Hugging Face's logo

ClarenceDan
/
93993d99-8ea8-47e0-849f-d360c7481cb7

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
93993d99-8ea8-47e0-849f-d360c7481cb7
File size: 3,226 Bytes 
02421a4
 
 
d8db278
02421a4
d8db278
02421a4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1ca1e47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f3cbd08
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d8db278
 
 
 
 
 
 
02421a4
 
 
 
 
 
 
 
 
 
 
 
 
 
d8db278
02421a4
 
 
 
d8db278
02421a4
 
 
 
 
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": 0.00028650216667263544,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.8650216667263546e-05,
      "grad_norm": 0.3048948049545288,
      "learning_rate": 2e-05,
      "loss": 0.4302,
      "step": 1
    },
    {
      "epoch": 2.8650216667263546e-05,
      "eval_loss": 0.44896185398101807,
      "eval_runtime": 703.6224,
      "eval_samples_per_second": 20.888,
      "eval_steps_per_second": 10.445,
      "step": 1
    },
    {
      "epoch": 5.730043333452709e-05,
      "grad_norm": 0.2823459208011627,
      "learning_rate": 4e-05,
      "loss": 0.3545,
      "step": 2
    },
    {
      "epoch": 8.595065000179063e-05,
      "grad_norm": 0.2789570689201355,
      "learning_rate": 6e-05,
      "loss": 0.448,
      "step": 3
    },
    {
      "epoch": 8.595065000179063e-05,
      "eval_loss": 0.4462762176990509,
      "eval_runtime": 704.5436,
      "eval_samples_per_second": 20.86,
      "eval_steps_per_second": 10.431,
      "step": 3
    },
    {
      "epoch": 0.00011460086666905418,
      "grad_norm": 0.3155519962310791,
      "learning_rate": 8e-05,
      "loss": 0.3463,
      "step": 4
    },
    {
      "epoch": 0.00014325108333631772,
      "grad_norm": 0.47635114192962646,
      "learning_rate": 0.0001,
      "loss": 0.3387,
      "step": 5
    },
    {
      "epoch": 0.00017190130000358127,
      "grad_norm": 0.43341612815856934,
      "learning_rate": 0.00012,
      "loss": 0.4044,
      "step": 6
    },
    {
      "epoch": 0.00017190130000358127,
      "eval_loss": 0.4110422134399414,
      "eval_runtime": 743.8877,
      "eval_samples_per_second": 19.757,
      "eval_steps_per_second": 9.879,
      "step": 6
    },
    {
      "epoch": 0.00020055151667084482,
      "grad_norm": 0.6188974380493164,
      "learning_rate": 0.00014,
      "loss": 0.2789,
      "step": 7
    },
    {
      "epoch": 0.00022920173333810837,
      "grad_norm": 0.6034024357795715,
      "learning_rate": 0.00016,
      "loss": 0.3266,
      "step": 8
    },
    {
      "epoch": 0.0002578519500053719,
      "grad_norm": 0.39841750264167786,
      "learning_rate": 0.00018,
      "loss": 0.2998,
      "step": 9
    },
    {
      "epoch": 0.0002578519500053719,
      "eval_loss": 0.26757845282554626,
      "eval_runtime": 707.5272,
      "eval_samples_per_second": 20.772,
      "eval_steps_per_second": 10.387,
      "step": 9
    },
    {
      "epoch": 0.00028650216667263544,
      "grad_norm": 0.5604045987129211,
      "learning_rate": 0.0002,
      "loss": 0.249,
      "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": 3166204172697600.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}