Hugging Face's logo

philip-hightech
/
b491eac5-30a3-4770-952e-1fb1816ce224

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
b491eac5-30a3-4770-952e-1fb1816ce224
File size: 3,203 Bytes 
d1db576
 
 
1282f23
d1db576
1282f23
d1db576
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7740dae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
820b16c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1282f23
 
 
 
 
 
 
d1db576
 
 
 
 
 
 
 
 
 
 
 
 
 
1282f23
d1db576
 
 
 
1282f23
d1db576
 
 
 
 
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": 0.002201067517746107,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00022010675177461069,
      "grad_norm": 2.3378818035125732,
      "learning_rate": 2e-05,
      "loss": 0.9409,
      "step": 1
    },
    {
      "epoch": 0.00022010675177461069,
      "eval_loss": 1.067487120628357,
      "eval_runtime": 60.8202,
      "eval_samples_per_second": 31.453,
      "eval_steps_per_second": 15.735,
      "step": 1
    },
    {
      "epoch": 0.00044021350354922137,
      "grad_norm": 1.5687549114227295,
      "learning_rate": 4e-05,
      "loss": 0.8715,
      "step": 2
    },
    {
      "epoch": 0.0006603202553238321,
      "grad_norm": 1.8344545364379883,
      "learning_rate": 6e-05,
      "loss": 1.0449,
      "step": 3
    },
    {
      "epoch": 0.0006603202553238321,
      "eval_loss": 1.047654628753662,
      "eval_runtime": 59.6437,
      "eval_samples_per_second": 32.074,
      "eval_steps_per_second": 16.045,
      "step": 3
    },
    {
      "epoch": 0.0008804270070984427,
      "grad_norm": 3.1621816158294678,
      "learning_rate": 8e-05,
      "loss": 1.0538,
      "step": 4
    },
    {
      "epoch": 0.0011005337588730535,
      "grad_norm": 1.8105907440185547,
      "learning_rate": 0.0001,
      "loss": 0.816,
      "step": 5
    },
    {
      "epoch": 0.0013206405106476642,
      "grad_norm": 2.7975521087646484,
      "learning_rate": 0.00012,
      "loss": 0.8251,
      "step": 6
    },
    {
      "epoch": 0.0013206405106476642,
      "eval_loss": 0.6414834856987,
      "eval_runtime": 59.6493,
      "eval_samples_per_second": 32.071,
      "eval_steps_per_second": 16.044,
      "step": 6
    },
    {
      "epoch": 0.0015407472624222747,
      "grad_norm": 1.5536985397338867,
      "learning_rate": 0.00014,
      "loss": 0.5466,
      "step": 7
    },
    {
      "epoch": 0.0017608540141968855,
      "grad_norm": 1.6163760423660278,
      "learning_rate": 0.00016,
      "loss": 0.439,
      "step": 8
    },
    {
      "epoch": 0.0019809607659714962,
      "grad_norm": 1.6741958856582642,
      "learning_rate": 0.00018,
      "loss": 0.49,
      "step": 9
    },
    {
      "epoch": 0.0019809607659714962,
      "eval_loss": 0.44979140162467957,
      "eval_runtime": 59.7227,
      "eval_samples_per_second": 32.031,
      "eval_steps_per_second": 16.024,
      "step": 9
    },
    {
      "epoch": 0.002201067517746107,
      "grad_norm": 1.604898452758789,
      "learning_rate": 0.0002,
      "loss": 0.4402,
      "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": 1849564248145920.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}