Hugging Face's logo

filipesantoscv11
/
5b18091d-c4b0-4dbc-a700-8ebed727e5f5

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
5b18091d-c4b0-4dbc-a700-8ebed727e5f5
File size: 3,061 Bytes 
a2ebeea
 
 
17a91b6
a2ebeea
17a91b6
a2ebeea
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
959bf3e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17a91b6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a2ebeea
 
 
 
 
 
 
 
 
 
 
 
 
 
17a91b6
a2ebeea
 
 
 
17a91b6
a2ebeea
 
 
 
 
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": 0.0025854825156744875,
  "eval_steps": 8,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.618275052248293e-05,
      "eval_loss": NaN,
      "eval_runtime": 257.7137,
      "eval_samples_per_second": 18.959,
      "eval_steps_per_second": 9.48,
      "step": 1
    },
    {
      "epoch": 0.0002585482515674488,
      "grad_norm": NaN,
      "learning_rate": 3e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.0005170965031348976,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.0006894620041798634,
      "eval_loss": NaN,
      "eval_runtime": 256.5086,
      "eval_samples_per_second": 19.048,
      "eval_steps_per_second": 9.524,
      "step": 8
    },
    {
      "epoch": 0.0007756447547023463,
      "grad_norm": NaN,
      "learning_rate": 9e-05,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.001034193006269795,
      "grad_norm": NaN,
      "learning_rate": 9.755282581475769e-05,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.0012927412578372438,
      "grad_norm": NaN,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.0013789240083597269,
      "eval_loss": NaN,
      "eval_runtime": 256.7487,
      "eval_samples_per_second": 19.03,
      "eval_steps_per_second": 9.515,
      "step": 16
    },
    {
      "epoch": 0.0015512895094046927,
      "grad_norm": NaN,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.0018098377609721413,
      "grad_norm": NaN,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 0.0,
      "step": 21
    },
    {
      "epoch": 0.00206838601253959,
      "grad_norm": NaN,
      "learning_rate": 2.061073738537635e-05,
      "loss": 0.0,
      "step": 24
    },
    {
      "epoch": 0.00206838601253959,
      "eval_loss": NaN,
      "eval_runtime": 256.7275,
      "eval_samples_per_second": 19.032,
      "eval_steps_per_second": 9.516,
      "step": 24
    },
    {
      "epoch": 0.002326934264107039,
      "grad_norm": NaN,
      "learning_rate": 5.449673790581611e-06,
      "loss": 0.0,
      "step": 27
    },
    {
      "epoch": 0.0025854825156744875,
      "grad_norm": NaN,
      "learning_rate": 0.0,
      "loss": 0.0,
      "step": 30
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0572960236568576e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}