phungkhaccuong commited on
Commit
61d27ce
·
verified ·
1 Parent(s): b539cca

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:a117dc8670f219835aa12683c6db7a4a61641d2be401903b78e664b76981542c
3
  size 94412008
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8392484c956a76a4ef280b378132b225b8bfc3b31cd32760d2ffa8e1aeaa5b7f
3
  size 94412008
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:502f2932b9ffe82636db376bf1abe6fb7f3ad0329f4721deec7bb1fa582e5688
3
  size 48260756
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e373464e9ada85178d6250b59198039c871ffe91668c6ca9f5d1d4ebe8821175
3
  size 48260756
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93ae244803d7ef9abaa10b6cffd0d92c84081c32e8f8a0c736bc8caeb4991343
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1685548eaae179354a1307e0984d0efd590ba815ab3fde8d3709f44ebea4f44a
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": 0.01253616200578592,
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": 7.3319,
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": 1.540514893529088e+16,
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": 0.016072002571520413,
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": 7.3319,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.01285760205721633,
94
+ "grad_norm": 3.29642391204834,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 7.1911,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.01285760205721633,
101
+ "eval_loss": 1.737903118133545,
102
+ "eval_runtime": 146.8799,
103
+ "eval_samples_per_second": 8.919,
104
+ "eval_steps_per_second": 4.459,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.01446480231436837,
109
+ "grad_norm": 2.7461295127868652,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 6.8776,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.016072002571520413,
116
+ "grad_norm": 3.059666156768799,
117
+ "learning_rate": 0.0,
118
+ "loss": 6.687,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.016072002571520413,
123
+ "eval_loss": 1.7350869178771973,
124
+ "eval_runtime": 147.115,
125
+ "eval_samples_per_second": 8.905,
126
+ "eval_steps_per_second": 4.452,
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": 1.947039657099264e+16,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null