Hugging Face's logo

cs552-mlp
/
phi3-openbookqa

PEFT
Safetensors
Model card Files
xet
Community
phi3-openbookqa
File size: 4,616 Bytes 
b128aa3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
 
{
  "best_metric": 1.5293647050857544,
  "best_model_checkpoint": "./output/checkpoints/2024-06-10_15-16-32/checkpoint-10",
  "epoch": 0.5263157894736842,
  "eval_steps": 1,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 22.303813934326172,
      "learning_rate": 0.0002,
      "loss": 5.2005,
      "step": 1
    },
    {
      "epoch": 0.05263157894736842,
      "eval_loss": 5.126399993896484,
      "eval_runtime": 8.3738,
      "eval_samples_per_second": 7.404,
      "eval_steps_per_second": 0.478,
      "step": 1
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 21.968650817871094,
      "learning_rate": 0.0004,
      "loss": 5.1548,
      "step": 2
    },
    {
      "epoch": 0.10526315789473684,
      "eval_loss": 2.035064935684204,
      "eval_runtime": 8.1279,
      "eval_samples_per_second": 7.628,
      "eval_steps_per_second": 0.492,
      "step": 2
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 4.796197891235352,
      "learning_rate": 0.00037647058823529414,
      "loss": 1.9739,
      "step": 3
    },
    {
      "epoch": 0.15789473684210525,
      "eval_loss": 1.565435767173767,
      "eval_runtime": 8.1953,
      "eval_samples_per_second": 7.565,
      "eval_steps_per_second": 0.488,
      "step": 3
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 2.5580379962921143,
      "learning_rate": 0.00035294117647058826,
      "loss": 1.5127,
      "step": 4
    },
    {
      "epoch": 0.21052631578947367,
      "eval_loss": 1.5319403409957886,
      "eval_runtime": 8.2189,
      "eval_samples_per_second": 7.544,
      "eval_steps_per_second": 0.487,
      "step": 4
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 1.5636128187179565,
      "learning_rate": 0.0003294117647058824,
      "loss": 1.5023,
      "step": 5
    },
    {
      "epoch": 0.2631578947368421,
      "eval_loss": 1.4795572757720947,
      "eval_runtime": 8.1979,
      "eval_samples_per_second": 7.563,
      "eval_steps_per_second": 0.488,
      "step": 5
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.6475034952163696,
      "learning_rate": 0.00030588235294117644,
      "loss": 1.4094,
      "step": 6
    },
    {
      "epoch": 0.3157894736842105,
      "eval_loss": 1.4736040830612183,
      "eval_runtime": 8.1682,
      "eval_samples_per_second": 7.59,
      "eval_steps_per_second": 0.49,
      "step": 6
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 1.273154616355896,
      "learning_rate": 0.0002823529411764706,
      "loss": 1.2526,
      "step": 7
    },
    {
      "epoch": 0.3684210526315789,
      "eval_loss": 1.801269292831421,
      "eval_runtime": 8.1796,
      "eval_samples_per_second": 7.58,
      "eval_steps_per_second": 0.489,
      "step": 7
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 1.148282527923584,
      "learning_rate": 0.00025882352941176474,
      "loss": 1.2184,
      "step": 8
    },
    {
      "epoch": 0.42105263157894735,
      "eval_loss": 1.6574877500534058,
      "eval_runtime": 8.2558,
      "eval_samples_per_second": 7.51,
      "eval_steps_per_second": 0.485,
      "step": 8
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.6692990064620972,
      "learning_rate": 0.00023529411764705883,
      "loss": 1.1489,
      "step": 9
    },
    {
      "epoch": 0.47368421052631576,
      "eval_loss": 1.5531737804412842,
      "eval_runtime": 8.2574,
      "eval_samples_per_second": 7.508,
      "eval_steps_per_second": 0.484,
      "step": 9
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.5520226955413818,
      "learning_rate": 0.00021176470588235295,
      "loss": 1.1021,
      "step": 10
    },
    {
      "epoch": 0.5263157894736842,
      "eval_loss": 1.5293647050857544,
      "eval_runtime": 8.3253,
      "eval_samples_per_second": 7.447,
      "eval_steps_per_second": 0.48,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 19,
  "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": 7436398315438080.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}