Hugging Face's logo

nathanialhunt
/
3912d8a4-06a2-4225-9b6c-2913b8138bb1

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
3912d8a4-06a2-4225-9b6c-2913b8138bb1
File size: 3,216 Bytes 
f9aeaed
 
 
9d52e29
f9aeaed
9d52e29
f9aeaed
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4000095
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f782d38
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9d52e29
 
 
 
 
 
 
f9aeaed
 
 
 
 
 
 
 
 
 
 
 
 
 
9d52e29
f9aeaed
 
 
 
9d52e29
f9aeaed
 
 
 
 
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": 0.0015081250235644535,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00015081250235644535,
      "grad_norm": 0.5317559242248535,
      "learning_rate": 2e-05,
      "loss": 1.3914,
      "step": 1
    },
    {
      "epoch": 0.00015081250235644535,
      "eval_loss": 1.3070451021194458,
      "eval_runtime": 118.3819,
      "eval_samples_per_second": 23.585,
      "eval_steps_per_second": 11.792,
      "step": 1
    },
    {
      "epoch": 0.0003016250047128907,
      "grad_norm": 0.6152631044387817,
      "learning_rate": 4e-05,
      "loss": 1.2828,
      "step": 2
    },
    {
      "epoch": 0.00045243750706933604,
      "grad_norm": 0.4285082221031189,
      "learning_rate": 6e-05,
      "loss": 1.1774,
      "step": 3
    },
    {
      "epoch": 0.00045243750706933604,
      "eval_loss": 1.3028250932693481,
      "eval_runtime": 117.0178,
      "eval_samples_per_second": 23.86,
      "eval_steps_per_second": 11.93,
      "step": 3
    },
    {
      "epoch": 0.0006032500094257814,
      "grad_norm": 0.5396704077720642,
      "learning_rate": 8e-05,
      "loss": 1.4807,
      "step": 4
    },
    {
      "epoch": 0.0007540625117822267,
      "grad_norm": 0.5223986506462097,
      "learning_rate": 0.0001,
      "loss": 1.1522,
      "step": 5
    },
    {
      "epoch": 0.0009048750141386721,
      "grad_norm": 0.5262135863304138,
      "learning_rate": 0.00012,
      "loss": 1.2866,
      "step": 6
    },
    {
      "epoch": 0.0009048750141386721,
      "eval_loss": 1.2506712675094604,
      "eval_runtime": 117.1884,
      "eval_samples_per_second": 23.825,
      "eval_steps_per_second": 11.912,
      "step": 6
    },
    {
      "epoch": 0.0010556875164951175,
      "grad_norm": 0.6160966157913208,
      "learning_rate": 0.00014,
      "loss": 1.3513,
      "step": 7
    },
    {
      "epoch": 0.0012065000188515628,
      "grad_norm": 0.6128122806549072,
      "learning_rate": 0.00016,
      "loss": 1.2196,
      "step": 8
    },
    {
      "epoch": 0.0013573125212080082,
      "grad_norm": 0.4621923565864563,
      "learning_rate": 0.00018,
      "loss": 1.3301,
      "step": 9
    },
    {
      "epoch": 0.0013573125212080082,
      "eval_loss": 1.1254338026046753,
      "eval_runtime": 117.0854,
      "eval_samples_per_second": 23.846,
      "eval_steps_per_second": 11.923,
      "step": 9
    },
    {
      "epoch": 0.0015081250235644535,
      "grad_norm": 0.443646639585495,
      "learning_rate": 0.0002,
      "loss": 1.1217,
      "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": 2389343238881280.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}