Hugging Face's logo

trenden
/
69ba7e05-5cb7-4ec8-a2b0-a567810fb5a0

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
69ba7e05-5cb7-4ec8-a2b0-a567810fb5a0
File size: 3,188 Bytes 
3f84eeb
 
 
5f61315
3f84eeb
5f61315
3f84eeb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2a144f1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10933cc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5f61315
 
 
 
 
 
 
3f84eeb
 
 
 
 
 
 
 
 
 
 
 
 
 
5f61315
3f84eeb
 
 
 
5f61315
3f84eeb
 
 
 
 
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": 0.013067624959163672,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013067624959163672,
      "grad_norm": 1.7657692432403564,
      "learning_rate": 2e-05,
      "loss": 6.7344,
      "step": 1
    },
    {
      "epoch": 0.0013067624959163672,
      "eval_loss": 6.717371940612793,
      "eval_runtime": 16.7474,
      "eval_samples_per_second": 19.287,
      "eval_steps_per_second": 9.673,
      "step": 1
    },
    {
      "epoch": 0.0026135249918327343,
      "grad_norm": 1.6176117658615112,
      "learning_rate": 4e-05,
      "loss": 6.7046,
      "step": 2
    },
    {
      "epoch": 0.003920287487749101,
      "grad_norm": 1.6528016328811646,
      "learning_rate": 6e-05,
      "loss": 5.8803,
      "step": 3
    },
    {
      "epoch": 0.003920287487749101,
      "eval_loss": 6.710137844085693,
      "eval_runtime": 14.7271,
      "eval_samples_per_second": 21.932,
      "eval_steps_per_second": 11.0,
      "step": 3
    },
    {
      "epoch": 0.005227049983665469,
      "grad_norm": 1.8608736991882324,
      "learning_rate": 8e-05,
      "loss": 5.9868,
      "step": 4
    },
    {
      "epoch": 0.006533812479581836,
      "grad_norm": 2.0123531818389893,
      "learning_rate": 0.0001,
      "loss": 4.8973,
      "step": 5
    },
    {
      "epoch": 0.007840574975498203,
      "grad_norm": 2.2245185375213623,
      "learning_rate": 0.00012,
      "loss": 5.5564,
      "step": 6
    },
    {
      "epoch": 0.007840574975498203,
      "eval_loss": 6.524731636047363,
      "eval_runtime": 14.77,
      "eval_samples_per_second": 21.869,
      "eval_steps_per_second": 10.968,
      "step": 6
    },
    {
      "epoch": 0.00914733747141457,
      "grad_norm": 2.8602676391601562,
      "learning_rate": 0.00014,
      "loss": 5.6889,
      "step": 7
    },
    {
      "epoch": 0.010454099967330937,
      "grad_norm": 2.6527276039123535,
      "learning_rate": 0.00016,
      "loss": 5.2183,
      "step": 8
    },
    {
      "epoch": 0.011760862463247305,
      "grad_norm": 2.932201623916626,
      "learning_rate": 0.00018,
      "loss": 4.7739,
      "step": 9
    },
    {
      "epoch": 0.011760862463247305,
      "eval_loss": 5.452193260192871,
      "eval_runtime": 14.8133,
      "eval_samples_per_second": 21.805,
      "eval_steps_per_second": 10.936,
      "step": 9
    },
    {
      "epoch": 0.013067624959163672,
      "grad_norm": 2.4018781185150146,
      "learning_rate": 0.0002,
      "loss": 4.6505,
      "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": 3136744882962432.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}