tuanna08go commited on
Commit
9979d30
·
verified ·
1 Parent(s): 040300d

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:e93e8e8fed04acec8aea6128b20fdcecf2dd087169d5b203efa73943eb40ed28
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ab71bef9326aa3bd8b8c2be41e038db17306b91003d5db201ca8ab062996ccd4
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fcdc3efe1fe08b13f79c5239b1968327c723fea84609e0c137f4d22783937726
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e0f9d6c8d0332ca25c06e311e048fefe28d2890dead6a931c51ba705a49edc0
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21355fb2906cf74fd6ba95539ab93100f87dc71321132f9f2b93def20296bd54
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3b6915890ecd305de352352de95cac060a691fcf98b13a8c69760b2ad8c78fc
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": 0.004155346012466038,
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": 1.9431,
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": 1074326308651008.0,
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": 0.0053273666826487666,
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": 1.9431,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.004261893346119014,
94
+ "grad_norm": 1.080267071723938,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 1.8965,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.004261893346119014,
101
+ "eval_loss": 1.917460560798645,
102
+ "eval_runtime": 110.5959,
103
+ "eval_samples_per_second": 35.734,
104
+ "eval_steps_per_second": 17.867,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.00479463001438389,
109
+ "grad_norm": 0.974481463432312,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 1.9192,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.0053273666826487666,
116
+ "grad_norm": 1.0862126350402832,
117
+ "learning_rate": 0.0,
118
+ "loss": 1.8109,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.0053273666826487666,
123
+ "eval_loss": 1.9136332273483276,
124
+ "eval_runtime": 110.8246,
125
+ "eval_samples_per_second": 35.66,
126
+ "eval_steps_per_second": 17.83,
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": 1381276682551296.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null