Hugging Face's logo

nathanialhunt
/
618638da-3005-4c88-910c-fba189c48de3

PEFT
Safetensors
llama
axolotl
Generated from Trainer
custom_code
Model card Files Community
618638da-3005-4c88-910c-fba189c48de3
File size: 3,209 Bytes 
fa17a95
 
 
813f81e
fa17a95
813f81e
fa17a95
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
0792aff
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
165b558
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
813f81e
 
 
 
 
 
 
fa17a95
 
 
 
 
 
 
 
 
 
 
 
 
 
813f81e
fa17a95
 
 
 
813f81e
fa17a95
 
 
 
 
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": 0.0014972301242701003,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00014972301242701004,
      "grad_norm": 5.4886040687561035,
      "learning_rate": 2e-05,
      "loss": 13.9691,
      "step": 1
    },
    {
      "epoch": 0.00014972301242701004,
      "eval_loss": 3.1406643390655518,
      "eval_runtime": 94.6682,
      "eval_samples_per_second": 29.714,
      "eval_steps_per_second": 14.862,
      "step": 1
    },
    {
      "epoch": 0.0002994460248540201,
      "grad_norm": 3.7217674255371094,
      "learning_rate": 4e-05,
      "loss": 12.1924,
      "step": 2
    },
    {
      "epoch": 0.0004491690372810301,
      "grad_norm": 3.217331886291504,
      "learning_rate": 6e-05,
      "loss": 10.7015,
      "step": 3
    },
    {
      "epoch": 0.0004491690372810301,
      "eval_loss": 3.133810520172119,
      "eval_runtime": 94.5561,
      "eval_samples_per_second": 29.75,
      "eval_steps_per_second": 14.88,
      "step": 3
    },
    {
      "epoch": 0.0005988920497080402,
      "grad_norm": 4.119112014770508,
      "learning_rate": 8e-05,
      "loss": 13.303,
      "step": 4
    },
    {
      "epoch": 0.0007486150621350501,
      "grad_norm": 3.7569944858551025,
      "learning_rate": 0.0001,
      "loss": 12.3719,
      "step": 5
    },
    {
      "epoch": 0.0008983380745620602,
      "grad_norm": 5.156914710998535,
      "learning_rate": 0.00012,
      "loss": 13.0945,
      "step": 6
    },
    {
      "epoch": 0.0008983380745620602,
      "eval_loss": 3.020592451095581,
      "eval_runtime": 94.5439,
      "eval_samples_per_second": 29.753,
      "eval_steps_per_second": 14.882,
      "step": 6
    },
    {
      "epoch": 0.0010480610869890701,
      "grad_norm": 7.51618766784668,
      "learning_rate": 0.00014,
      "loss": 12.9868,
      "step": 7
    },
    {
      "epoch": 0.0011977840994160803,
      "grad_norm": 7.297400951385498,
      "learning_rate": 0.00016,
      "loss": 11.1761,
      "step": 8
    },
    {
      "epoch": 0.0013475071118430903,
      "grad_norm": 8.24133586883545,
      "learning_rate": 0.00018,
      "loss": 10.9402,
      "step": 9
    },
    {
      "epoch": 0.0013475071118430903,
      "eval_loss": 2.616652250289917,
      "eval_runtime": 94.4398,
      "eval_samples_per_second": 29.786,
      "eval_steps_per_second": 14.898,
      "step": 9
    },
    {
      "epoch": 0.0014972301242701003,
      "grad_norm": 11.070828437805176,
      "learning_rate": 0.0002,
      "loss": 10.0693,
      "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": 1750905435193344.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}