Hugging Face's logo

nathanialhunt
/
1c474ca5-85dd-4220-9089-5093df561c87

PEFT
Safetensors
falcon
axolotl
Generated from Trainer
custom_code
Model card Files Community
1c474ca5-85dd-4220-9089-5093df561c87
File size: 3,171 Bytes 
d13bda9
 
 
f486d94
d13bda9
f486d94
d13bda9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
8340046
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
634a526
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
f486d94
 
 
 
 
 
 
d13bda9
 
 
 
 
 
 
 
 
 
 
 
 
 
f486d94
d13bda9
 
 
 
f486d94
d13bda9
 
 
 
 
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": 0.46511627906976744,
  "eval_steps": 3,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 16.168792724609375,
      "learning_rate": 2e-05,
      "loss": 12.5927,
      "step": 1
    },
    {
      "epoch": 0.046511627906976744,
      "eval_loss": 3.677544593811035,
      "eval_runtime": 0.1596,
      "eval_samples_per_second": 56.401,
      "eval_steps_per_second": 31.334,
      "step": 1
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 14.232671737670898,
      "learning_rate": 4e-05,
      "loss": 13.2225,
      "step": 2
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 16.136791229248047,
      "learning_rate": 6e-05,
      "loss": 12.742,
      "step": 3
    },
    {
      "epoch": 0.13953488372093023,
      "eval_loss": 3.6357693672180176,
      "eval_runtime": 0.1605,
      "eval_samples_per_second": 56.06,
      "eval_steps_per_second": 31.144,
      "step": 3
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 11.944231986999512,
      "learning_rate": 8e-05,
      "loss": 9.897,
      "step": 4
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 17.337947845458984,
      "learning_rate": 0.0001,
      "loss": 12.6181,
      "step": 5
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 17.71935272216797,
      "learning_rate": 0.00012,
      "loss": 11.1099,
      "step": 6
    },
    {
      "epoch": 0.27906976744186046,
      "eval_loss": 2.780703067779541,
      "eval_runtime": 0.1757,
      "eval_samples_per_second": 51.211,
      "eval_steps_per_second": 28.45,
      "step": 6
    },
    {
      "epoch": 0.32558139534883723,
      "grad_norm": 18.756610870361328,
      "learning_rate": 0.00014,
      "loss": 9.2466,
      "step": 7
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 18.909032821655273,
      "learning_rate": 0.00016,
      "loss": 8.2619,
      "step": 8
    },
    {
      "epoch": 0.4186046511627907,
      "grad_norm": 22.742977142333984,
      "learning_rate": 0.00018,
      "loss": 5.61,
      "step": 9
    },
    {
      "epoch": 0.4186046511627907,
      "eval_loss": 0.8675842881202698,
      "eval_runtime": 0.1575,
      "eval_samples_per_second": 57.131,
      "eval_steps_per_second": 31.74,
      "step": 9
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 17.746034622192383,
      "learning_rate": 0.0002,
      "loss": 3.3071,
      "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": 298572369100800.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}