tuanna08go commited on
Commit
539c938
·
verified ·
1 Parent(s): bf0ed8c

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:b731c15778727381cc2e7d5933fad8b42e9331217d02c203e30d7aa14fcb088c
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:983a691c73595650a9762431fedb0b16d078668eac8a40f5a9bc57c17789bb48
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:da374e66568fa19ab6e02a93c5cb75a239086dbf72603e4142fc99d625cec491
3
  size 13685516
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:931bfb8d38517b248f30dfa43cbef78cf009a6d39cae06af020504c87172318a
3
  size 13685516
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:125724582db1a62dac8cbcb3104285de08f049398c980919acba95a3edd476e7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f5fc987139c560c75276a19ed6d0196d3123190b163d3f7d42aa9b9f6490c873
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": 0.01244614648157013,
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": 0.5216,
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": 1975993031983104.0,
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": 0.015956598053295037,
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": 0.5216,
90
  "step": 35
91
+ },
92
+ {
93
+ "epoch": 0.01276527844263603,
94
+ "grad_norm": 0.1474408060312271,
95
+ "learning_rate": 1.4644660940672627e-05,
96
+ "loss": 0.558,
97
+ "step": 40
98
+ },
99
+ {
100
+ "epoch": 0.01276527844263603,
101
+ "eval_loss": 0.5630071759223938,
102
+ "eval_runtime": 44.2419,
103
+ "eval_samples_per_second": 29.836,
104
+ "eval_steps_per_second": 14.918,
105
+ "step": 40
106
+ },
107
+ {
108
+ "epoch": 0.014360938247965534,
109
+ "grad_norm": 0.1654672771692276,
110
+ "learning_rate": 3.8060233744356633e-06,
111
+ "loss": 0.5653,
112
+ "step": 45
113
+ },
114
+ {
115
+ "epoch": 0.015956598053295037,
116
+ "grad_norm": 0.1382376104593277,
117
+ "learning_rate": 0.0,
118
+ "loss": 0.5764,
119
+ "step": 50
120
+ },
121
+ {
122
+ "epoch": 0.015956598053295037,
123
+ "eval_loss": 0.5614041686058044,
124
+ "eval_runtime": 43.6709,
125
+ "eval_samples_per_second": 30.226,
126
+ "eval_steps_per_second": 15.113,
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": 2538735384133632.0,
148
  "train_batch_size": 2,
149
  "trial_name": null,
150
  "trial_params": null