Hugging Face's logo

JacksonBrune
/
b76d293f-281f-4589-8343-d3aad9a7c3d5

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files Community
b76d293f-281f-4589-8343-d3aad9a7c3d5
File size: 2,955 Bytes 
147ca94
 
 
5564dc5
147ca94
5564dc5
147ca94
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5d96a34
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
82ad6b8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5564dc5
 
 
 
 
 
 
147ca94
 
 
 
 
 
 
 
 
 
 
 
 
 
5564dc5
147ca94
 
 
 
5564dc5
147ca94
 
 
 
 
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": 0.007950705625124229,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000795070562512423,
      "grad_norm": NaN,
      "learning_rate": 2e-05,
      "loss": 0.0,
      "step": 1
    },
    {
      "epoch": 0.000795070562512423,
      "eval_loss": NaN,
      "eval_runtime": 19.9186,
      "eval_samples_per_second": 26.608,
      "eval_steps_per_second": 13.304,
      "step": 1
    },
    {
      "epoch": 0.001590141125024846,
      "grad_norm": NaN,
      "learning_rate": 4e-05,
      "loss": 0.0,
      "step": 2
    },
    {
      "epoch": 0.002385211687537269,
      "grad_norm": NaN,
      "learning_rate": 6e-05,
      "loss": 0.0,
      "step": 3
    },
    {
      "epoch": 0.002385211687537269,
      "eval_loss": NaN,
      "eval_runtime": 18.7547,
      "eval_samples_per_second": 28.26,
      "eval_steps_per_second": 14.13,
      "step": 3
    },
    {
      "epoch": 0.003180282250049692,
      "grad_norm": NaN,
      "learning_rate": 8e-05,
      "loss": 0.0,
      "step": 4
    },
    {
      "epoch": 0.0039753528125621145,
      "grad_norm": NaN,
      "learning_rate": 0.0001,
      "loss": 0.0,
      "step": 5
    },
    {
      "epoch": 0.004770423375074538,
      "grad_norm": NaN,
      "learning_rate": 0.00012,
      "loss": 0.0,
      "step": 6
    },
    {
      "epoch": 0.004770423375074538,
      "eval_loss": NaN,
      "eval_runtime": 19.0613,
      "eval_samples_per_second": 27.805,
      "eval_steps_per_second": 13.903,
      "step": 6
    },
    {
      "epoch": 0.005565493937586961,
      "grad_norm": NaN,
      "learning_rate": 0.00014,
      "loss": 0.0,
      "step": 7
    },
    {
      "epoch": 0.006360564500099384,
      "grad_norm": NaN,
      "learning_rate": 0.00016,
      "loss": 0.0,
      "step": 8
    },
    {
      "epoch": 0.007155635062611807,
      "grad_norm": NaN,
      "learning_rate": 0.00018,
      "loss": 0.0,
      "step": 9
    },
    {
      "epoch": 0.007155635062611807,
      "eval_loss": NaN,
      "eval_runtime": 18.8351,
      "eval_samples_per_second": 28.139,
      "eval_steps_per_second": 14.069,
      "step": 9
    },
    {
      "epoch": 0.007950705625124229,
      "grad_norm": NaN,
      "learning_rate": 0.0002,
      "loss": 0.0,
      "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": 2103203743137792.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}