polejowska commited on
Commit
daf1d92
1 Parent(s): ee7d49b

End of training

Browse files
runs/Feb26_20-37-41_b0051077c075/events.out.tfevents.1677443867.b0051077c075.1132.6 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:653ec58812d01357f0bef34a643c676f75245050fc0eddcfd9c24b4740aea982
3
- size 6237
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11757cbf9ba59602aa24e51edeb00edacc835d725b37b4fb667ca0ed9cd569b5
3
+ size 6591
trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 5.0,
5
- "global_step": 470,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -78,18 +78,88 @@
78
  "step": 470
79
  },
80
  {
81
- "epoch": 5.0,
82
- "step": 470,
83
- "total_flos": 1.1450900938752e+17,
84
- "train_loss": 3.3688572660405587,
85
- "train_runtime": 692.9876,
86
- "train_samples_per_second": 5.411,
87
- "train_steps_per_second": 0.678
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
88
  }
89
  ],
90
- "max_steps": 470,
91
- "num_train_epochs": 5,
92
- "total_flos": 1.1450900938752e+17,
93
  "trial_name": null,
94
  "trial_params": null
95
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "global_step": 940,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
78
  "step": 470
79
  },
80
  {
81
+ "epoch": 6.0,
82
+ "learning_rate": 4e-05,
83
+ "loss": 3.2701,
84
+ "step": 564
85
+ },
86
+ {
87
+ "epoch": 6.0,
88
+ "eval_loss": 2.648871421813965,
89
+ "eval_runtime": 23.3072,
90
+ "eval_samples_per_second": 8.581,
91
+ "eval_steps_per_second": 1.073,
92
+ "step": 564
93
+ },
94
+ {
95
+ "epoch": 7.0,
96
+ "learning_rate": 3e-05,
97
+ "loss": 3.1847,
98
+ "step": 658
99
+ },
100
+ {
101
+ "epoch": 7.0,
102
+ "eval_loss": 2.699300765991211,
103
+ "eval_runtime": 22.1301,
104
+ "eval_samples_per_second": 9.037,
105
+ "eval_steps_per_second": 1.13,
106
+ "step": 658
107
+ },
108
+ {
109
+ "epoch": 8.0,
110
+ "learning_rate": 2e-05,
111
+ "loss": 3.0959,
112
+ "step": 752
113
+ },
114
+ {
115
+ "epoch": 8.0,
116
+ "eval_loss": 2.636422634124756,
117
+ "eval_runtime": 21.8919,
118
+ "eval_samples_per_second": 9.136,
119
+ "eval_steps_per_second": 1.142,
120
+ "step": 752
121
+ },
122
+ {
123
+ "epoch": 9.0,
124
+ "learning_rate": 1e-05,
125
+ "loss": 3.0506,
126
+ "step": 846
127
+ },
128
+ {
129
+ "epoch": 9.0,
130
+ "eval_loss": 2.6463677883148193,
131
+ "eval_runtime": 22.9819,
132
+ "eval_samples_per_second": 8.702,
133
+ "eval_steps_per_second": 1.088,
134
+ "step": 846
135
+ },
136
+ {
137
+ "epoch": 10.0,
138
+ "learning_rate": 0.0,
139
+ "loss": 3.0497,
140
+ "step": 940
141
+ },
142
+ {
143
+ "epoch": 10.0,
144
+ "eval_loss": 2.63041615486145,
145
+ "eval_runtime": 23.2242,
146
+ "eval_samples_per_second": 8.612,
147
+ "eval_steps_per_second": 1.076,
148
+ "step": 940
149
+ },
150
+ {
151
+ "epoch": 10.0,
152
+ "step": 940,
153
+ "total_flos": 2.2901801877504e+17,
154
+ "train_loss": 1.5650983120532747,
155
+ "train_runtime": 702.8978,
156
+ "train_samples_per_second": 10.67,
157
+ "train_steps_per_second": 1.337
158
  }
159
  ],
160
+ "max_steps": 940,
161
+ "num_train_epochs": 10,
162
+ "total_flos": 2.2901801877504e+17,
163
  "trial_name": null,
164
  "trial_params": null
165
  }