ccore commited on
Commit
e971c28
·
verified ·
1 Parent(s): 2c599db

Training in progress, epoch 3, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11cba36f33d6ea1686e5921b9e8226d79e2149dc7aa27d964c02332e9d64e4bf
3
  size 500979600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e09b2888c55226003d1777f8e74624ba24b23e653122bda72249d07cea5cc534
3
  size 500979600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3e9d81b84f8749c6e3ee76416818a9b83899ee97fabd0627c0f592cf88bf379
3
  size 1002078330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7b43b9be14768ed562cc56fbceb4e4c212eff27a8bced56a087b2aaf2fed8a7
3
  size 1002078330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b485a847440f127ecf9cb2f6df76817ef2f8c330051dbb916825bec059e34b44
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:376d7899996a3d8015fb5b3439bc1391f1ffa20289c9f6ee4d9dd26e8beaf425
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3a4377bc7de4eb855c30d3cab6f59db045275bc94d864baaa5b4002704f4cdff
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e0d537959189cef256eb23e89b5091772521a8ab26abc843e67a86264df692a
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.5414664149284363,
3
- "best_model_checkpoint": "./opt_trained3/checkpoint-30",
4
- "epoch": 2.0,
5
  "eval_steps": 500,
6
- "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -23,6 +23,14 @@
23
  "eval_samples_per_second": 50.162,
24
  "eval_steps_per_second": 12.541,
25
  "step": 30
 
 
 
 
 
 
 
 
26
  }
27
  ],
28
  "logging_steps": 500,
@@ -42,7 +50,7 @@
42
  "attributes": {}
43
  }
44
  },
45
- "total_flos": 1113211226880000.0,
46
  "train_batch_size": 24,
47
  "trial_name": null,
48
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5381864309310913,
3
+ "best_model_checkpoint": "./opt_trained3/checkpoint-45",
4
+ "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 45,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
23
  "eval_samples_per_second": 50.162,
24
  "eval_steps_per_second": 12.541,
25
  "step": 30
26
+ },
27
+ {
28
+ "epoch": 3.0,
29
+ "eval_loss": 0.5381864309310913,
30
+ "eval_runtime": 5.9811,
31
+ "eval_samples_per_second": 50.158,
32
+ "eval_steps_per_second": 12.539,
33
+ "step": 45
34
  }
35
  ],
36
  "logging_steps": 500,
 
50
  "attributes": {}
51
  }
52
  },
53
+ "total_flos": 1669816840320000.0,
54
  "train_batch_size": 24,
55
  "trial_name": null,
56
  "trial_params": null