phungkhaccuong commited on
Commit
9cb60d7
·
verified ·
1 Parent(s): 24da00a

Training in progress, step 50, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e8f8ce199b6cd7f2a90cebfc1bc4d7d13b3533d231201a7ba670ee99d6574223
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7780ad08a3693d215df134a43f16bd6bb1fdba55043f4ca34696504a637b4449
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a3f9b8a9607a5e94e2d321e2de3a6ff0f73a34145cdca58271f7793f1629d0c
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fb7ad493c46c3a798fa92ddc4dec1828852acbab1fbd440ffd0a6ad5892e2ad
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cacaf8ca7dccda8c7558dd4f048e47ecbfd6553f222b04583f4b378449c85d41
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6eacdb173cbd67a85646be76568e2309906bff3c93348530b9a1ac8d07a898ab
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.05418548106981591,
5
  "eval_steps": 10,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -88,6 +88,43 @@
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 1.0,
90
  "step": 35
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
91
  }
92
  ],
93
  "logging_steps": 5,
@@ -102,12 +139,12 @@
102
  "should_evaluate": false,
103
  "should_log": false,
104
  "should_save": true,
105
- "should_training_stop": false
106
  },
107
  "attributes": {}
108
  }
109
  },
110
- "total_flos": 6796280579751936.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.06946856547412296,
5
  "eval_steps": 10,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
88
  "learning_rate": 3.086582838174551e-05,
89
  "loss": 1.0,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.055574852379298365,
94
+ "grad_norm": 1.9555302858352661,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 0.9449,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.055574852379298365,
101
+ "eval_loss": 0.8849262595176697,
102
+ "eval_runtime": 34.1213,
103
+ "eval_samples_per_second": 8.88,
104
+ "eval_steps_per_second": 4.455,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.06252170892671066,
109
+ "grad_norm": 1.7785624265670776,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 0.7927,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.06946856547412296,
116
+ "grad_norm": 1.3851503133773804,
117
+ "learning_rate": 0.0,
118
+ "loss": 0.8639,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.06946856547412296,
123
+ "eval_loss": 0.8625767230987549,
124
+ "eval_runtime": 34.1038,
125
+ "eval_samples_per_second": 8.885,
126
+ "eval_steps_per_second": 4.457,
127
+ "step": 50
128
  }
129
  ],
130
  "logging_steps": 5,
 
139
  "should_evaluate": false,
140
  "should_log": false,
141
  "should_save": true,
142
+ "should_training_stop": true
143
  },
144
  "attributes": {}
145
  }
146
  },
147
+ "total_flos": 8713180230451200.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null