Hugging Face's logo

cs552-mlp
/
phi3-lora-openbookqa3

PEFT
Safetensors
Model card Files Community
phi3-lora-openbookqa3
File size: 4,639 Bytes 
801acfa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": 1.6195639371871948,
  "best_model_checkpoint": "./output/checkpoints/2024-06-11_15-20-56/checkpoint-10",
  "epoch": 0.2702702702702703,
  "eval_steps": 1,
  "global_step": 10,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02702702702702703,
      "grad_norm": 3.045227289199829,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 5.5922,
      "step": 1
    },
    {
      "epoch": 0.02702702702702703,
      "eval_loss": 5.6431684494018555,
      "eval_runtime": 11.0821,
      "eval_samples_per_second": 11.189,
      "eval_steps_per_second": 0.722,
      "step": 1
    },
    {
      "epoch": 0.05405405405405406,
      "grad_norm": 3.084507942199707,
      "learning_rate": 6.666666666666667e-05,
      "loss": 5.6812,
      "step": 2
    },
    {
      "epoch": 0.05405405405405406,
      "eval_loss": 5.540425777435303,
      "eval_runtime": 11.083,
      "eval_samples_per_second": 11.188,
      "eval_steps_per_second": 0.722,
      "step": 2
    },
    {
      "epoch": 0.08108108108108109,
      "grad_norm": 3.1143131256103516,
      "learning_rate": 0.0001,
      "loss": 5.5805,
      "step": 3
    },
    {
      "epoch": 0.08108108108108109,
      "eval_loss": 5.062227725982666,
      "eval_runtime": 11.1285,
      "eval_samples_per_second": 11.143,
      "eval_steps_per_second": 0.719,
      "step": 3
    },
    {
      "epoch": 0.10810810810810811,
      "grad_norm": 3.3044817447662354,
      "learning_rate": 0.00013333333333333334,
      "loss": 5.0744,
      "step": 4
    },
    {
      "epoch": 0.10810810810810811,
      "eval_loss": 4.176051139831543,
      "eval_runtime": 11.2317,
      "eval_samples_per_second": 11.04,
      "eval_steps_per_second": 0.712,
      "step": 4
    },
    {
      "epoch": 0.13513513513513514,
      "grad_norm": 3.3503236770629883,
      "learning_rate": 0.0001666666666666667,
      "loss": 4.1348,
      "step": 5
    },
    {
      "epoch": 0.13513513513513514,
      "eval_loss": 3.137871265411377,
      "eval_runtime": 11.1384,
      "eval_samples_per_second": 11.133,
      "eval_steps_per_second": 0.718,
      "step": 5
    },
    {
      "epoch": 0.16216216216216217,
      "grad_norm": 2.9682626724243164,
      "learning_rate": 0.0002,
      "loss": 3.0425,
      "step": 6
    },
    {
      "epoch": 0.16216216216216217,
      "eval_loss": 2.459784746170044,
      "eval_runtime": 11.1086,
      "eval_samples_per_second": 11.163,
      "eval_steps_per_second": 0.72,
      "step": 6
    },
    {
      "epoch": 0.1891891891891892,
      "grad_norm": 1.8949077129364014,
      "learning_rate": 0.00023333333333333336,
      "loss": 2.3291,
      "step": 7
    },
    {
      "epoch": 0.1891891891891892,
      "eval_loss": 2.064051866531372,
      "eval_runtime": 11.1293,
      "eval_samples_per_second": 11.142,
      "eval_steps_per_second": 0.719,
      "step": 7
    },
    {
      "epoch": 0.21621621621621623,
      "grad_norm": 1.2975975275039673,
      "learning_rate": 0.0002666666666666667,
      "loss": 1.9481,
      "step": 8
    },
    {
      "epoch": 0.21621621621621623,
      "eval_loss": 1.826060175895691,
      "eval_runtime": 11.1457,
      "eval_samples_per_second": 11.125,
      "eval_steps_per_second": 0.718,
      "step": 8
    },
    {
      "epoch": 0.24324324324324326,
      "grad_norm": 0.9844012260437012,
      "learning_rate": 0.00030000000000000003,
      "loss": 1.6863,
      "step": 9
    },
    {
      "epoch": 0.24324324324324326,
      "eval_loss": 1.7158275842666626,
      "eval_runtime": 11.1384,
      "eval_samples_per_second": 11.133,
      "eval_steps_per_second": 0.718,
      "step": 9
    },
    {
      "epoch": 0.2702702702702703,
      "grad_norm": 0.9899163246154785,
      "learning_rate": 0.0003333333333333334,
      "loss": 1.6293,
      "step": 10
    },
    {
      "epoch": 0.2702702702702703,
      "eval_loss": 1.6195639371871948,
      "eval_runtime": 11.1633,
      "eval_samples_per_second": 11.108,
      "eval_steps_per_second": 0.717,
      "step": 10
    }
  ],
  "logging_steps": 1,
  "max_steps": 111,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "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": 3708922028359680.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}