Hugging Face's logo

daniel40
/
2e10f7b2-5c08-4ed8-bf14-216565c32694

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
2e10f7b2-5c08-4ed8-bf14-216565c32694
File size: 2,093 Bytes 
9d46e38
 
 
c5527bd
9d46e38
c5527bd
9d46e38
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5f18962
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c5527bd
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9d46e38
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c5527bd
9d46e38
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06320907617504051,
  "eval_steps": 13,
  "global_step": 39,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0016207455429497568,
      "eval_loss": 3.8959412574768066,
      "eval_runtime": 5.4702,
      "eval_samples_per_second": 47.53,
      "eval_steps_per_second": 23.765,
      "step": 1
    },
    {
      "epoch": 0.01620745542949757,
      "grad_norm": 0.8758059144020081,
      "learning_rate": 0.0002,
      "loss": 3.4861,
      "step": 10
    },
    {
      "epoch": 0.02106969205834684,
      "eval_loss": 3.616358757019043,
      "eval_runtime": 4.4298,
      "eval_samples_per_second": 58.693,
      "eval_steps_per_second": 29.347,
      "step": 13
    },
    {
      "epoch": 0.03241491085899514,
      "grad_norm": 1.264078140258789,
      "learning_rate": 0.00017071067811865476,
      "loss": 3.47,
      "step": 20
    },
    {
      "epoch": 0.04213938411669368,
      "eval_loss": 3.4697425365448,
      "eval_runtime": 4.4531,
      "eval_samples_per_second": 58.387,
      "eval_steps_per_second": 29.193,
      "step": 26
    },
    {
      "epoch": 0.04862236628849271,
      "grad_norm": 0.9814926981925964,
      "learning_rate": 0.0001,
      "loss": 3.2828,
      "step": 30
    },
    {
      "epoch": 0.06320907617504051,
      "eval_loss": 3.4281005859375,
      "eval_runtime": 4.4556,
      "eval_samples_per_second": 58.353,
      "eval_steps_per_second": 29.177,
      "step": 39
    }
  ],
  "logging_steps": 10,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 352929491976192.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}