Hugging Face's logo

kostiantynk
/
a54e460e-86b4-4b01-b8c9-f968572be82d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
a54e460e-86b4-4b01-b8c9-f968572be82d
File size: 3,235 Bytes 
16c8c6c
 
 
62bfa62
16c8c6c
62bfa62
16c8c6c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d9b5fa0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7f4191f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
62bfa62
 
 
 
 
 
 
16c8c6c
 
 
 
 
 
 
 
 
 
 
 
 
 
62bfa62
16c8c6c
 
 
 
62bfa62
16c8c6c
 
 
 
 
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": 0.0003216106260150835,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 3.2161062601508354e-05,
      "grad_norm": 0.037894561886787415,
      "learning_rate": 2e-05,
      "loss": 10.3721,
      "step": 1
    },
    {
      "epoch": 3.2161062601508354e-05,
      "eval_loss": 10.37723159790039,
      "eval_runtime": 40.3622,
      "eval_samples_per_second": 324.363,
      "eval_steps_per_second": 162.181,
      "step": 1
    },
    {
      "epoch": 6.432212520301671e-05,
      "grad_norm": 0.03640003129839897,
      "learning_rate": 4e-05,
      "loss": 10.3779,
      "step": 2
    },
    {
      "epoch": 9.648318780452506e-05,
      "grad_norm": 0.0508461557328701,
      "learning_rate": 6e-05,
      "loss": 10.3819,
      "step": 3
    },
    {
      "epoch": 9.648318780452506e-05,
      "eval_loss": 10.37720775604248,
      "eval_runtime": 39.8227,
      "eval_samples_per_second": 328.757,
      "eval_steps_per_second": 164.378,
      "step": 3
    },
    {
      "epoch": 0.00012864425040603342,
      "grad_norm": 0.0384635366499424,
      "learning_rate": 8e-05,
      "loss": 10.3668,
      "step": 4
    },
    {
      "epoch": 0.00016080531300754176,
      "grad_norm": 0.04587297514081001,
      "learning_rate": 0.0001,
      "loss": 10.3753,
      "step": 5
    },
    {
      "epoch": 0.0001929663756090501,
      "grad_norm": 0.04739292338490486,
      "learning_rate": 0.00012,
      "loss": 10.3766,
      "step": 6
    },
    {
      "epoch": 0.0001929663756090501,
      "eval_loss": 10.377087593078613,
      "eval_runtime": 40.4096,
      "eval_samples_per_second": 323.982,
      "eval_steps_per_second": 161.991,
      "step": 6
    },
    {
      "epoch": 0.00022512743821055849,
      "grad_norm": 0.030477037653326988,
      "learning_rate": 0.00014,
      "loss": 10.3733,
      "step": 7
    },
    {
      "epoch": 0.00025728850081206683,
      "grad_norm": 0.05945686623454094,
      "learning_rate": 0.00016,
      "loss": 10.3731,
      "step": 8
    },
    {
      "epoch": 0.0002894495634135752,
      "grad_norm": 0.03877415508031845,
      "learning_rate": 0.00018,
      "loss": 10.3822,
      "step": 9
    },
    {
      "epoch": 0.0002894495634135752,
      "eval_loss": 10.376890182495117,
      "eval_runtime": 40.4574,
      "eval_samples_per_second": 323.6,
      "eval_steps_per_second": 161.8,
      "step": 9
    },
    {
      "epoch": 0.0003216106260150835,
      "grad_norm": 0.04710560292005539,
      "learning_rate": 0.0002,
      "loss": 10.3771,
      "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": 142239989760.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}