ramdhanfirdaus commited on
Commit
e4cee8f
1 Parent(s): 9556c46

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:448396aae2c09f4fd0b7678d957f7a092971c758d28fe4f81f437ae0c1e2f22c
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b9358e8f61ff32be0f1a8e2b6320ba18620c6a643cdaa27e17f918b4d0b2a0f
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:25926aa470808bec0d8847649d220f3e5ebc260c8c25a23ceb787541c851f2e6
3
  size 151034501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73cc838b4de838a2a68358156162015cd6e5c6850454b9cd688901ac3ed2eb2b
3
  size 151034501
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b6dc081960b6e1c8f4843c703818680fc59b25fd62613d0ff6e6883368f5fd6b
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:973a043ee80396c3f986716db6c1e3d60244b3dc4a66dc2d497c8b441255aa1b
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.432775616645813,
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,
@@ -133,13 +133,27 @@
133
  "eval_samples_per_second": 14.977,
134
  "eval_steps_per_second": 1.874,
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": 2.918207621536481e+17,
143
  "trial_name": null,
144
  "trial_params": null
145
  }
 
1
  {
2
+ "best_metric": 1.4167886972427368,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1000",
4
+ "epoch": 0.7285974499089253,
5
  "eval_steps": 100,
6
+ "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
133
  "eval_samples_per_second": 14.977,
134
  "eval_steps_per_second": 1.874,
135
  "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.73,
139
+ "learning_rate": 0.0002,
140
+ "loss": 1.4271,
141
+ "step": 1000
142
+ },
143
+ {
144
+ "epoch": 0.73,
145
+ "eval_loss": 1.4167886972427368,
146
+ "eval_runtime": 418.6904,
147
+ "eval_samples_per_second": 14.985,
148
+ "eval_steps_per_second": 1.875,
149
+ "step": 1000
150
  }
151
  ],
152
  "logging_steps": 100,
153
  "max_steps": 4116,
154
  "num_train_epochs": 3,
155
  "save_steps": 100,
156
+ "total_flos": 3.2426327742291456e+17,
157
  "trial_name": null,
158
  "trial_params": null
159
  }