Hugging Face's logo

vmpsergio
/
2bf69ce0-f510-4031-ad51-8df4fbb0e47d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
2bf69ce0-f510-4031-ad51-8df4fbb0e47d
File size: 3,084 Bytes 
a2ba784
22c1f85
 
 
a2ba784
22c1f85
a2ba784
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22c1f85
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a2ba784
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
22c1f85
a2ba784
 
 
 
 
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": 1.1928067207336426,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.008487163165711862,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000424358158285593,
      "eval_loss": 1.508124828338623,
      "eval_runtime": 128.6731,
      "eval_samples_per_second": 7.717,
      "eval_steps_per_second": 3.863,
      "step": 1
    },
    {
      "epoch": 0.001273074474856779,
      "grad_norm": 0.5830173492431641,
      "learning_rate": 6e-05,
      "loss": 1.5825,
      "step": 3
    },
    {
      "epoch": 0.0021217907914279654,
      "eval_loss": 1.466567039489746,
      "eval_runtime": 129.6671,
      "eval_samples_per_second": 7.658,
      "eval_steps_per_second": 3.833,
      "step": 5
    },
    {
      "epoch": 0.002546148949713558,
      "grad_norm": 0.5419243574142456,
      "learning_rate": 0.00012,
      "loss": 1.427,
      "step": 6
    },
    {
      "epoch": 0.0038192234245703373,
      "grad_norm": 0.8369843363761902,
      "learning_rate": 0.00018,
      "loss": 1.3801,
      "step": 9
    },
    {
      "epoch": 0.004243581582855931,
      "eval_loss": 1.3134835958480835,
      "eval_runtime": 129.6779,
      "eval_samples_per_second": 7.657,
      "eval_steps_per_second": 3.833,
      "step": 10
    },
    {
      "epoch": 0.005092297899427116,
      "grad_norm": 0.7152264714241028,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.3058,
      "step": 12
    },
    {
      "epoch": 0.006365372374283896,
      "grad_norm": 0.5883220434188843,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.2339,
      "step": 15
    },
    {
      "epoch": 0.006365372374283896,
      "eval_loss": 1.2224185466766357,
      "eval_runtime": 129.5429,
      "eval_samples_per_second": 7.665,
      "eval_steps_per_second": 3.837,
      "step": 15
    },
    {
      "epoch": 0.0076384468491406746,
      "grad_norm": 0.6324528455734253,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.1509,
      "step": 18
    },
    {
      "epoch": 0.008487163165711862,
      "eval_loss": 1.1928067207336426,
      "eval_runtime": 129.2663,
      "eval_samples_per_second": 7.682,
      "eval_steps_per_second": 3.845,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7511608746049536.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}