Hugging Face's logo

lesso15
/
cfb2b759-642c-4778-9f9f-06f95260070c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
cfb2b759-642c-4778-9f9f-06f95260070c
File size: 2,874 Bytes 
c501d00
 
 
971188a
c501d00
971188a
c501d00
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
971188a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c501d00
 
 
 
 
 
 
 
 
 
 
 
 
 
971188a
c501d00
 
 
 
 
 
 
 
971188a
c501d00
 
 
 
971188a
c501d00
 
 
 
 
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
 
{
  "best_metric": NaN,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.030864197530864196,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015432098765432098,
      "eval_loss": NaN,
      "eval_runtime": 10.4816,
      "eval_samples_per_second": 6.583,
      "eval_steps_per_second": 3.339,
      "step": 1
    },
    {
      "epoch": 0.004629629629629629,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.007716049382716049,
      "eval_loss": NaN,
      "eval_runtime": 9.2579,
      "eval_samples_per_second": 7.453,
      "eval_steps_per_second": 3.781,
      "step": 5
    },
    {
      "epoch": 0.009259259259259259,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.013888888888888888,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.015432098765432098,
      "eval_loss": NaN,
      "eval_runtime": 8.6581,
      "eval_samples_per_second": 7.969,
      "eval_steps_per_second": 4.042,
      "step": 10
    },
    {
      "epoch": 0.018518518518518517,
      "grad_norm": NaN,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0,
      "step": 12
    },
    {
      "epoch": 0.023148148148148147,
      "grad_norm": NaN,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.0,
      "step": 15
    },
    {
      "epoch": 0.023148148148148147,
      "eval_loss": NaN,
      "eval_runtime": 8.9641,
      "eval_samples_per_second": 7.697,
      "eval_steps_per_second": 3.904,
      "step": 15
    },
    {
      "epoch": 0.027777777777777776,
      "grad_norm": NaN,
      "learning_rate": 8.954715367323468e-05,
      "loss": 0.0,
      "step": 18
    },
    {
      "epoch": 0.030864197530864196,
      "eval_loss": NaN,
      "eval_runtime": 10.4253,
      "eval_samples_per_second": 6.618,
      "eval_steps_per_second": 3.357,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 2,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 2
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 79458808627200.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}