Hugging Face's logo

duyphu
/
b5622cc4-6bfb-4c46-895f-d6742f2b873a

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
b5622cc4-6bfb-4c46-895f-d6742f2b873a
File size: 3,701 Bytes 
fd465b1
 
 
f255827
3a8f073
f255827
fd465b1
 
 
 
 
 
 
3a8f073
 
 
fd465b1
3a8f073
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1dca2b0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8154f8a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f255827
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fd465b1
 
 
3a8f073
fd465b1
 
3a8f073
fd465b1
 
 
 
 
 
 
f255827
fd465b1
 
 
 
f255827
fd465b1
 
 
 
 
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": 0.07259528130671507,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0014519056261343012,
      "eval_loss": 2.4837050437927246,
      "eval_runtime": 34.809,
      "eval_samples_per_second": 8.331,
      "eval_steps_per_second": 4.166,
      "step": 1
    },
    {
      "epoch": 0.007259528130671506,
      "grad_norm": 1.4090709686279297,
      "learning_rate": 5e-05,
      "loss": 2.4528,
      "step": 5
    },
    {
      "epoch": 0.014519056261343012,
      "grad_norm": 1.6987773180007935,
      "learning_rate": 0.0001,
      "loss": 2.2668,
      "step": 10
    },
    {
      "epoch": 0.014519056261343012,
      "eval_loss": 2.2202208042144775,
      "eval_runtime": 35.1159,
      "eval_samples_per_second": 8.258,
      "eval_steps_per_second": 4.129,
      "step": 10
    },
    {
      "epoch": 0.021778584392014518,
      "grad_norm": 3.0617473125457764,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.1563,
      "step": 15
    },
    {
      "epoch": 0.029038112522686024,
      "grad_norm": 2.7853174209594727,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.9604,
      "step": 20
    },
    {
      "epoch": 0.029038112522686024,
      "eval_loss": 1.92987859249115,
      "eval_runtime": 35.1927,
      "eval_samples_per_second": 8.24,
      "eval_steps_per_second": 4.12,
      "step": 20
    },
    {
      "epoch": 0.036297640653357534,
      "grad_norm": 2.5411033630371094,
      "learning_rate": 6.91341716182545e-05,
      "loss": 1.8184,
      "step": 25
    },
    {
      "epoch": 0.043557168784029036,
      "grad_norm": 2.588447093963623,
      "learning_rate": 5e-05,
      "loss": 1.8994,
      "step": 30
    },
    {
      "epoch": 0.043557168784029036,
      "eval_loss": 1.8195312023162842,
      "eval_runtime": 35.2383,
      "eval_samples_per_second": 8.23,
      "eval_steps_per_second": 4.115,
      "step": 30
    },
    {
      "epoch": 0.050816696914700546,
      "grad_norm": 2.859415054321289,
      "learning_rate": 3.086582838174551e-05,
      "loss": 1.8508,
      "step": 35
    },
    {
      "epoch": 0.05807622504537205,
      "grad_norm": 2.951900005340576,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 1.5987,
      "step": 40
    },
    {
      "epoch": 0.05807622504537205,
      "eval_loss": 1.776922345161438,
      "eval_runtime": 35.2749,
      "eval_samples_per_second": 8.221,
      "eval_steps_per_second": 4.111,
      "step": 40
    },
    {
      "epoch": 0.06533575317604355,
      "grad_norm": 2.383507251739502,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 1.7098,
      "step": 45
    },
    {
      "epoch": 0.07259528130671507,
      "grad_norm": 2.7600584030151367,
      "learning_rate": 0.0,
      "loss": 1.7854,
      "step": 50
    },
    {
      "epoch": 0.07259528130671507,
      "eval_loss": 1.769264578819275,
      "eval_runtime": 35.2817,
      "eval_samples_per_second": 8.22,
      "eval_steps_per_second": 4.11,
      "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": 1.803325141942272e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}