Hugging Face's logo

havinash-ai
/
beab5b08-c80f-41fd-9ec2-f8386c1dfbfd

PEFT
Safetensors
opt
axolotl
Generated from Trainer
Model card Files Community
beab5b08-c80f-41fd-9ec2-f8386c1dfbfd
File size: 3,203 Bytes 
ce29a3b
 
 
4bbf5bd
ce29a3b
4bbf5bd
ce29a3b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e0cface
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bdcfbdd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4bbf5bd
 
 
 
 
 
 
ce29a3b
 
 
 
 
 
 
 
 
 
 
 
 
 
4bbf5bd
ce29a3b
 
 
 
4bbf5bd
ce29a3b
 
 
 
 
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": 0.0016332530317259401,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00016332530317259402,
      "grad_norm": 1.9298620223999023,
      "learning_rate": 2e-05,
      "loss": 5.5226,
      "step": 1
    },
    {
      "epoch": 0.00016332530317259402,
      "eval_loss": 1.2396178245544434,
      "eval_runtime": 32.8028,
      "eval_samples_per_second": 78.591,
      "eval_steps_per_second": 39.295,
      "step": 1
    },
    {
      "epoch": 0.00032665060634518803,
      "grad_norm": 2.632509231567383,
      "learning_rate": 4e-05,
      "loss": 5.8417,
      "step": 2
    },
    {
      "epoch": 0.0004899759095177821,
      "grad_norm": 1.8391531705856323,
      "learning_rate": 6e-05,
      "loss": 4.8234,
      "step": 3
    },
    {
      "epoch": 0.0004899759095177821,
      "eval_loss": 1.238764762878418,
      "eval_runtime": 31.9845,
      "eval_samples_per_second": 80.602,
      "eval_steps_per_second": 40.301,
      "step": 3
    },
    {
      "epoch": 0.0006533012126903761,
      "grad_norm": 2.708847761154175,
      "learning_rate": 8e-05,
      "loss": 6.02,
      "step": 4
    },
    {
      "epoch": 0.0008166265158629701,
      "grad_norm": 2.039414644241333,
      "learning_rate": 0.0001,
      "loss": 5.1642,
      "step": 5
    },
    {
      "epoch": 0.0009799518190355642,
      "grad_norm": 2.06784987449646,
      "learning_rate": 0.00012,
      "loss": 5.1002,
      "step": 6
    },
    {
      "epoch": 0.0009799518190355642,
      "eval_loss": 1.2361284494400024,
      "eval_runtime": 31.8873,
      "eval_samples_per_second": 80.847,
      "eval_steps_per_second": 40.424,
      "step": 6
    },
    {
      "epoch": 0.0011432771222081581,
      "grad_norm": 2.7405037879943848,
      "learning_rate": 0.00014,
      "loss": 5.6114,
      "step": 7
    },
    {
      "epoch": 0.0013066024253807521,
      "grad_norm": 2.1372079849243164,
      "learning_rate": 0.00016,
      "loss": 5.2708,
      "step": 8
    },
    {
      "epoch": 0.0014699277285533461,
      "grad_norm": 1.879054069519043,
      "learning_rate": 0.00018,
      "loss": 5.0464,
      "step": 9
    },
    {
      "epoch": 0.0014699277285533461,
      "eval_loss": 1.2333914041519165,
      "eval_runtime": 31.673,
      "eval_samples_per_second": 81.394,
      "eval_steps_per_second": 40.697,
      "step": 9
    },
    {
      "epoch": 0.0016332530317259401,
      "grad_norm": 2.1005377769470215,
      "learning_rate": 0.0002,
      "loss": 4.8574,
      "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": 132000786677760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}