Hugging Face's logo

ClarenceDan
/
e32d59a2-46c3-4d28-a30c-9bf266a29741

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
e32d59a2-46c3-4d28-a30c-9bf266a29741
File size: 3,216 Bytes 
6ab7bc5
 
 
da46918
6ab7bc5
da46918
6ab7bc5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e17975c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1d8f240
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
da46918
 
 
 
 
 
 
6ab7bc5
 
 
 
 
 
 
 
 
 
 
 
 
 
da46918
6ab7bc5
 
 
 
da46918
6ab7bc5
 
 
 
 
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": 0.00023673121537805974,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.3673121537805975e-05,
      "grad_norm": 1.7583783864974976,
      "learning_rate": 2e-05,
      "loss": 1.5384,
      "step": 1
    },
    {
      "epoch": 2.3673121537805975e-05,
      "eval_loss": 1.7546149492263794,
      "eval_runtime": 515.8762,
      "eval_samples_per_second": 34.479,
      "eval_steps_per_second": 17.241,
      "step": 1
    },
    {
      "epoch": 4.734624307561195e-05,
      "grad_norm": 1.560328722000122,
      "learning_rate": 4e-05,
      "loss": 1.9956,
      "step": 2
    },
    {
      "epoch": 7.101936461341793e-05,
      "grad_norm": 2.629258394241333,
      "learning_rate": 6e-05,
      "loss": 1.7636,
      "step": 3
    },
    {
      "epoch": 7.101936461341793e-05,
      "eval_loss": 1.7382676601409912,
      "eval_runtime": 514.9284,
      "eval_samples_per_second": 34.543,
      "eval_steps_per_second": 17.272,
      "step": 3
    },
    {
      "epoch": 9.46924861512239e-05,
      "grad_norm": 2.8225064277648926,
      "learning_rate": 8e-05,
      "loss": 1.672,
      "step": 4
    },
    {
      "epoch": 0.00011836560768902987,
      "grad_norm": 2.1037559509277344,
      "learning_rate": 0.0001,
      "loss": 1.5066,
      "step": 5
    },
    {
      "epoch": 0.00014203872922683586,
      "grad_norm": 2.2576792240142822,
      "learning_rate": 0.00012,
      "loss": 1.9723,
      "step": 6
    },
    {
      "epoch": 0.00014203872922683586,
      "eval_loss": 1.6413675546646118,
      "eval_runtime": 1074.9501,
      "eval_samples_per_second": 16.547,
      "eval_steps_per_second": 8.274,
      "step": 6
    },
    {
      "epoch": 0.0001657118507646418,
      "grad_norm": 1.7553894519805908,
      "learning_rate": 0.00014,
      "loss": 1.7371,
      "step": 7
    },
    {
      "epoch": 0.0001893849723024478,
      "grad_norm": 2.429262638092041,
      "learning_rate": 0.00016,
      "loss": 1.7913,
      "step": 8
    },
    {
      "epoch": 0.00021305809384025378,
      "grad_norm": 2.018078327178955,
      "learning_rate": 0.00018,
      "loss": 1.1738,
      "step": 9
    },
    {
      "epoch": 0.00021305809384025378,
      "eval_loss": 1.3432157039642334,
      "eval_runtime": 1108.4642,
      "eval_samples_per_second": 16.047,
      "eval_steps_per_second": 8.024,
      "step": 9
    },
    {
      "epoch": 0.00023673121537805974,
      "grad_norm": 2.38704514503479,
      "learning_rate": 0.0002,
      "loss": 1.1479,
      "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": 1628733135912960.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}