mgh6 commited on
Commit
5706ca4
·
verified ·
1 Parent(s): ace73a6

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:f63b7401d6f1f053dafd113e09af67725b58a90ee651f882b7b24a7ae624677f
3
  size 1442155488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04d0e771323dd251c9c4b854f1c2a314eb54e97b5c672c344934e40a31ba06f4
3
  size 1442155488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99bb53e19ef6ae8d533c317034f43a15e1a71989d60a33361f86e0b67a99dedc
3
  size 2884319911
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad2796589724711b75582a78e1a2f8a10e3538709b6c9dd8f8744a6488eab50c
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": 17.238,
22
  "eval_steps_per_second": 2.155,
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": 17.238,
22
  "eval_steps_per_second": 2.155,
23
  "step": 500
24
+ },
25
+ {
26
+ "epoch": 0.8,
27
+ "learning_rate": 0.0009733333333333334,
28
+ "loss": 130852.424,
29
+ "step": 1000
30
+ },
31
+ {
32
+ "epoch": 0.8,
33
+ "eval_loss": 129977.7265625,
34
+ "eval_runtime": 1174.3321,
35
+ "eval_samples_per_second": 17.03,
36
+ "eval_steps_per_second": 2.129,
37
+ "step": 1000
38
  }
39
  ],
40
  "logging_steps": 500,