Hugging Face's logo

phungkhaccuong
/
2c364321-bc92-4760-abd4-5dfbb8bc02c8

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
2c364321-bc92-4760-abd4-5dfbb8bc02c8
File size: 3,695 Bytes 
568146b
 
 
058795d
0ec7b9a
058795d
568146b
 
 
 
 
 
 
0ec7b9a
 
 
568146b
0ec7b9a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bdb2cf6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1cc84b4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
058795d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
568146b
 
 
0ec7b9a
568146b
 
0ec7b9a
568146b
 
 
 
 
 
 
058795d
568146b
 
 
 
058795d
568146b
 
 
 
 
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": 0.1276324186343331,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025526483726866626,
      "eval_loss": 2.834757089614868,
      "eval_runtime": 9.3708,
      "eval_samples_per_second": 17.608,
      "eval_steps_per_second": 8.857,
      "step": 1
    },
    {
      "epoch": 0.012763241863433313,
      "grad_norm": 0.622917652130127,
      "learning_rate": 5e-05,
      "loss": 2.8162,
      "step": 5
    },
    {
      "epoch": 0.025526483726866625,
      "grad_norm": 0.4492838382720947,
      "learning_rate": 0.0001,
      "loss": 2.7871,
      "step": 10
    },
    {
      "epoch": 0.025526483726866625,
      "eval_loss": 2.7915663719177246,
      "eval_runtime": 9.2446,
      "eval_samples_per_second": 17.848,
      "eval_steps_per_second": 8.978,
      "step": 10
    },
    {
      "epoch": 0.03828972559029994,
      "grad_norm": 0.5710231065750122,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.7649,
      "step": 15
    },
    {
      "epoch": 0.05105296745373325,
      "grad_norm": 0.5380902886390686,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.7337,
      "step": 20
    },
    {
      "epoch": 0.05105296745373325,
      "eval_loss": 2.7470574378967285,
      "eval_runtime": 9.2673,
      "eval_samples_per_second": 17.805,
      "eval_steps_per_second": 8.956,
      "step": 20
    },
    {
      "epoch": 0.06381620931716656,
      "grad_norm": 0.6101768016815186,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.7201,
      "step": 25
    },
    {
      "epoch": 0.07657945118059988,
      "grad_norm": 0.6069520711898804,
      "learning_rate": 5e-05,
      "loss": 2.7406,
      "step": 30
    },
    {
      "epoch": 0.07657945118059988,
      "eval_loss": 2.727977991104126,
      "eval_runtime": 9.3209,
      "eval_samples_per_second": 17.702,
      "eval_steps_per_second": 8.905,
      "step": 30
    },
    {
      "epoch": 0.08934269304403318,
      "grad_norm": 0.5778947472572327,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.6019,
      "step": 35
    },
    {
      "epoch": 0.1021059349074665,
      "grad_norm": 0.6996490359306335,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.7452,
      "step": 40
    },
    {
      "epoch": 0.1021059349074665,
      "eval_loss": 2.7188756465911865,
      "eval_runtime": 9.4298,
      "eval_samples_per_second": 17.498,
      "eval_steps_per_second": 8.802,
      "step": 40
    },
    {
      "epoch": 0.1148691767708998,
      "grad_norm": 0.6797233819961548,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.7534,
      "step": 45
    },
    {
      "epoch": 0.1276324186343331,
      "grad_norm": 0.6642326712608337,
      "learning_rate": 0.0,
      "loss": 2.6603,
      "step": 50
    },
    {
      "epoch": 0.1276324186343331,
      "eval_loss": 2.717184543609619,
      "eval_runtime": 9.3197,
      "eval_samples_per_second": 17.704,
      "eval_steps_per_second": 8.906,
      "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": 4713523634503680.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}