chauhoang commited on
Commit
ab1a92e
·
verified ·
1 Parent(s): 948a159

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 sha256:9e7e240056d70a44ab0b411455b91006036ba0957fd5ec5b1009a9e96e23339d
3
  size 608249904
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e23f93cdd93b2b623fdde3edd074fcb6416c691974a549d692267f0b9b98f288
3
  size 608249904
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:651d1a2c31d6ba3b267a51e9ef45544c2f523f3e03bd17081b349db2d4d4634a
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d18a30e5411a1b35544f310cdfb36a6ad42ca657c5ff811640c25be8eef2803
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a5f891767aaacfb795fc4c851c74f7dcf55cd20474ec59a43d271975d0645cf
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d36cf02c5c091e1cf6b7a556033f9afe92924f5c6d18c68aeec7f759f6f16a6c
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": 0.000637603917176886,
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": 0.2852,
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": 6835416091066368.0,
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": 0.0008174409194575462,
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": 0.2852,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.000653952735566037,
94
+ "grad_norm": 5.884018898010254,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 0.2247,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.000653952735566037,
101
+ "eval_loss": 0.3139568865299225,
102
+ "eval_runtime": 1631.947,
103
+ "eval_samples_per_second": 15.782,
104
+ "eval_steps_per_second": 7.891,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.0007356968275117916,
109
+ "grad_norm": 13.396302223205566,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 0.3011,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.0008174409194575462,
116
+ "grad_norm": 3.231811761856079,
117
+ "learning_rate": 0.0,
118
+ "loss": 0.1717,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.0008174409194575462,
123
+ "eval_loss": 0.27322423458099365,
124
+ "eval_runtime": 1630.2265,
125
+ "eval_samples_per_second": 15.798,
126
+ "eval_steps_per_second": 7.9,
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": 8763353962905600.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null