Hugging Face's logo

chauhoang
/
cbe324eb-13ec-4f47-aac8-65bea34b4233

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
Community
cbe324eb-13ec-4f47-aac8-65bea34b4233
File size: 3,751 Bytes 
be1601d
 
 
fc01c38
412a438
fc01c38
be1601d
 
 
 
 
 
 
412a438
 
 
be1601d
412a438
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3cb3de0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
ad18f21
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fc01c38
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
be1601d
 
 
412a438
be1601d
 
412a438
be1601d
 
 
 
 
 
 
fc01c38
be1601d
 
 
 
fc01c38
be1601d
 
 
 
 
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": 0.0006385614487682149,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.2771228975364299e-05,
      "eval_loss": 2.566653251647949,
      "eval_runtime": 1235.1891,
      "eval_samples_per_second": 26.691,
      "eval_steps_per_second": 13.346,
      "step": 1
    },
    {
      "epoch": 6.38561448768215e-05,
      "grad_norm": 0.48807352781295776,
      "learning_rate": 5e-05,
      "loss": 2.5533,
      "step": 5
    },
    {
      "epoch": 0.000127712289753643,
      "grad_norm": 0.5297641158103943,
      "learning_rate": 0.0001,
      "loss": 2.5952,
      "step": 10
    },
    {
      "epoch": 0.000127712289753643,
      "eval_loss": 2.4731204509735107,
      "eval_runtime": 1235.5847,
      "eval_samples_per_second": 26.683,
      "eval_steps_per_second": 13.342,
      "step": 10
    },
    {
      "epoch": 0.0001915684346304645,
      "grad_norm": 0.6554055213928223,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.3075,
      "step": 15
    },
    {
      "epoch": 0.000255424579507286,
      "grad_norm": 1.4760862588882446,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.1224,
      "step": 20
    },
    {
      "epoch": 0.000255424579507286,
      "eval_loss": 2.0983011722564697,
      "eval_runtime": 1208.4435,
      "eval_samples_per_second": 27.282,
      "eval_steps_per_second": 13.642,
      "step": 20
    },
    {
      "epoch": 0.00031928072438410746,
      "grad_norm": 0.8199297189712524,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.0542,
      "step": 25
    },
    {
      "epoch": 0.000383136869260929,
      "grad_norm": 0.8175716996192932,
      "learning_rate": 5e-05,
      "loss": 2.0226,
      "step": 30
    },
    {
      "epoch": 0.000383136869260929,
      "eval_loss": 1.9621654748916626,
      "eval_runtime": 1211.5072,
      "eval_samples_per_second": 27.213,
      "eval_steps_per_second": 13.607,
      "step": 30
    },
    {
      "epoch": 0.00044699301413775045,
      "grad_norm": 0.8850980401039124,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.9742,
      "step": 35
    },
    {
      "epoch": 0.000510849159014572,
      "grad_norm": 0.7436493635177612,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.9278,
      "step": 40
    },
    {
      "epoch": 0.000510849159014572,
      "eval_loss": 1.9221231937408447,
      "eval_runtime": 1209.3488,
      "eval_samples_per_second": 27.262,
      "eval_steps_per_second": 13.631,
      "step": 40
    },
    {
      "epoch": 0.0005747053038913935,
      "grad_norm": 0.8459659218788147,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.9795,
      "step": 45
    },
    {
      "epoch": 0.0006385614487682149,
      "grad_norm": 0.8609293699264526,
      "learning_rate": 0.0,
      "loss": 2.0347,
      "step": 50
    },
    {
      "epoch": 0.0006385614487682149,
      "eval_loss": 1.9152170419692993,
      "eval_runtime": 1207.7242,
      "eval_samples_per_second": 27.298,
      "eval_steps_per_second": 13.65,
      "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": 4100243324928000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}