Hugging Face's logo

daniel40
/
c839e9b4-62a5-4aca-bf9a-0e3d93b4ef8a

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files Community
c839e9b4-62a5-4aca-bf9a-0e3d93b4ef8a
File size: 3,205 Bytes 
4b79f2b
 
 
bd157f0
4b79f2b
bd157f0
4b79f2b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4811edf
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
805158e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bd157f0
 
 
 
 
 
 
4b79f2b
 
 
 
 
 
 
 
 
 
 
 
 
 
bd157f0
4b79f2b
 
 
 
bd157f0
4b79f2b
 
 
 
 
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": 0.0035622050048980318,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00035622050048980317,
      "grad_norm": 0.9710186719894409,
      "learning_rate": 2e-05,
      "loss": 1.2377,
      "step": 1
    },
    {
      "epoch": 0.00035622050048980317,
      "eval_loss": 2.328693151473999,
      "eval_runtime": 33.1988,
      "eval_samples_per_second": 35.604,
      "eval_steps_per_second": 17.802,
      "step": 1
    },
    {
      "epoch": 0.0007124410009796063,
      "grad_norm": 0.877776563167572,
      "learning_rate": 4e-05,
      "loss": 1.5089,
      "step": 2
    },
    {
      "epoch": 0.0010686615014694097,
      "grad_norm": 1.2864619493484497,
      "learning_rate": 6e-05,
      "loss": 1.5115,
      "step": 3
    },
    {
      "epoch": 0.0010686615014694097,
      "eval_loss": 2.317746162414551,
      "eval_runtime": 33.2835,
      "eval_samples_per_second": 35.513,
      "eval_steps_per_second": 17.757,
      "step": 3
    },
    {
      "epoch": 0.0014248820019592127,
      "grad_norm": 1.4197344779968262,
      "learning_rate": 8e-05,
      "loss": 1.5582,
      "step": 4
    },
    {
      "epoch": 0.0017811025024490159,
      "grad_norm": 0.8563295006752014,
      "learning_rate": 0.0001,
      "loss": 0.9642,
      "step": 5
    },
    {
      "epoch": 0.0021373230029388193,
      "grad_norm": 0.9468586444854736,
      "learning_rate": 0.00012,
      "loss": 1.2557,
      "step": 6
    },
    {
      "epoch": 0.0021373230029388193,
      "eval_loss": 2.194425582885742,
      "eval_runtime": 33.2939,
      "eval_samples_per_second": 35.502,
      "eval_steps_per_second": 17.751,
      "step": 6
    },
    {
      "epoch": 0.002493543503428622,
      "grad_norm": 0.8728165030479431,
      "learning_rate": 0.00014,
      "loss": 1.3749,
      "step": 7
    },
    {
      "epoch": 0.0028497640039184253,
      "grad_norm": 0.936583399772644,
      "learning_rate": 0.00016,
      "loss": 1.4407,
      "step": 8
    },
    {
      "epoch": 0.0032059845044082286,
      "grad_norm": 0.7932253479957581,
      "learning_rate": 0.00018,
      "loss": 1.2949,
      "step": 9
    },
    {
      "epoch": 0.0032059845044082286,
      "eval_loss": 1.9489015340805054,
      "eval_runtime": 33.2862,
      "eval_samples_per_second": 35.51,
      "eval_steps_per_second": 17.755,
      "step": 9
    },
    {
      "epoch": 0.0035622050048980318,
      "grad_norm": 1.0440819263458252,
      "learning_rate": 0.0002,
      "loss": 1.0205,
      "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": 575111930314752.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}