Hugging Face's logo

kostiantynk
/
bdafea2a-fcdb-42ac-a6fb-4fbfb8c0e281

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files Community
bdafea2a-fcdb-42ac-a6fb-4fbfb8c0e281
File size: 3,176 Bytes 
2e29b6c
 
 
206d417
2e29b6c
206d417
2e29b6c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2e71ac3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2535ce9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
206d417
 
 
 
 
 
 
2e29b6c
 
 
 
 
 
 
 
 
 
 
 
 
 
206d417
2e29b6c
 
 
 
206d417
2e29b6c
 
 
 
 
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": 0.0049800796812749,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00049800796812749,
      "grad_norm": 1.4692789316177368,
      "learning_rate": 2e-05,
      "loss": 2.8063,
      "step": 1
    },
    {
      "epoch": 0.00049800796812749,
      "eval_loss": 2.97845196723938,
      "eval_runtime": 45.5862,
      "eval_samples_per_second": 18.558,
      "eval_steps_per_second": 9.279,
      "step": 1
    },
    {
      "epoch": 0.00099601593625498,
      "grad_norm": 1.4389501810073853,
      "learning_rate": 4e-05,
      "loss": 2.8635,
      "step": 2
    },
    {
      "epoch": 0.00149402390438247,
      "grad_norm": 2.2483975887298584,
      "learning_rate": 6e-05,
      "loss": 3.4006,
      "step": 3
    },
    {
      "epoch": 0.00149402390438247,
      "eval_loss": 2.9519526958465576,
      "eval_runtime": 45.5115,
      "eval_samples_per_second": 18.589,
      "eval_steps_per_second": 9.294,
      "step": 3
    },
    {
      "epoch": 0.00199203187250996,
      "grad_norm": 1.5795270204544067,
      "learning_rate": 8e-05,
      "loss": 2.7943,
      "step": 4
    },
    {
      "epoch": 0.00249003984063745,
      "grad_norm": 1.3678991794586182,
      "learning_rate": 0.0001,
      "loss": 2.6807,
      "step": 5
    },
    {
      "epoch": 0.00298804780876494,
      "grad_norm": 1.5033429861068726,
      "learning_rate": 0.00012,
      "loss": 2.8275,
      "step": 6
    },
    {
      "epoch": 0.00298804780876494,
      "eval_loss": 2.6760687828063965,
      "eval_runtime": 45.6888,
      "eval_samples_per_second": 18.517,
      "eval_steps_per_second": 9.258,
      "step": 6
    },
    {
      "epoch": 0.0034860557768924302,
      "grad_norm": 1.0134755373001099,
      "learning_rate": 0.00014,
      "loss": 2.4683,
      "step": 7
    },
    {
      "epoch": 0.00398406374501992,
      "grad_norm": 0.830837607383728,
      "learning_rate": 0.00016,
      "loss": 2.5534,
      "step": 8
    },
    {
      "epoch": 0.004482071713147411,
      "grad_norm": 0.8642377853393555,
      "learning_rate": 0.00018,
      "loss": 2.5087,
      "step": 9
    },
    {
      "epoch": 0.004482071713147411,
      "eval_loss": 2.5361790657043457,
      "eval_runtime": 45.6708,
      "eval_samples_per_second": 18.524,
      "eval_steps_per_second": 9.262,
      "step": 9
    },
    {
      "epoch": 0.0049800796812749,
      "grad_norm": 0.9797606468200684,
      "learning_rate": 0.0002,
      "loss": 2.4235,
      "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": 2514182181224448.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}