Hugging Face's logo

dimasik87
/
6813e4a9-59b5-485f-b2d9-38de43e7887d

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files Community
6813e4a9-59b5-485f-b2d9-38de43e7887d
File size: 3,531 Bytes 
6f91f5a
 
 
b9532f9
6f91f5a
b9532f9
6f91f5a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d0d959f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b9532f9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6f91f5a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
b9532f9
6f91f5a
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03230148048452221,
  "eval_steps": 4,
  "global_step": 12,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0026917900403768506,
      "grad_norm": 2.0982859134674072,
      "learning_rate": 2e-05,
      "loss": 0.7376,
      "step": 1
    },
    {
      "epoch": 0.0026917900403768506,
      "eval_loss": 0.7193137407302856,
      "eval_runtime": 10.1138,
      "eval_samples_per_second": 7.811,
      "eval_steps_per_second": 7.811,
      "step": 1
    },
    {
      "epoch": 0.005383580080753701,
      "grad_norm": 2.031587839126587,
      "learning_rate": 4e-05,
      "loss": 0.7275,
      "step": 2
    },
    {
      "epoch": 0.008075370121130552,
      "grad_norm": 2.1216890811920166,
      "learning_rate": 6e-05,
      "loss": 0.6912,
      "step": 3
    },
    {
      "epoch": 0.010767160161507403,
      "grad_norm": 1.755471110343933,
      "learning_rate": 8e-05,
      "loss": 0.6835,
      "step": 4
    },
    {
      "epoch": 0.010767160161507403,
      "eval_loss": 0.6272252202033997,
      "eval_runtime": 10.0256,
      "eval_samples_per_second": 7.88,
      "eval_steps_per_second": 7.88,
      "step": 4
    },
    {
      "epoch": 0.013458950201884253,
      "grad_norm": 1.9561946392059326,
      "learning_rate": 0.0001,
      "loss": 0.7364,
      "step": 5
    },
    {
      "epoch": 0.016150740242261104,
      "grad_norm": 1.8313077688217163,
      "learning_rate": 0.00012,
      "loss": 0.6385,
      "step": 6
    },
    {
      "epoch": 0.018842530282637954,
      "grad_norm": 1.4374486207962036,
      "learning_rate": 0.00014,
      "loss": 0.4741,
      "step": 7
    },
    {
      "epoch": 0.021534320323014805,
      "grad_norm": 1.279863715171814,
      "learning_rate": 0.00016,
      "loss": 0.3742,
      "step": 8
    },
    {
      "epoch": 0.021534320323014805,
      "eval_loss": 0.3805864155292511,
      "eval_runtime": 10.1128,
      "eval_samples_per_second": 7.812,
      "eval_steps_per_second": 7.812,
      "step": 8
    },
    {
      "epoch": 0.024226110363391656,
      "grad_norm": 1.7297841310501099,
      "learning_rate": 0.00018,
      "loss": 0.3654,
      "step": 9
    },
    {
      "epoch": 0.026917900403768506,
      "grad_norm": 1.6552913188934326,
      "learning_rate": 0.0002,
      "loss": 0.3738,
      "step": 10
    },
    {
      "epoch": 0.029609690444145357,
      "grad_norm": 1.50761079788208,
      "learning_rate": 0.0001996917333733128,
      "loss": 0.4244,
      "step": 11
    },
    {
      "epoch": 0.03230148048452221,
      "grad_norm": 1.431064248085022,
      "learning_rate": 0.00019876883405951377,
      "loss": 0.2788,
      "step": 12
    },
    {
      "epoch": 0.03230148048452221,
      "eval_loss": 0.32530486583709717,
      "eval_runtime": 10.0708,
      "eval_samples_per_second": 7.844,
      "eval_steps_per_second": 7.844,
      "step": 12
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 4,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5007739164033024.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}