss": NaN,
      "eval_runtime": 443.6788,
      "eval_samples_per_second": 22.178,
      "eval_steps_per_second": 11.089,
      "step": 3
    },
    {
      "epoch": 0.00017116143732816996,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.00021395179666021245,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.00025674215599225494,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.00025674215599225494,
      "eval_loss": NaN,
      "eval_runtime": 443.4752,
      "eval_samples_per_second": 22.188,
      "eval_steps_per_second": 11.094,
      "step": 6
    },
    {
      "epoch": 0.0002995325153242974,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.0003423228746563399,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.0003851132339883824,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.0003851132339883824,
      "eval_loss": NaN,
      "eval_runtime": 443.6013,
      "eval_samples_per_second": 22.182,
      "eval_steps_per_second": 11.091,
      "step": 9
    },
    {
      "epoch": 0.0004279035933204249,
      "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": 1338925557743616.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}