Hugging Face's logo

trenden
/
63bd93dc-ce75-4513-ac10-cade1bba594e

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
63bd93dc-ce75-4513-ac10-cade1bba594e
File size: 3,156 Bytes 
bb1c1d1
 
 
d2bcdf1
bb1c1d1
d2bcdf1
bb1c1d1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bccbbd9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c38165a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d2bcdf1
 
 
 
 
 
 
bb1c1d1
 
 
 
 
 
 
 
 
 
 
 
 
 
d2bcdf1
bb1c1d1
 
 
 
d2bcdf1
bb1c1d1
 
 
 
 
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": 0.2127659574468085,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02127659574468085,
      "grad_norm": 3.739654541015625,
      "learning_rate": 2e-05,
      "loss": 4.3413,
      "step": 1
    },
    {
      "epoch": 0.02127659574468085,
      "eval_loss": 3.7383079528808594,
      "eval_runtime": 0.7916,
      "eval_samples_per_second": 25.265,
      "eval_steps_per_second": 12.632,
      "step": 1
    },
    {
      "epoch": 0.0425531914893617,
      "grad_norm": 2.7427635192871094,
      "learning_rate": 4e-05,
      "loss": 4.0764,
      "step": 2
    },
    {
      "epoch": 0.06382978723404255,
      "grad_norm": 2.1136608123779297,
      "learning_rate": 6e-05,
      "loss": 3.8131,
      "step": 3
    },
    {
      "epoch": 0.06382978723404255,
      "eval_loss": 3.731614589691162,
      "eval_runtime": 0.3012,
      "eval_samples_per_second": 66.397,
      "eval_steps_per_second": 33.199,
      "step": 3
    },
    {
      "epoch": 0.0851063829787234,
      "grad_norm": 2.1976680755615234,
      "learning_rate": 8e-05,
      "loss": 3.7946,
      "step": 4
    },
    {
      "epoch": 0.10638297872340426,
      "grad_norm": 2.464569330215454,
      "learning_rate": 0.0001,
      "loss": 3.6771,
      "step": 5
    },
    {
      "epoch": 0.1276595744680851,
      "grad_norm": 3.11846661567688,
      "learning_rate": 0.00012,
      "loss": 4.2779,
      "step": 6
    },
    {
      "epoch": 0.1276595744680851,
      "eval_loss": 3.676224946975708,
      "eval_runtime": 0.3202,
      "eval_samples_per_second": 62.46,
      "eval_steps_per_second": 31.23,
      "step": 6
    },
    {
      "epoch": 0.14893617021276595,
      "grad_norm": 3.397935628890991,
      "learning_rate": 0.00014,
      "loss": 4.021,
      "step": 7
    },
    {
      "epoch": 0.1702127659574468,
      "grad_norm": 2.54946231842041,
      "learning_rate": 0.00016,
      "loss": 3.4491,
      "step": 8
    },
    {
      "epoch": 0.19148936170212766,
      "grad_norm": 2.3854799270629883,
      "learning_rate": 0.00018,
      "loss": 3.4781,
      "step": 9
    },
    {
      "epoch": 0.19148936170212766,
      "eval_loss": 3.475511074066162,
      "eval_runtime": 0.3117,
      "eval_samples_per_second": 64.163,
      "eval_steps_per_second": 32.082,
      "step": 9
    },
    {
      "epoch": 0.2127659574468085,
      "grad_norm": 3.3925769329071045,
      "learning_rate": 0.0002,
      "loss": 3.7794,
      "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": 240545515438080.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}