rizkyjun commited on
Commit
6fbed9d
1 Parent(s): cd99149

Training in progress, step 600, 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:e9cd3933633a2e6a4b1382d53cafe40193c9907c91875d494970cc229c50ac9b
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf75e9f7d313d527240ac551355e534391d99f81884f733e019c5dcebe82e55b
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80dba94d76f2c0d891c86d552eaa28d21303620b85616f9de25a03095026f583
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d25c396353aecdb4280688541fb3749f41820f123cf2b5100ea7a9d50de74bb1
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:902bb6277fa9332254dbb09d997080ddfd5d2413b689c8efea4dbf0ed8526ba1
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5dd9eab2552fff04796cac197a350c170210977f4c82c1a504ecd3da12163e05
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c1a2ac1c11599601eeac95feb1dbfd49ec5c625e61dcce18b3f094491f9cf2d
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.4726672172546387,
3
- "best_model_checkpoint": "./outputs/checkpoint-500",
4
- "epoch": 0.36429872495446264,
5
  "eval_steps": 100,
6
- "global_step": 500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -77,13 +77,27 @@
77
  "eval_samples_per_second": 25.615,
78
  "eval_steps_per_second": 3.205,
79
  "step": 500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
80
  }
81
  ],
82
  "logging_steps": 100,
83
  "max_steps": 4116,
84
  "num_train_epochs": 3,
85
  "save_steps": 100,
86
- "total_flos": 1.469294009229312e+16,
87
  "trial_name": null,
88
  "trial_params": null
89
  }
 
1
  {
2
+ "best_metric": 2.4451191425323486,
3
+ "best_model_checkpoint": "./outputs/checkpoint-600",
4
+ "epoch": 0.4371584699453552,
5
  "eval_steps": 100,
6
+ "global_step": 600,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
77
  "eval_samples_per_second": 25.615,
78
  "eval_steps_per_second": 3.205,
79
  "step": 500
80
+ },
81
+ {
82
+ "epoch": 0.44,
83
+ "learning_rate": 0.0002,
84
+ "loss": 2.4435,
85
+ "step": 600
86
+ },
87
+ {
88
+ "epoch": 0.44,
89
+ "eval_loss": 2.4451191425323486,
90
+ "eval_runtime": 216.439,
91
+ "eval_samples_per_second": 28.987,
92
+ "eval_steps_per_second": 3.627,
93
+ "step": 600
94
  }
95
  ],
96
  "logging_steps": 100,
97
  "max_steps": 4116,
98
  "num_train_epochs": 3,
99
  "save_steps": 100,
100
+ "total_flos": 1.763801617342464e+16,
101
  "trial_name": null,
102
  "trial_params": null
103
  }