Hugging Face's logo

filipesantoscv11
/
82e750a7-1d14-42f9-882e-7c7d351b567b

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files Community
82e750a7-1d14-42f9-882e-7c7d351b567b
File size: 2,391 Bytes 
6a0862e
 
 
25e8fcc
6a0862e
25e8fcc
6a0862e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25e8fcc
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6a0862e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25e8fcc
6a0862e
 
 
 
 
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
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012202562538133009,
  "eval_steps": 8,
  "global_step": 20,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006101281269066504,
      "eval_loss": 6.149837493896484,
      "eval_runtime": 13.1757,
      "eval_samples_per_second": 52.445,
      "eval_steps_per_second": 26.261,
      "step": 1
    },
    {
      "epoch": 0.0018303843807199512,
      "grad_norm": 2.8964645862579346,
      "learning_rate": 3e-05,
      "loss": 5.932,
      "step": 3
    },
    {
      "epoch": 0.0036607687614399025,
      "grad_norm": 2.998232364654541,
      "learning_rate": 6e-05,
      "loss": 6.0007,
      "step": 6
    },
    {
      "epoch": 0.004881025015253203,
      "eval_loss": 5.871977806091309,
      "eval_runtime": 12.2074,
      "eval_samples_per_second": 56.605,
      "eval_steps_per_second": 28.343,
      "step": 8
    },
    {
      "epoch": 0.005491153142159854,
      "grad_norm": 2.0585145950317383,
      "learning_rate": 9e-05,
      "loss": 5.5782,
      "step": 9
    },
    {
      "epoch": 0.007321537522879805,
      "grad_norm": 3.959272623062134,
      "learning_rate": 9.755282581475769e-05,
      "loss": 5.8618,
      "step": 12
    },
    {
      "epoch": 0.009151921903599756,
      "grad_norm": 1.9303548336029053,
      "learning_rate": 8.535533905932738e-05,
      "loss": 5.3369,
      "step": 15
    },
    {
      "epoch": 0.009762050030506406,
      "eval_loss": 5.450654983520508,
      "eval_runtime": 12.3075,
      "eval_samples_per_second": 56.145,
      "eval_steps_per_second": 28.113,
      "step": 16
    },
    {
      "epoch": 0.010982306284319707,
      "grad_norm": 2.4457473754882812,
      "learning_rate": 6.545084971874738e-05,
      "loss": 5.3219,
      "step": 18
    }
  ],
  "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": 310615725834240.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}