File size: 5,625 Bytes
017f2e3
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 4.0,
  "eval_steps": 500,
  "global_step": 9956,
  "is_hyper_param_search": true,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2008838891120932,
      "grad_norm": 2.296739339828491,
      "learning_rate": 1.0356804114498648e-06,
      "loss": 0.5028,
      "step": 500
    },
    {
      "epoch": 0.4017677782241864,
      "grad_norm": 2.885403871536255,
      "learning_rate": 9.9232836408905e-07,
      "loss": 0.1797,
      "step": 1000
    },
    {
      "epoch": 0.6026516673362796,
      "grad_norm": 4.714044570922852,
      "learning_rate": 9.489763167282352e-07,
      "loss": 0.1448,
      "step": 1500
    },
    {
      "epoch": 0.8035355564483728,
      "grad_norm": 3.8532094955444336,
      "learning_rate": 9.056242693674206e-07,
      "loss": 0.1199,
      "step": 2000
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.9636836795859589,
      "eval_f1": 0.6468026587210636,
      "eval_loss": 0.10681386291980743,
      "eval_precision": 0.5823359471729261,
      "eval_recall": 0.727319587628866,
      "eval_runtime": 20.4746,
      "eval_samples_per_second": 208.356,
      "eval_steps_per_second": 26.081,
      "step": 2489
    },
    {
      "epoch": 1.004419445560466,
      "grad_norm": 1.4627267122268677,
      "learning_rate": 8.622722220066057e-07,
      "loss": 0.1126,
      "step": 2500
    },
    {
      "epoch": 1.2053033346725592,
      "grad_norm": 2.071267604827881,
      "learning_rate": 8.189201746457909e-07,
      "loss": 0.1053,
      "step": 3000
    },
    {
      "epoch": 1.4061872237846524,
      "grad_norm": 6.656711101531982,
      "learning_rate": 7.755681272849762e-07,
      "loss": 0.0984,
      "step": 3500
    },
    {
      "epoch": 1.6070711128967456,
      "grad_norm": 1.1916735172271729,
      "learning_rate": 7.322160799241614e-07,
      "loss": 0.0966,
      "step": 4000
    },
    {
      "epoch": 1.8079550020088389,
      "grad_norm": 2.3483071327209473,
      "learning_rate": 6.888640325633467e-07,
      "loss": 0.0914,
      "step": 4500
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.9708767672041989,
      "eval_f1": 0.7143198661247907,
      "eval_loss": 0.0914178416132927,
      "eval_precision": 0.6660722246990638,
      "eval_recall": 0.7701030927835052,
      "eval_runtime": 19.9542,
      "eval_samples_per_second": 213.79,
      "eval_steps_per_second": 26.761,
      "step": 4978
    },
    {
      "epoch": 2.008838891120932,
      "grad_norm": 4.1778669357299805,
      "learning_rate": 6.455119852025319e-07,
      "loss": 0.0846,
      "step": 5000
    },
    {
      "epoch": 2.2097227802330255,
      "grad_norm": 2.798360586166382,
      "learning_rate": 6.02159937841717e-07,
      "loss": 0.0857,
      "step": 5500
    },
    {
      "epoch": 2.4106066693451185,
      "grad_norm": 1.7000788450241089,
      "learning_rate": 5.588078904809024e-07,
      "loss": 0.0809,
      "step": 6000
    },
    {
      "epoch": 2.611490558457212,
      "grad_norm": 2.7977373600006104,
      "learning_rate": 5.154558431200876e-07,
      "loss": 0.083,
      "step": 6500
    },
    {
      "epoch": 2.812374447569305,
      "grad_norm": 2.01316499710083,
      "learning_rate": 4.721037957592728e-07,
      "loss": 0.0776,
      "step": 7000
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.9727700697378616,
      "eval_f1": 0.7365162519347542,
      "eval_loss": 0.08494957536458969,
      "eval_precision": 0.6844434609426865,
      "eval_recall": 0.7971649484536083,
      "eval_runtime": 19.9143,
      "eval_samples_per_second": 214.218,
      "eval_steps_per_second": 26.815,
      "step": 7467
    },
    {
      "epoch": 3.0132583366813983,
      "grad_norm": 0.729656457901001,
      "learning_rate": 4.287517483984581e-07,
      "loss": 0.0834,
      "step": 7500
    },
    {
      "epoch": 3.2141422257934913,
      "grad_norm": 4.330155849456787,
      "learning_rate": 3.853997010376433e-07,
      "loss": 0.0772,
      "step": 8000
    },
    {
      "epoch": 3.4150261149055847,
      "grad_norm": 2.2002146244049072,
      "learning_rate": 3.420476536768285e-07,
      "loss": 0.075,
      "step": 8500
    },
    {
      "epoch": 3.6159100040176777,
      "grad_norm": 2.16339111328125,
      "learning_rate": 2.9869560631601374e-07,
      "loss": 0.0753,
      "step": 9000
    },
    {
      "epoch": 3.816793893129771,
      "grad_norm": 1.6610848903656006,
      "learning_rate": 2.55343558955199e-07,
      "loss": 0.0696,
      "step": 9500
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.9732963932221231,
      "eval_f1": 0.7483106105512746,
      "eval_loss": 0.0842830166220665,
      "eval_precision": 0.6928649835345774,
      "eval_recall": 0.8134020618556701,
      "eval_runtime": 21.3601,
      "eval_samples_per_second": 199.718,
      "eval_steps_per_second": 25.0,
      "step": 9956
    }
  ],
  "logging_steps": 500,
  "max_steps": 12445,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 5,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2474729943855180.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": {
    "learning_rate": 1.0790324588106795e-06,
    "num_train_epochs": 5,
    "per_device_train_batch_size": 8,
    "seed": 32
  }
}