Hugging Face's logo

chauhoang
/
c1754119-55e6-46d8-8863-973237a2e37c

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
c1754119-55e6-46d8-8863-973237a2e37c
File size: 3,724 Bytes 
df2b70a
 
 
35dcd38
f980146
35dcd38
df2b70a
 
 
 
 
 
 
f980146
 
 
df2b70a
f980146
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7c68d6e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c2d396c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35dcd38
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
df2b70a
 
 
f980146
df2b70a
 
f980146
df2b70a
 
 
 
 
 
 
35dcd38
df2b70a
 
 
 
35dcd38
df2b70a
 
 
 
 
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": 0.024752475247524754,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004950495049504951,
      "eval_loss": 2.6221022605895996,
      "eval_runtime": 27.7766,
      "eval_samples_per_second": 30.637,
      "eval_steps_per_second": 15.337,
      "step": 1
    },
    {
      "epoch": 0.0024752475247524753,
      "grad_norm": 0.7501001358032227,
      "learning_rate": 5e-05,
      "loss": 2.548,
      "step": 5
    },
    {
      "epoch": 0.0049504950495049506,
      "grad_norm": 0.6144944429397583,
      "learning_rate": 0.0001,
      "loss": 2.5697,
      "step": 10
    },
    {
      "epoch": 0.0049504950495049506,
      "eval_loss": 2.592329978942871,
      "eval_runtime": 27.7412,
      "eval_samples_per_second": 30.676,
      "eval_steps_per_second": 15.356,
      "step": 10
    },
    {
      "epoch": 0.007425742574257425,
      "grad_norm": 0.8921784162521362,
      "learning_rate": 9.619397662556435e-05,
      "loss": 2.6192,
      "step": 15
    },
    {
      "epoch": 0.009900990099009901,
      "grad_norm": 0.547026515007019,
      "learning_rate": 8.535533905932738e-05,
      "loss": 2.5644,
      "step": 20
    },
    {
      "epoch": 0.009900990099009901,
      "eval_loss": 2.4996721744537354,
      "eval_runtime": 27.6222,
      "eval_samples_per_second": 30.809,
      "eval_steps_per_second": 15.422,
      "step": 20
    },
    {
      "epoch": 0.012376237623762377,
      "grad_norm": 0.717430591583252,
      "learning_rate": 6.91341716182545e-05,
      "loss": 2.4506,
      "step": 25
    },
    {
      "epoch": 0.01485148514851485,
      "grad_norm": 0.6969410181045532,
      "learning_rate": 5e-05,
      "loss": 2.4852,
      "step": 30
    },
    {
      "epoch": 0.01485148514851485,
      "eval_loss": 2.4748666286468506,
      "eval_runtime": 27.7477,
      "eval_samples_per_second": 30.669,
      "eval_steps_per_second": 15.353,
      "step": 30
    },
    {
      "epoch": 0.017326732673267328,
      "grad_norm": 0.5595166683197021,
      "learning_rate": 3.086582838174551e-05,
      "loss": 2.5691,
      "step": 35
    },
    {
      "epoch": 0.019801980198019802,
      "grad_norm": 0.6102985739707947,
      "learning_rate": 1.4644660940672627e-05,
      "loss": 2.3449,
      "step": 40
    },
    {
      "epoch": 0.019801980198019802,
      "eval_loss": 2.467658281326294,
      "eval_runtime": 27.8329,
      "eval_samples_per_second": 30.575,
      "eval_steps_per_second": 15.306,
      "step": 40
    },
    {
      "epoch": 0.022277227722772276,
      "grad_norm": 0.7228185534477234,
      "learning_rate": 3.8060233744356633e-06,
      "loss": 2.4674,
      "step": 45
    },
    {
      "epoch": 0.024752475247524754,
      "grad_norm": 0.6576347947120667,
      "learning_rate": 0.0,
      "loss": 2.5014,
      "step": 50
    },
    {
      "epoch": 0.024752475247524754,
      "eval_loss": 2.466404438018799,
      "eval_runtime": 27.709,
      "eval_samples_per_second": 30.712,
      "eval_steps_per_second": 15.374,
      "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": 1624279061889024.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}