File size: 5,937 Bytes
3f23f19
 
 
10465d2
 
3f23f19
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
525c241
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
20417b5
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
bb5f68d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98d0e27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
c067a76
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
35cb6bb
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
eb6a777
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
362f6b1
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
26bb0d4
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
10465d2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3f23f19
 
 
 
10465d2
3f23f19
 
 
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
{
  "best_metric": 1.528552770614624,
  "best_model_checkpoint": "/home2/s5431786/jb-internship-repr/results/Salesforce-codet5-small-java-small-selected-wo-tokens/checkpoint-2000",
  "epoch": 3.051740879456235,
  "global_step": 22000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.28,
      "learning_rate": 9.94363646983237e-05,
      "loss": 2.1009,
      "step": 2000
    },
    {
      "epoch": 0.28,
      "eval_exact_match": 0.31785774198959904,
      "eval_loss": 1.528552770614624,
      "eval_rouge1": 0.5232290073169683,
      "eval_rouge2": 0.24795642157242634,
      "eval_rougeL": 0.5233033679411545,
      "eval_runtime": 163.446,
      "eval_samples_per_second": 145.883,
      "eval_steps_per_second": 1.523,
      "step": 2000
    },
    {
      "epoch": 0.55,
      "learning_rate": 9.359558437007184e-05,
      "loss": 1.3098,
      "step": 4000
    },
    {
      "epoch": 0.55,
      "eval_exact_match": 0.29667840966280823,
      "eval_loss": 1.5582195520401,
      "eval_rouge1": 0.499918373090859,
      "eval_rouge2": 0.22982882883486827,
      "eval_rougeL": 0.49974542584946463,
      "eval_runtime": 169.5108,
      "eval_samples_per_second": 140.664,
      "eval_steps_per_second": 1.469,
      "step": 4000
    },
    {
      "epoch": 0.83,
      "learning_rate": 8.775480404182e-05,
      "loss": 1.1968,
      "step": 6000
    },
    {
      "epoch": 0.83,
      "eval_exact_match": 0.321003187384667,
      "eval_loss": 1.551592469215393,
      "eval_rouge1": 0.5260578932396776,
      "eval_rouge2": 0.25462429236963685,
      "eval_rougeL": 0.5257669098334219,
      "eval_runtime": 163.9432,
      "eval_samples_per_second": 145.441,
      "eval_steps_per_second": 1.519,
      "step": 6000
    },
    {
      "epoch": 1.11,
      "learning_rate": 8.191402371356814e-05,
      "loss": 1.1145,
      "step": 8000
    },
    {
      "epoch": 1.11,
      "eval_exact_match": 0.31735447072638817,
      "eval_loss": 1.572016954421997,
      "eval_rouge1": 0.5094747473558878,
      "eval_rouge2": 0.2465356707776194,
      "eval_rougeL": 0.5091592701411148,
      "eval_runtime": 163.415,
      "eval_samples_per_second": 145.911,
      "eval_steps_per_second": 1.524,
      "step": 8000
    },
    {
      "epoch": 1.39,
      "learning_rate": 7.607908416564453e-05,
      "loss": 1.0477,
      "step": 10000
    },
    {
      "epoch": 1.39,
      "eval_exact_match": 0.33387854386847843,
      "eval_loss": 1.5617761611938477,
      "eval_rouge1": 0.5280223151246797,
      "eval_rouge2": 0.2615585801921996,
      "eval_rougeL": 0.5274734242132477,
      "eval_runtime": 165.805,
      "eval_samples_per_second": 143.807,
      "eval_steps_per_second": 1.502,
      "step": 10000
    },
    {
      "epoch": 1.66,
      "learning_rate": 7.023830383739268e-05,
      "loss": 1.0219,
      "step": 12000
    },
    {
      "epoch": 1.66,
      "eval_exact_match": 0.32372924006039255,
      "eval_loss": 1.5944069623947144,
      "eval_rouge1": 0.5133412941637794,
      "eval_rouge2": 0.24304376784560536,
      "eval_rougeL": 0.5128045498112566,
      "eval_runtime": 164.4858,
      "eval_samples_per_second": 144.961,
      "eval_steps_per_second": 1.514,
      "step": 12000
    },
    {
      "epoch": 1.94,
      "learning_rate": 6.440044389930495e-05,
      "loss": 1.0027,
      "step": 14000
    },
    {
      "epoch": 1.94,
      "eval_exact_match": 0.3238550578761953,
      "eval_loss": 1.5750421285629272,
      "eval_rouge1": 0.5206336041126007,
      "eval_rouge2": 0.24470678869584325,
      "eval_rougeL": 0.5202257107678057,
      "eval_runtime": 161.6161,
      "eval_samples_per_second": 147.535,
      "eval_steps_per_second": 1.541,
      "step": 14000
    },
    {
      "epoch": 2.22,
      "learning_rate": 5.856258396121722e-05,
      "loss": 0.9263,
      "step": 16000
    },
    {
      "epoch": 2.22,
      "eval_exact_match": 0.33018788793826537,
      "eval_loss": 1.5776818990707397,
      "eval_rouge1": 0.5179861628783158,
      "eval_rouge2": 0.24451742588852704,
      "eval_rougeL": 0.5176686731279507,
      "eval_runtime": 165.4256,
      "eval_samples_per_second": 144.137,
      "eval_steps_per_second": 1.505,
      "step": 16000
    },
    {
      "epoch": 2.5,
      "learning_rate": 5.272180363296537e-05,
      "loss": 0.9054,
      "step": 18000
    },
    {
      "epoch": 2.5,
      "eval_exact_match": 0.3242325113236034,
      "eval_loss": 1.6233525276184082,
      "eval_rouge1": 0.5204582779286969,
      "eval_rouge2": 0.24576987021627228,
      "eval_rougeL": 0.520011433933161,
      "eval_runtime": 164.3556,
      "eval_samples_per_second": 145.076,
      "eval_steps_per_second": 1.515,
      "step": 18000
    },
    {
      "epoch": 2.77,
      "learning_rate": 4.688102330471351e-05,
      "loss": 0.8921,
      "step": 20000
    },
    {
      "epoch": 2.77,
      "eval_exact_match": 0.3301459486663312,
      "eval_loss": 1.5790328979492188,
      "eval_rouge1": 0.5328535938777187,
      "eval_rouge2": 0.2582260548148201,
      "eval_rougeL": 0.5322687769671152,
      "eval_runtime": 166.1094,
      "eval_samples_per_second": 143.544,
      "eval_steps_per_second": 1.499,
      "step": 20000
    },
    {
      "epoch": 3.05,
      "learning_rate": 4.104316336662578e-05,
      "loss": 0.8781,
      "step": 22000
    },
    {
      "epoch": 3.05,
      "eval_exact_match": 0.3254906894816306,
      "eval_loss": 1.6439645290374756,
      "eval_rouge1": 0.5162815076416999,
      "eval_rouge2": 0.24675202503744387,
      "eval_rougeL": 0.5156010398670283,
      "eval_runtime": 164.6699,
      "eval_samples_per_second": 144.799,
      "eval_steps_per_second": 1.512,
      "step": 22000
    }
  ],
  "max_steps": 36045,
  "num_train_epochs": 5,
  "total_flos": 2.8580534242246656e+17,
  "trial_name": null,
  "trial_params": null
}