Hugging Face's logo

ardaspear
/
41cfc501-f7b2-4b8b-b351-08d8844513be

PEFT
Safetensors
falcon
axolotl
Generated from Trainer
custom_code
Model card Files Community
41cfc501-f7b2-4b8b-b351-08d8844513be
File size: 3,872 Bytes 
9ddd0ec
 
 
7f65e78
9ddd0ec
7f65e78
9ddd0ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
fae6e4c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
db7897c
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7f65e78
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9ddd0ec
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7f65e78
9ddd0ec
 
 
 
 
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
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
 
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04092071611253197,
  "eval_steps": 9,
  "global_step": 36,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011366865586814436,
      "eval_loss": 11.095451354980469,
      "eval_runtime": 5.6106,
      "eval_samples_per_second": 132.071,
      "eval_steps_per_second": 33.151,
      "step": 1
    },
    {
      "epoch": 0.0034100596760443308,
      "grad_norm": 2.3856959342956543,
      "learning_rate": 3e-05,
      "loss": 44.3673,
      "step": 3
    },
    {
      "epoch": 0.0068201193520886615,
      "grad_norm": 2.4655117988586426,
      "learning_rate": 6e-05,
      "loss": 44.3703,
      "step": 6
    },
    {
      "epoch": 0.010230179028132993,
      "grad_norm": 2.2212629318237305,
      "learning_rate": 9e-05,
      "loss": 44.3261,
      "step": 9
    },
    {
      "epoch": 0.010230179028132993,
      "eval_loss": 11.074569702148438,
      "eval_runtime": 4.7833,
      "eval_samples_per_second": 154.915,
      "eval_steps_per_second": 38.885,
      "step": 9
    },
    {
      "epoch": 0.013640238704177323,
      "grad_norm": 2.743508815765381,
      "learning_rate": 9.987820251299122e-05,
      "loss": 44.2612,
      "step": 12
    },
    {
      "epoch": 0.017050298380221655,
      "grad_norm": 1.8524738550186157,
      "learning_rate": 9.924038765061042e-05,
      "loss": 44.2154,
      "step": 15
    },
    {
      "epoch": 0.020460358056265986,
      "grad_norm": 1.639198660850525,
      "learning_rate": 9.806308479691595e-05,
      "loss": 44.167,
      "step": 18
    },
    {
      "epoch": 0.020460358056265986,
      "eval_loss": 11.030960083007812,
      "eval_runtime": 4.7631,
      "eval_samples_per_second": 155.569,
      "eval_steps_per_second": 39.05,
      "step": 18
    },
    {
      "epoch": 0.023870417732310314,
      "grad_norm": 1.5570883750915527,
      "learning_rate": 9.635919272833938e-05,
      "loss": 44.1426,
      "step": 21
    },
    {
      "epoch": 0.027280477408354646,
      "grad_norm": 1.5581414699554443,
      "learning_rate": 9.414737964294636e-05,
      "loss": 44.0753,
      "step": 24
    },
    {
      "epoch": 0.030690537084398978,
      "grad_norm": 1.6539247035980225,
      "learning_rate": 9.145187862775209e-05,
      "loss": 44.0163,
      "step": 27
    },
    {
      "epoch": 0.030690537084398978,
      "eval_loss": 10.998085021972656,
      "eval_runtime": 4.7738,
      "eval_samples_per_second": 155.223,
      "eval_steps_per_second": 38.963,
      "step": 27
    },
    {
      "epoch": 0.03410059676044331,
      "grad_norm": 1.4229531288146973,
      "learning_rate": 8.83022221559489e-05,
      "loss": 44.0237,
      "step": 30
    },
    {
      "epoch": 0.03751065643648764,
      "grad_norm": 1.3927640914916992,
      "learning_rate": 8.473291852294987e-05,
      "loss": 43.9566,
      "step": 33
    },
    {
      "epoch": 0.04092071611253197,
      "grad_norm": 1.352387547492981,
      "learning_rate": 8.07830737662829e-05,
      "loss": 43.9265,
      "step": 36
    },
    {
      "epoch": 0.04092071611253197,
      "eval_loss": 10.977602005004883,
      "eval_runtime": 4.7507,
      "eval_samples_per_second": 155.978,
      "eval_steps_per_second": 39.152,
      "step": 36
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 318520688640.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}