Hugging Face's logo

ClarenceDan
/
ea2e7018-ea8d-464e-be35-f2f066a812e6

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
ea2e7018-ea8d-464e-be35-f2f066a812e6
File size: 2,979 Bytes 
7cd9bae
 
 
ae8391a
7cd9bae
ae8391a
7cd9bae
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b25b48f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
935474c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ae8391a
 
 
 
 
 
 
7cd9bae
 
 
 
 
 
 
 
 
 
 
 
 
 
ae8391a
7cd9bae
 
 
 
ae8391a
7cd9bae
 
 
 
 
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": 0.0001645379568499208,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.6453795684992083e-05,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 1.6453795684992083e-05,
      "eval_loss": NaN,
      "eval_runtime": 420.8996,
      "eval_samples_per_second": 60.798,
      "eval_steps_per_second": 30.399,
      "step": 1
    },
    {
      "epoch": 3.2907591369984166e-05,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 4.936138705497624e-05,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 4.936138705497624e-05,
      "eval_loss": NaN,
      "eval_runtime": 418.4943,
      "eval_samples_per_second": 61.148,
      "eval_steps_per_second": 30.574,
      "step": 3
    },
    {
      "epoch": 6.581518273996833e-05,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 8.22689784249604e-05,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 9.872277410995248e-05,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 9.872277410995248e-05,
      "eval_loss": NaN,
      "eval_runtime": 420.687,
      "eval_samples_per_second": 60.829,
      "eval_steps_per_second": 30.415,
      "step": 6
    },
    {
      "epoch": 0.00011517656979494457,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.00013163036547993666,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.00014808416116492875,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.00014808416116492875,
      "eval_loss": NaN,
      "eval_runtime": 420.4148,
      "eval_samples_per_second": 60.868,
      "eval_steps_per_second": 30.434,
      "step": 9
    },
    {
      "epoch": 0.0001645379568499208,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 270613704867840.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}