ramdhanfirdaus commited on
Commit
40a0e78
1 Parent(s): 98db35a

Training in progress, step 900, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:237bed6661e8466d663836b3e20bd89e5dd493304384e6fd2b772d2ef7009f2f
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c327d5945c4e02ff4f63b8a838cd1edeb8bc5e0971709c80713280abee3b525
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06af277f1880fb680744922e2990da90606a14c16d42c1318307e982f843718d
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:65aafa816b059c56057e4355527c1b409efb463fde0809c9b38b4dd74529bed3
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abaef124d8e265d68d5751114b7c7b99ba0eb280d27af45a9884fb7e66277ae9
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99f1c1111b8d1f0cb2cc4b559a49a0a42b0bb5df350eda9361510f1ff2ab08e2
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.6834267377853394,
3
- "best_model_checkpoint": "./outputs/checkpoint-800",
4
- "epoch": 0.5828779599271403,
5
  "eval_steps": 100,
6
- "global_step": 800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -119,13 +119,27 @@
119
  "eval_samples_per_second": 43.662,
120
  "eval_steps_per_second": 5.463,
121
  "step": 800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
122
  }
123
  ],
124
  "logging_steps": 100,
125
  "max_steps": 4116,
126
  "num_train_epochs": 3,
127
  "save_steps": 100,
128
- "total_flos": 4.770964776085094e+16,
129
  "trial_name": null,
130
  "trial_params": null
131
  }
 
1
  {
2
+ "best_metric": 1.6576156616210938,
3
+ "best_model_checkpoint": "./outputs/checkpoint-900",
4
+ "epoch": 0.6557377049180327,
5
  "eval_steps": 100,
6
+ "global_step": 900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
119
  "eval_samples_per_second": 43.662,
120
  "eval_steps_per_second": 5.463,
121
  "step": 800
122
+ },
123
+ {
124
+ "epoch": 0.66,
125
+ "learning_rate": 0.0002,
126
+ "loss": 1.6624,
127
+ "step": 900
128
+ },
129
+ {
130
+ "epoch": 0.66,
131
+ "eval_loss": 1.6576156616210938,
132
+ "eval_runtime": 143.6985,
133
+ "eval_samples_per_second": 43.661,
134
+ "eval_steps_per_second": 5.463,
135
+ "step": 900
136
  }
137
  ],
138
  "logging_steps": 100,
139
  "max_steps": 4116,
140
  "num_train_epochs": 3,
141
  "save_steps": 100,
142
+ "total_flos": 5.365902922462003e+16,
143
  "trial_name": null,
144
  "trial_params": null
145
  }