Hugging Face's logo

quannh197
/
f5fb298c-df1a-4966-9c77-a5b493faeff6

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
f5fb298c-df1a-4966-9c77-a5b493faeff6
File size: 3,172 Bytes
acc6461
 
 
fb37049
acc6461
fb37049
acc6461
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cf5528f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
54478a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fb37049
 
 
 
 
 
 
acc6461
 
 
 
 
 
 
 
 
 
 
 
 
 
fb37049
acc6461
 
 
 
fb37049
acc6461
 
 
 
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
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.18691588785046728,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 0.9504849910736084,
      "learning_rate": 2e-05,
      "loss": 2.0864,
      "step": 1
    },
    {
      "epoch": 0.018691588785046728,
      "eval_loss": 2.4634759426116943,
      "eval_runtime": 1.9807,
      "eval_samples_per_second": 11.612,
      "eval_steps_per_second": 6.059,
      "step": 1
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 1.128625512123108,
      "learning_rate": 4e-05,
      "loss": 2.052,
      "step": 2
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 1.1591551303863525,
      "learning_rate": 6e-05,
      "loss": 2.0881,
      "step": 3
    },
    {
      "epoch": 0.056074766355140186,
      "eval_loss": 2.4596502780914307,
      "eval_runtime": 0.7432,
      "eval_samples_per_second": 30.947,
      "eval_steps_per_second": 16.146,
      "step": 3
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 1.0428029298782349,
      "learning_rate": 8e-05,
      "loss": 2.0578,
      "step": 4
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 1.082016944885254,
      "learning_rate": 0.0001,
      "loss": 1.9756,
      "step": 5
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 1.079058289527893,
      "learning_rate": 0.00012,
      "loss": 2.1077,
      "step": 6
    },
    {
      "epoch": 0.11214953271028037,
      "eval_loss": 2.4028377532958984,
      "eval_runtime": 0.7562,
      "eval_samples_per_second": 30.415,
      "eval_steps_per_second": 15.868,
      "step": 6
    },
    {
      "epoch": 0.1308411214953271,
      "grad_norm": 1.3398456573486328,
      "learning_rate": 0.00014,
      "loss": 2.3719,
      "step": 7
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 1.376936912536621,
      "learning_rate": 0.00016,
      "loss": 1.7642,
      "step": 8
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 1.6025842428207397,
      "learning_rate": 0.00018,
      "loss": 1.9801,
      "step": 9
    },
    {
      "epoch": 0.16822429906542055,
      "eval_loss": 2.127096652984619,
      "eval_runtime": 0.7449,
      "eval_samples_per_second": 30.878,
      "eval_steps_per_second": 16.11,
      "step": 9
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 1.239439845085144,
      "learning_rate": 0.0002,
      "loss": 1.8532,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1895803354349568.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}