Hugging Face's logo

havinash-ai
/
96e6dfdf-0bef-4430-92c3-2accfd7390f3

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
96e6dfdf-0bef-4430-92c3-2accfd7390f3
File size: 3,234 Bytes 
081495a
 
 
41fa314
081495a
41fa314
081495a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9ec1b56
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ab5d848
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41fa314
 
 
 
 
 
 
081495a
 
 
 
 
 
 
 
 
 
 
 
 
 
41fa314
081495a
 
 
 
41fa314
081495a
 
 
 
 
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": 0.0017248070372127117,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00017248070372127117,
      "grad_norm": 0.04714099317789078,
      "learning_rate": 2e-05,
      "loss": 11.9346,
      "step": 1
    },
    {
      "epoch": 0.00017248070372127117,
      "eval_loss": 11.933449745178223,
      "eval_runtime": 8.4249,
      "eval_samples_per_second": 289.854,
      "eval_steps_per_second": 144.927,
      "step": 1
    },
    {
      "epoch": 0.00034496140744254234,
      "grad_norm": 0.038016416132450104,
      "learning_rate": 4e-05,
      "loss": 11.9327,
      "step": 2
    },
    {
      "epoch": 0.0005174421111638135,
      "grad_norm": 0.0610128715634346,
      "learning_rate": 6e-05,
      "loss": 11.9345,
      "step": 3
    },
    {
      "epoch": 0.0005174421111638135,
      "eval_loss": 11.933433532714844,
      "eval_runtime": 8.5079,
      "eval_samples_per_second": 287.028,
      "eval_steps_per_second": 143.514,
      "step": 3
    },
    {
      "epoch": 0.0006899228148850847,
      "grad_norm": 0.025043468922376633,
      "learning_rate": 8e-05,
      "loss": 11.9273,
      "step": 4
    },
    {
      "epoch": 0.0008624035186063559,
      "grad_norm": 0.04784798249602318,
      "learning_rate": 0.0001,
      "loss": 11.9414,
      "step": 5
    },
    {
      "epoch": 0.001034884222327627,
      "grad_norm": 0.04146360605955124,
      "learning_rate": 0.00012,
      "loss": 11.9318,
      "step": 6
    },
    {
      "epoch": 0.001034884222327627,
      "eval_loss": 11.933374404907227,
      "eval_runtime": 8.6107,
      "eval_samples_per_second": 283.602,
      "eval_steps_per_second": 141.801,
      "step": 6
    },
    {
      "epoch": 0.0012073649260488982,
      "grad_norm": 0.04689552262425423,
      "learning_rate": 0.00014,
      "loss": 11.9323,
      "step": 7
    },
    {
      "epoch": 0.0013798456297701694,
      "grad_norm": 0.040808454155921936,
      "learning_rate": 0.00016,
      "loss": 11.9289,
      "step": 8
    },
    {
      "epoch": 0.0015523263334914405,
      "grad_norm": 0.031402040272951126,
      "learning_rate": 0.00018,
      "loss": 11.9277,
      "step": 9
    },
    {
      "epoch": 0.0015523263334914405,
      "eval_loss": 11.933272361755371,
      "eval_runtime": 8.5761,
      "eval_samples_per_second": 284.745,
      "eval_steps_per_second": 142.372,
      "step": 9
    },
    {
      "epoch": 0.0017248070372127117,
      "grad_norm": 0.037368640303611755,
      "learning_rate": 0.0002,
      "loss": 11.9342,
      "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": 1181614080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}