bhuvanmdev commited on
Commit
99aa8a0
·
verified ·
1 Parent(s): 01e6d47

Training in progress, step 1430, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6808dd327f6b3084d418d704b1410ab5b4920ece09285db52a32aa7605a852aa
3
  size 1316913776
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:863d16d7c48261195a7a0f3d5791f538faa011b7c047ff2885d3cadba3d91bbd
3
  size 1316913776
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72c67711d65987cd86d63dd8b7abad826d13d8fd78a67946d2b4d7ddf43251fd
3
  size 8908124
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ab40046a9af210a467776da8fb44c42a66a3335a8d2d14289aa87d40bed8ad3
3
  size 8908124
last-checkpoint/rng_state.pth CHANGED
Binary files a/last-checkpoint/rng_state.pth and b/last-checkpoint/rng_state.pth differ
 
last-checkpoint/scheduler.pt CHANGED
Binary files a/last-checkpoint/scheduler.pt and b/last-checkpoint/scheduler.pt differ
 
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.30485186775440104,
5
  "eval_steps": 500,
6
- "global_step": 1420,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -1001,6 +1001,13 @@
1001
  "learning_rate": 0.0003475740661227995,
1002
  "loss": 0.7792,
1003
  "step": 1420
 
 
 
 
 
 
 
1004
  }
1005
  ],
1006
  "logging_steps": 10,
@@ -1008,7 +1015,7 @@
1008
  "num_input_tokens_seen": 0,
1009
  "num_train_epochs": 1,
1010
  "save_steps": 10,
1011
- "total_flos": 1.0767132782165837e+17,
1012
  "train_batch_size": 3,
1013
  "trial_name": null,
1014
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.3069987118935165,
5
  "eval_steps": 500,
6
+ "global_step": 1430,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
1001
  "learning_rate": 0.0003475740661227995,
1002
  "loss": 0.7792,
1003
  "step": 1420
1004
+ },
1005
+ {
1006
+ "epoch": 0.3069987118935165,
1007
+ "grad_norm": 1.0442615747451782,
1008
+ "learning_rate": 0.0003465006440532417,
1009
+ "loss": 0.7734,
1010
+ "step": 1430
1011
  }
1012
  ],
1013
  "logging_steps": 10,
 
1015
  "num_input_tokens_seen": 0,
1016
  "num_train_epochs": 1,
1017
  "save_steps": 10,
1018
+ "total_flos": 1.0829674193791795e+17,
1019
  "train_batch_size": 3,
1020
  "trial_name": null,
1021
  "trial_params": null