Femboyuwu2000 commited on
Commit
6a16135
·
verified ·
1 Parent(s): 9c5caba

Training in progress, step 3780, 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:d2eb339fca1743ce5981d75d94271aea8c49805aa8787cc062a2e480f02e91a8
3
  size 13982248
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4223f69fa5c4d343cdb0daf20def262d26468340b68b3012ba5b5bf860add746
3
  size 13982248
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:819c50564431ec790e5c787d93b2db9cabbb70df63553d50a801172070601bd3
3
  size 7062522
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07336ce007d26d9a03fa7d6fb0fb6a9b44ea05300d930f065fe4546aa4d1e107
3
  size 7062522
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e850e7ecc226d31ccfa0012c8cc354a952ec0a60022ef713d966322a18df683d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b38fda0416b95acf561519c239d9553c03304b18c4ad47455ccbf998847d400
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c260417484aa6b4e9e662c09fdefa26287d404d4aaa654726d7eb8d7f1d0b789
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eab6ea1f9b7df74951725865c85704c6f9d44947e8a6d8f259ab0d7413d273be
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": 0.3008,
5
  "eval_steps": 500,
6
- "global_step": 3760,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1323,6 +1323,13 @@
1323
  "learning_rate": 2.8078528754588207e-05,
1324
  "loss": 3.5173,
1325
  "step": 3760
 
 
 
 
 
 
 
1326
  }
1327
  ],
1328
  "logging_steps": 20,
@@ -1330,7 +1337,7 @@
1330
  "num_input_tokens_seen": 0,
1331
  "num_train_epochs": 2,
1332
  "save_steps": 20,
1333
- "total_flos": 8883020977766400.0,
1334
  "train_batch_size": 8,
1335
  "trial_name": null,
1336
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3024,
5
  "eval_steps": 500,
6
+ "global_step": 3780,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1323
  "learning_rate": 2.8078528754588207e-05,
1324
  "loss": 3.5173,
1325
  "step": 3760
1326
+ },
1327
+ {
1328
+ "epoch": 0.3,
1329
+ "grad_norm": 28.02115821838379,
1330
+ "learning_rate": 2.805467086984027e-05,
1331
+ "loss": 3.4905,
1332
+ "step": 3780
1333
  }
1334
  ],
1335
  "logging_steps": 20,
 
1337
  "num_input_tokens_seen": 0,
1338
  "num_train_epochs": 2,
1339
  "save_steps": 20,
1340
+ "total_flos": 8928030689820672.0,
1341
  "train_batch_size": 8,
1342
  "trial_name": null,
1343
  "trial_params": null