mgh6 commited on
Commit
35a5ce6
·
verified ·
1 Parent(s): 5c23609

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d264508ae08e274c28d27a55ec1820872279f6489579c376f16a0dd3f63505c5
3
  size 1442155488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0d5b70e245438e166b96f618cde7523d1a18886aad9728e90c28031a3a77b49
3
  size 1442155488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6cd73ea51c992e4e47713a6dfc35e0d17bca3ad81ef1cd0e9c58a45d7afe0db
3
  size 2884319911
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:582e16a1da51339ba33a94e5700cf386e1f505c219e75be970158702084828ce
3
  size 2884319911
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc057f3c42a7f268a03e1c2cbf4efada08801fa84e6b247630c5d5aebe7a49e0
3
  size 14503
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:076446b2848c20d501548c01c0270f7d595321cf5d08de360d97df6dda4d5978
3
  size 14503
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:673b41d82e959aac00dcaee03910aa1ae8fec244a3f68516132c0a2a2c133a42
3
  size 623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e358772ebc9ad6cfde934716864f9a69585d3a037926074d0d518226baec18ce
3
  size 623
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.4,
5
  "eval_steps": 500,
6
- "global_step": 500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -21,6 +21,20 @@
21
  "eval_samples_per_second": 16.768,
22
  "eval_steps_per_second": 2.096,
23
  "step": 500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
24
  }
25
  ],
26
  "logging_steps": 500,
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.8,
5
  "eval_steps": 500,
6
+ "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
21
  "eval_samples_per_second": 16.768,
22
  "eval_steps_per_second": 2.096,
23
  "step": 500
24
+ },
25
+ {
26
+ "epoch": 0.8,
27
+ "learning_rate": 0.0009733333333333334,
28
+ "loss": 130631.296,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 0.8,
33
+ "eval_loss": 129769.484375,
34
+ "eval_runtime": 1199.9356,
35
+ "eval_samples_per_second": 16.667,
36
+ "eval_steps_per_second": 2.083,
37
+ "step": 1000
38
  }
39
  ],
40
  "logging_steps": 500,