Hugging Face's logo

cvoffer
/
5cc364b2-3adc-4706-bb76-1f31a385a0de

PEFT
Safetensors
gemma2
axolotl
Generated from Trainer
Model card Files Community
5cc364b2-3adc-4706-bb76-1f31a385a0de
File size: 3,083 Bytes 
8e44575
8ba1918
 
 
8e44575
8ba1918
8e44575
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8ba1918
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8e44575
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8ba1918
8e44575
 
 
 
 
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
 
{
  "best_metric": 1.1946930885314941,
  "best_model_checkpoint": "miner_id_24/checkpoint-20",
  "epoch": 0.0851063829787234,
  "eval_steps": 5,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00425531914893617,
      "eval_loss": 2.4387693405151367,
      "eval_runtime": 7.599,
      "eval_samples_per_second": 13.028,
      "eval_steps_per_second": 6.58,
      "step": 1
    },
    {
      "epoch": 0.01276595744680851,
      "grad_norm": 4.859747409820557,
      "learning_rate": 0.00012,
      "loss": 2.3682,
      "step": 3
    },
    {
      "epoch": 0.02127659574468085,
      "eval_loss": 1.6072040796279907,
      "eval_runtime": 7.7816,
      "eval_samples_per_second": 12.722,
      "eval_steps_per_second": 6.425,
      "step": 5
    },
    {
      "epoch": 0.02553191489361702,
      "grad_norm": 1.4412251710891724,
      "learning_rate": 0.0001992114701314478,
      "loss": 1.7322,
      "step": 6
    },
    {
      "epoch": 0.03829787234042553,
      "grad_norm": 1.558541178703308,
      "learning_rate": 0.00018763066800438636,
      "loss": 1.357,
      "step": 9
    },
    {
      "epoch": 0.0425531914893617,
      "eval_loss": 1.296438217163086,
      "eval_runtime": 7.9452,
      "eval_samples_per_second": 12.46,
      "eval_steps_per_second": 6.293,
      "step": 10
    },
    {
      "epoch": 0.05106382978723404,
      "grad_norm": 1.7230987548828125,
      "learning_rate": 0.000163742398974869,
      "loss": 1.4363,
      "step": 12
    },
    {
      "epoch": 0.06382978723404255,
      "grad_norm": 1.4550708532333374,
      "learning_rate": 0.00013090169943749476,
      "loss": 1.3038,
      "step": 15
    },
    {
      "epoch": 0.06382978723404255,
      "eval_loss": 1.222257137298584,
      "eval_runtime": 8.1242,
      "eval_samples_per_second": 12.186,
      "eval_steps_per_second": 6.154,
      "step": 15
    },
    {
      "epoch": 0.07659574468085106,
      "grad_norm": 1.2237554788589478,
      "learning_rate": 9.372094804706867e-05,
      "loss": 1.1423,
      "step": 18
    },
    {
      "epoch": 0.0851063829787234,
      "eval_loss": 1.1946930885314941,
      "eval_runtime": 8.2924,
      "eval_samples_per_second": 11.939,
      "eval_steps_per_second": 6.03,
      "step": 20
    }
  ],
  "logging_steps": 3,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 1,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "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
}