Hugging Face's logo

gavrilstep
/
8d4a2e58-9f89-4f53-b4b4-22c28935b4ed

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
4-bit precision
bitsandbytes
Model card Files Community
8d4a2e58-9f89-4f53-b4b4-22c28935b4ed
File size: 2,807 Bytes 
f87b2d3
 
 
658a166
f87b2d3
658a166
f87b2d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
658a166
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f87b2d3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
658a166
f87b2d3
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05649717514124294,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002824858757062147,
      "eval_loss": 1.9134138822555542,
      "eval_runtime": 17.0767,
      "eval_samples_per_second": 8.784,
      "eval_steps_per_second": 4.392,
      "step": 1
    },
    {
      "epoch": 0.00847457627118644,
      "grad_norm": 22.408552169799805,
      "learning_rate": 6e-05,
      "loss": 1.9676,
      "step": 3
    },
    {
      "epoch": 0.014124293785310734,
      "eval_loss": 1.819502592086792,
      "eval_runtime": 17.0594,
      "eval_samples_per_second": 8.793,
      "eval_steps_per_second": 4.396,
      "step": 5
    },
    {
      "epoch": 0.01694915254237288,
      "grad_norm": 20.456899642944336,
      "learning_rate": 0.00012,
      "loss": 1.8743,
      "step": 6
    },
    {
      "epoch": 0.025423728813559324,
      "grad_norm": 2.078036069869995,
      "learning_rate": 0.00018,
      "loss": 1.7442,
      "step": 9
    },
    {
      "epoch": 0.02824858757062147,
      "eval_loss": 1.6691161394119263,
      "eval_runtime": 17.0825,
      "eval_samples_per_second": 8.781,
      "eval_steps_per_second": 4.39,
      "step": 10
    },
    {
      "epoch": 0.03389830508474576,
      "grad_norm": 0.814409077167511,
      "learning_rate": 0.00019510565162951537,
      "loss": 1.5952,
      "step": 12
    },
    {
      "epoch": 0.0423728813559322,
      "grad_norm": 0.873404324054718,
      "learning_rate": 0.00017071067811865476,
      "loss": 1.5137,
      "step": 15
    },
    {
      "epoch": 0.0423728813559322,
      "eval_loss": 1.5807734727859497,
      "eval_runtime": 17.144,
      "eval_samples_per_second": 8.749,
      "eval_steps_per_second": 4.375,
      "step": 15
    },
    {
      "epoch": 0.05084745762711865,
      "grad_norm": 0.7489776611328125,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.5281,
      "step": 18
    },
    {
      "epoch": 0.05649717514124294,
      "eval_loss": 1.543881893157959,
      "eval_runtime": 17.093,
      "eval_samples_per_second": 8.776,
      "eval_steps_per_second": 4.388,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2010596581048320.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}