flytech commited on
Commit
47cb00d
·
1 Parent(s): 0e4f302

Training in progress, step 400, 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:aae165229259f5e79c8bc41f3b98140cda9d6055f6ac903b0118937af2b0520c
3
  size 14708920
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:08762a2d7c8daeec0abadfd7545ad40d3c12d64ca5d07401b931f06efefa48a8
3
  size 14708920
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f710a2d173e3a3472fd779839476f7feb77d86d64a8210c76dd39f2d95b31200
3
- size 7601797
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4226eb9dcf83705b47b2c90ecea07103f72a0dd704f555bc7b6150a6fa10811c
3
+ size 7601989
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:064538dacf9c9137d32b1d1ee4f73bb878f1d9cc4eb45bca70c01340aa9678db
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a6a40c527d2e02104f50a405546d1fce1f377100d0f95dacedff416f57ba9b3
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f4880f3f40e7ab04d8efce4fc909327351c41d3ccafff780222b4189f527a9a0
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:468a8363eb81d314ece26266458e95441c269841fe873ca22d23f675428e66a4
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.37641154328732745,
5
  "eval_steps": 200,
6
- "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -20,13 +20,26 @@
20
  "eval_samples_per_second": 2.217,
21
  "eval_steps_per_second": 0.278,
22
  "step": 200
 
 
 
 
 
 
 
 
 
 
 
 
 
23
  }
24
  ],
25
  "logging_steps": 200,
26
  "max_steps": 1593,
27
  "num_train_epochs": 3,
28
  "save_steps": 200,
29
- "total_flos": 4.46724161667072e+16,
30
  "trial_name": null,
31
  "trial_params": null
32
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.7528230865746549,
5
  "eval_steps": 200,
6
+ "global_step": 400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
20
  "eval_samples_per_second": 2.217,
21
  "eval_steps_per_second": 0.278,
22
  "step": 200
23
+ },
24
+ {
25
+ "epoch": 0.75,
26
+ "learning_rate": 2e-05,
27
+ "loss": 0.711,
28
+ "step": 400
29
+ },
30
+ {
31
+ "epoch": 0.75,
32
+ "eval_runtime": 1015.2415,
33
+ "eval_samples_per_second": 2.216,
34
+ "eval_steps_per_second": 0.278,
35
+ "step": 400
36
  }
37
  ],
38
  "logging_steps": 200,
39
  "max_steps": 1593,
40
  "num_train_epochs": 3,
41
  "save_steps": 200,
42
+ "total_flos": 8.93448323334144e+16,
43
  "trial_name": null,
44
  "trial_params": null
45
  }