Hugging Face's logo

tensor24
/
miner_id_32021124-1cf4-4fe2-a3b8-92a347c6ab8a

PEFT
Safetensors
llama
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
miner_id_32021124-1cf4-4fe2-a3b8-92a347c6ab8a
File size: 3,190 Bytes 
34febc4
 
 
9684047
34febc4
9684047
34febc4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5ab6c15
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49c1588
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9684047
 
 
 
 
 
 
34febc4
 
 
 
 
 
 
 
 
 
 
 
 
 
9684047
34febc4
 
 
 
9684047
34febc4
 
 
 
 
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": 0.002975304968759298,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002975304968759298,
      "grad_norm": 4.083354473114014,
      "learning_rate": 2e-05,
      "loss": 6.2338,
      "step": 1
    },
    {
      "epoch": 0.0002975304968759298,
      "eval_loss": 3.9553987979888916,
      "eval_runtime": 170.2808,
      "eval_samples_per_second": 8.316,
      "eval_steps_per_second": 4.158,
      "step": 1
    },
    {
      "epoch": 0.0005950609937518596,
      "grad_norm": 2.295527219772339,
      "learning_rate": 4e-05,
      "loss": 3.6333,
      "step": 2
    },
    {
      "epoch": 0.0008925914906277894,
      "grad_norm": 2.81231689453125,
      "learning_rate": 6e-05,
      "loss": 4.7203,
      "step": 3
    },
    {
      "epoch": 0.0008925914906277894,
      "eval_loss": 3.942405939102173,
      "eval_runtime": 172.0013,
      "eval_samples_per_second": 8.232,
      "eval_steps_per_second": 4.116,
      "step": 3
    },
    {
      "epoch": 0.0011901219875037191,
      "grad_norm": 2.846064805984497,
      "learning_rate": 8e-05,
      "loss": 4.558,
      "step": 4
    },
    {
      "epoch": 0.001487652484379649,
      "grad_norm": 1.77438223361969,
      "learning_rate": 0.0001,
      "loss": 3.2527,
      "step": 5
    },
    {
      "epoch": 0.0017851829812555787,
      "grad_norm": 2.6561055183410645,
      "learning_rate": 0.00012,
      "loss": 4.8197,
      "step": 6
    },
    {
      "epoch": 0.0017851829812555787,
      "eval_loss": 3.7654619216918945,
      "eval_runtime": 171.8954,
      "eval_samples_per_second": 8.238,
      "eval_steps_per_second": 4.119,
      "step": 6
    },
    {
      "epoch": 0.0020827134781315083,
      "grad_norm": 1.1815612316131592,
      "learning_rate": 0.00014,
      "loss": 2.215,
      "step": 7
    },
    {
      "epoch": 0.0023802439750074383,
      "grad_norm": 2.3964359760284424,
      "learning_rate": 0.00016,
      "loss": 3.0826,
      "step": 8
    },
    {
      "epoch": 0.002677774471883368,
      "grad_norm": 4.077512264251709,
      "learning_rate": 0.00018,
      "loss": 3.6421,
      "step": 9
    },
    {
      "epoch": 0.002677774471883368,
      "eval_loss": 3.4991986751556396,
      "eval_runtime": 172.0593,
      "eval_samples_per_second": 8.23,
      "eval_steps_per_second": 4.115,
      "step": 9
    },
    {
      "epoch": 0.002975304968759298,
      "grad_norm": 2.2527685165405273,
      "learning_rate": 0.0002,
      "loss": 2.4711,
      "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": 2882232561696768.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}