CodeIsAbstract commited on
Commit
b7edadc
·
verified ·
1 Parent(s): 2c3de3c

Training in progress, step 30, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3eff71d9a518a41bfb28e73ae1dd6b312a9a8275111eb44f36a482de0c686fd3
3
  size 847599616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d96abf3f9691ac86ab25ff7137421e2a8b4083fe7ee1e534a607630e38da1a70
3
  size 847599616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:451a047c67adb552f69b1ee57d6ccfbd975f28d2db27303ea08b3bb99222f1ce
3
  size 1386414411
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0372906270350ea47d01c303401ff6944e65d7ca84169d0592a2e54e5dadce5
3
  size 1386414411
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffc94345284c067e63bc8b19cb79da3fce02d7f1d4fcfbf72afb2b30059f4b97
3
  size 14917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89cae3402b04c3b79e7827436454a3dc353c4d61ad250ac2370aaebbfabcea52
3
  size 14917
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:839bc332ed8a70d9ae7184583e63a4e9d83f0da96047149a53985c0c878892fc
3
  size 14917
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:903e602536db1a59b502d2179fad5c5483fbaf99bfa18a5697f07904de3a0519
3
  size 14917
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb4b8e87ee0160fc90bd1f1a2198d12f8bd9bc37df783ac81324bc967f9edc62
3
  size 1465
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b612f6e342d453521aa7dbb39c4dc0d4b0cdc9dbd54ab1a4de2cc98d0edc330
3
  size 1465
last-checkpoint/trainer_state.json CHANGED
@@ -2,9 +2,9 @@
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
- "epoch": 0.02,
6
  "eval_steps": 5,
7
- "global_step": 20,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
@@ -44,6 +44,24 @@
44
  "eval_samples_per_second": 13.881,
45
  "eval_steps_per_second": 6.94,
46
  "step": 20
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
47
  }
48
  ],
49
  "logging_steps": 100,
 
2
  "best_global_step": null,
3
  "best_metric": null,
4
  "best_model_checkpoint": null,
5
+ "epoch": 0.03,
6
  "eval_steps": 5,
7
+ "global_step": 30,
8
  "is_hyper_param_search": false,
9
  "is_local_process_zero": true,
10
  "is_world_process_zero": true,
 
44
  "eval_samples_per_second": 13.881,
45
  "eval_steps_per_second": 6.94,
46
  "step": 20
47
+ },
48
+ {
49
+ "epoch": 0.025,
50
+ "eval_accuracy": 0.08153333333333333,
51
+ "eval_loss": 18.101879119873047,
52
+ "eval_runtime": 41.6916,
53
+ "eval_samples_per_second": 11.993,
54
+ "eval_steps_per_second": 5.996,
55
+ "step": 25
56
+ },
57
+ {
58
+ "epoch": 0.03,
59
+ "eval_accuracy": 0.07606666666666667,
60
+ "eval_loss": 17.941076278686523,
61
+ "eval_runtime": 36.7785,
62
+ "eval_samples_per_second": 13.595,
63
+ "eval_steps_per_second": 6.797,
64
+ "step": 30
65
  }
66
  ],
67
  "logging_steps": 100,