Hugging Face's logo

chauhoang
/
5bffdcbc-e109-e343-7c14-c596ad38e219

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
5bffdcbc-e109-e343-7c14-c596ad38e219
File size: 3,725 Bytes 
3e90c0f
 
 
1c39613
6c3d828
1c39613
3e90c0f
 
 
 
 
 
 
6c3d828
 
 
3e90c0f
6c3d828
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cca2e8d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
324e8fe
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1c39613
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3e90c0f
 
 
6c3d828
3e90c0f
 
6c3d828
3e90c0f
 
 
 
 
 
 
1c39613
3e90c0f
 
 
 
1c39613
3e90c0f
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.006867660188173889,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001373532037634778,
      "eval_loss": 1.981343388557434,
      "eval_runtime": 108.8442,
      "eval_samples_per_second": 28.169,
      "eval_steps_per_second": 14.084,
      "step": 1
    },
    {
      "epoch": 0.000686766018817389,
      "grad_norm": 0.7336399555206299,
      "learning_rate": 5e-05,
      "loss": 1.7832,
      "step": 5
    },
    {
      "epoch": 0.001373532037634778,
      "grad_norm": 0.8265002965927124,
      "learning_rate": 0.0001,
      "loss": 1.8771,
      "step": 10
    },
    {
      "epoch": 0.001373532037634778,
      "eval_loss": 1.938093662261963,
      "eval_runtime": 108.8765,
      "eval_samples_per_second": 28.16,
      "eval_steps_per_second": 14.08,
      "step": 10
    },
    {
      "epoch": 0.0020602980564521666,
      "grad_norm": 0.7830203771591187,
      "learning_rate": 9.619397662556435e-05,
      "loss": 1.85,
      "step": 15
    },
    {
      "epoch": 0.002747064075269556,
      "grad_norm": 0.796001672744751,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.8302,
      "step": 20
    },
    {
      "epoch": 0.002747064075269556,
      "eval_loss": 1.7976608276367188,
      "eval_runtime": 108.7834,
      "eval_samples_per_second": 28.184,
      "eval_steps_per_second": 14.092,
      "step": 20
    },
    {
      "epoch": 0.0034338300940869445,
      "grad_norm": 0.679097056388855,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.6732,
      "step": 25
    },
    {
      "epoch": 0.004120596112904333,
      "grad_norm": 0.9102851152420044,
      "learning_rate": 5e-05,
      "loss": 1.6933,
      "step": 30
    },
    {
      "epoch": 0.004120596112904333,
      "eval_loss": 1.7453827857971191,
      "eval_runtime": 107.8127,
      "eval_samples_per_second": 28.438,
      "eval_steps_per_second": 14.219,
      "step": 30
    },
    {
      "epoch": 0.004807362131721722,
      "grad_norm": 1.0547045469284058,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.6154,
      "step": 35
    },
    {
      "epoch": 0.005494128150539112,
      "grad_norm": 0.9129773378372192,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.7811,
      "step": 40
    },
    {
      "epoch": 0.005494128150539112,
      "eval_loss": 1.7244644165039062,
      "eval_runtime": 109.0993,
      "eval_samples_per_second": 28.103,
      "eval_steps_per_second": 14.051,
      "step": 40
    },
    {
      "epoch": 0.0061808941693565,
      "grad_norm": 0.783636748790741,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.5446,
      "step": 45
    },
    {
      "epoch": 0.006867660188173889,
      "grad_norm": 0.7290799617767334,
      "learning_rate": 0.0,
      "loss": 1.6069,
      "step": 50
    },
    {
      "epoch": 0.006867660188173889,
      "eval_loss": 1.721480131149292,
      "eval_runtime": 108.121,
      "eval_samples_per_second": 28.357,
      "eval_steps_per_second": 14.179,
      "step": 50
    }
  ],
  "logging_steps": 5,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2207005104144384.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}