Hugging Face's logo

adammandic87
/
501a45e1-b5dc-4804-a72e-53d81037b496

PEFT
Safetensors
gpt_neox
axolotl
Generated from Trainer
Model card Files Community
501a45e1-b5dc-4804-a72e-53d81037b496
File size: 3,190 Bytes 
476e7c0
 
 
cc1d2d0
476e7c0
cc1d2d0
476e7c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3c251c6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4044092
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
cc1d2d0
 
 
 
 
 
 
476e7c0
 
 
 
 
 
 
 
 
 
 
 
 
 
cc1d2d0
476e7c0
 
 
 
cc1d2d0
476e7c0
 
 
 
 
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
126
127
128
129
130
131
132
133
134
135
136
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01002004008016032,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001002004008016032,
      "grad_norm": 0.34832796454429626,
      "learning_rate": 2e-05,
      "loss": 5.0781,
      "step": 1
    },
    {
      "epoch": 0.001002004008016032,
      "eval_loss": 1.245298981666565,
      "eval_runtime": 32.1607,
      "eval_samples_per_second": 13.091,
      "eval_steps_per_second": 6.561,
      "step": 1
    },
    {
      "epoch": 0.002004008016032064,
      "grad_norm": 0.3496541380882263,
      "learning_rate": 4e-05,
      "loss": 5.1646,
      "step": 2
    },
    {
      "epoch": 0.003006012024048096,
      "grad_norm": 0.3487575948238373,
      "learning_rate": 6e-05,
      "loss": 4.7958,
      "step": 3
    },
    {
      "epoch": 0.003006012024048096,
      "eval_loss": 1.2446060180664062,
      "eval_runtime": 30.9161,
      "eval_samples_per_second": 13.618,
      "eval_steps_per_second": 6.825,
      "step": 3
    },
    {
      "epoch": 0.004008016032064128,
      "grad_norm": 0.3600659966468811,
      "learning_rate": 8e-05,
      "loss": 4.7573,
      "step": 4
    },
    {
      "epoch": 0.00501002004008016,
      "grad_norm": 0.43822160363197327,
      "learning_rate": 0.0001,
      "loss": 4.6953,
      "step": 5
    },
    {
      "epoch": 0.006012024048096192,
      "grad_norm": 0.5357103943824768,
      "learning_rate": 0.00012,
      "loss": 4.6973,
      "step": 6
    },
    {
      "epoch": 0.006012024048096192,
      "eval_loss": 1.2071658372879028,
      "eval_runtime": 31.0044,
      "eval_samples_per_second": 13.579,
      "eval_steps_per_second": 6.805,
      "step": 6
    },
    {
      "epoch": 0.0070140280561122245,
      "grad_norm": 0.6890850067138672,
      "learning_rate": 0.00014,
      "loss": 4.7609,
      "step": 7
    },
    {
      "epoch": 0.008016032064128256,
      "grad_norm": 0.7650081515312195,
      "learning_rate": 0.00016,
      "loss": 4.4633,
      "step": 8
    },
    {
      "epoch": 0.009018036072144289,
      "grad_norm": 1.066926121711731,
      "learning_rate": 0.00018,
      "loss": 4.3805,
      "step": 9
    },
    {
      "epoch": 0.009018036072144289,
      "eval_loss": 1.0714982748031616,
      "eval_runtime": 30.8589,
      "eval_samples_per_second": 13.643,
      "eval_steps_per_second": 6.838,
      "step": 9
    },
    {
      "epoch": 0.01002004008016032,
      "grad_norm": 1.0714696645736694,
      "learning_rate": 0.0002,
      "loss": 4.1267,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 10,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6274650262732800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}