Hugging Face's logo

vermoney
/
19b017f4-6c04-4ce7-943b-7d1eccc93a84

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
19b017f4-6c04-4ce7-943b-7d1eccc93a84
File size: 2,157 Bytes 
9787537
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
{
  "best_metric": 11.931994438171387,
  "best_model_checkpoint": "miner_id_24/checkpoint-10",
  "epoch": 0.02372479240806643,
  "eval_steps": 5,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002372479240806643,
      "eval_loss": 11.932109832763672,
      "eval_runtime": 1.9995,
      "eval_samples_per_second": 89.021,
      "eval_steps_per_second": 44.511,
      "step": 1
    },
    {
      "epoch": 0.0071174377224199285,
      "grad_norm": 0.0459056980907917,
      "learning_rate": 0.00012,
      "loss": 11.9296,
      "step": 3
    },
    {
      "epoch": 0.011862396204033215,
      "eval_loss": 11.931997299194336,
      "eval_runtime": 2.1797,
      "eval_samples_per_second": 81.664,
      "eval_steps_per_second": 40.832,
      "step": 5
    },
    {
      "epoch": 0.014234875444839857,
      "grad_norm": 0.044158995151519775,
      "learning_rate": 0.0001992114701314478,
      "loss": 11.9327,
      "step": 6
    },
    {
      "epoch": 0.021352313167259787,
      "grad_norm": 0.05341486632823944,
      "learning_rate": 0.00018763066800438636,
      "loss": 11.9311,
      "step": 9
    },
    {
      "epoch": 0.02372479240806643,
      "eval_loss": 11.931994438171387,
      "eval_runtime": 1.9968,
      "eval_samples_per_second": 89.141,
      "eval_steps_per_second": 44.571,
      "step": 10
    }
  ],
  "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": 3747348480.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}