fpadovani commited on
Commit
9425b69
·
verified ·
1 Parent(s): 4051e91

Training in progress, step 500, checkpoint

Browse files
checkpoint-500/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:38f39a27b8dbc50e60f39724f6898bd571d4fd003bc1dfcf60d757e83a383382
3
  size 435544704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abcc0350254fa842e08bfb0ef7ef4d28280d8ec058c7b2fcd7212778fb144135
3
  size 435544704
checkpoint-500/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a52a8833776804fd3700ec88e7aa1827363dd16ec68dff93a0d37da99a274362
3
  size 871183627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d8d298c8d3bf9687050539987a10d733c0dda8eea8f4710553c11b647a53b59
3
  size 871183627
checkpoint-500/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd9f06c48fbdc17dd2ff2080be4b0717cdeb36abe5aee5d5bd734fe86ae61311
3
  size 14645
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:353e94aca0f970f319647a076f5784a062702f6e8eec22e07aca243bb1616cc8
3
  size 14645
checkpoint-500/trainer_state.json CHANGED
@@ -1,6 +1,6 @@
1
  {
2
  "best_global_step": 399,
3
- "best_metric": 5.983016014099121,
4
  "best_model_checkpoint": null,
5
  "epoch": 1.2531328320802004,
6
  "eval_steps": 500,
@@ -11,24 +11,24 @@
11
  "log_history": [
12
  {
13
  "epoch": 0.002506265664160401,
14
- "grad_norm": 15.276525497436523,
15
  "learning_rate": 0.0,
16
- "loss": 10.3822,
17
  "step": 1
18
  },
19
  {
20
  "epoch": 1.0,
21
- "grad_norm": 1.2039393186569214,
22
  "learning_rate": 7.960000000000001e-05,
23
- "loss": 6.9837,
24
  "step": 399
25
  },
26
  {
27
  "epoch": 1.0,
28
- "eval_loss": 5.983016014099121,
29
- "eval_runtime": 15.8842,
30
- "eval_samples_per_second": 1611.54,
31
- "eval_steps_per_second": 6.296,
32
  "step": 399
33
  }
34
  ],
 
1
  {
2
  "best_global_step": 399,
3
+ "best_metric": 5.9839253425598145,
4
  "best_model_checkpoint": null,
5
  "epoch": 1.2531328320802004,
6
  "eval_steps": 500,
 
11
  "log_history": [
12
  {
13
  "epoch": 0.002506265664160401,
14
+ "grad_norm": 15.287896156311035,
15
  "learning_rate": 0.0,
16
+ "loss": 10.3873,
17
  "step": 1
18
  },
19
  {
20
  "epoch": 1.0,
21
+ "grad_norm": 1.349755048751831,
22
  "learning_rate": 7.960000000000001e-05,
23
+ "loss": 6.9819,
24
  "step": 399
25
  },
26
  {
27
  "epoch": 1.0,
28
+ "eval_loss": 5.9839253425598145,
29
+ "eval_runtime": 40.2685,
30
+ "eval_samples_per_second": 635.682,
31
+ "eval_steps_per_second": 2.483,
32
  "step": 399
33
  }
34
  ],
checkpoint-500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3d99a586d2a38e89becddbee0adce6692398fb4ff8b6a71d5f8e545b03eeef6
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4d8e95126c79934c43d708d7208a8515199b20fd582881a681e358089ed0c56
3
  size 5905