Hugging Face's logo

ClarenceDan
/
b7b9fa71-4d28-4dc2-b61d-ec7d4f2c4cf5

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
b7b9fa71-4d28-4dc2-b61d-ec7d4f2c4cf5
File size: 3,210 Bytes 
aef966c
 
 
41d7d78
aef966c
41d7d78
aef966c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4faaab1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76db441
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
41d7d78
 
 
 
 
 
 
aef966c
 
 
 
 
 
 
 
 
 
 
 
 
 
41d7d78
aef966c
 
 
 
41d7d78
aef966c
 
 
 
 
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": 0.00046078702423739745,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 4.607870242373975e-05,
      "grad_norm": 0.323437362909317,
      "learning_rate": 2e-05,
      "loss": 4.5458,
      "step": 1
    },
    {
      "epoch": 4.607870242373975e-05,
      "eval_loss": 1.1763094663619995,
      "eval_runtime": 685.8318,
      "eval_samples_per_second": 13.324,
      "eval_steps_per_second": 6.662,
      "step": 1
    },
    {
      "epoch": 9.21574048474795e-05,
      "grad_norm": 0.32721254229545593,
      "learning_rate": 4e-05,
      "loss": 3.6827,
      "step": 2
    },
    {
      "epoch": 0.00013823610727121925,
      "grad_norm": 0.35817116498947144,
      "learning_rate": 6e-05,
      "loss": 4.3021,
      "step": 3
    },
    {
      "epoch": 0.00013823610727121925,
      "eval_loss": 1.1759949922561646,
      "eval_runtime": 761.442,
      "eval_samples_per_second": 12.001,
      "eval_steps_per_second": 6.0,
      "step": 3
    },
    {
      "epoch": 0.000184314809694959,
      "grad_norm": 0.29292038083076477,
      "learning_rate": 8e-05,
      "loss": 3.0989,
      "step": 4
    },
    {
      "epoch": 0.00023039351211869873,
      "grad_norm": 0.3303835690021515,
      "learning_rate": 0.0001,
      "loss": 3.9467,
      "step": 5
    },
    {
      "epoch": 0.0002764722145424385,
      "grad_norm": 0.40217289328575134,
      "learning_rate": 0.00012,
      "loss": 4.5857,
      "step": 6
    },
    {
      "epoch": 0.0002764722145424385,
      "eval_loss": 1.1704449653625488,
      "eval_runtime": 981.3093,
      "eval_samples_per_second": 9.312,
      "eval_steps_per_second": 4.656,
      "step": 6
    },
    {
      "epoch": 0.00032255091696617823,
      "grad_norm": 0.8704009652137756,
      "learning_rate": 0.00014,
      "loss": 4.4659,
      "step": 7
    },
    {
      "epoch": 0.000368629619389918,
      "grad_norm": 0.5341410040855408,
      "learning_rate": 0.00016,
      "loss": 5.1402,
      "step": 8
    },
    {
      "epoch": 0.0004147083218136577,
      "grad_norm": 0.5640665888786316,
      "learning_rate": 0.00018,
      "loss": 4.77,
      "step": 9
    },
    {
      "epoch": 0.0004147083218136577,
      "eval_loss": 1.1383893489837646,
      "eval_runtime": 690.0329,
      "eval_samples_per_second": 13.243,
      "eval_steps_per_second": 6.621,
      "step": 9
    },
    {
      "epoch": 0.00046078702423739745,
      "grad_norm": 0.7399348020553589,
      "learning_rate": 0.0002,
      "loss": 4.753,
      "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": 5065958888570880.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}