ccore commited on
Commit
cd4c54b
·
verified ·
1 Parent(s): 863902a

Training in progress, epoch 2, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d349f0b58b03412a4d76688dfda12d87a743414b7487492696f39d7eaeba5c6
3
  size 500979600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7f192f2d55fa4756368292ed33fce824ff85eca57caf3562d98cd73fc7a8cee
3
  size 500979600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b60e7bdba8f1f8bf41e8f0b268a6b237b458c2393a1e6fb9d3874d6e8c4f2084
3
  size 1002078330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0f2660e9ee44744f31ce9d189a6c7fcf6a3af4b38ca63f4f2b343d9bac7010f
3
  size 1002078330
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91c4d4e1a099584438df8e6abdc3506fd74ad79b44065cd75495056a300ae47b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3048c9a83832dc7b124896464922615490e6501c7f82e77ffa4a7fc426c05b2a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2639f3873201909b5b19d566bebe21cf251cebc7007a2f465554f2fe27921d6a
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b28276512ef152b82ddcfa3ee0b09e8e0d74b7c64fb28532e915209b8120e2d6
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.0177865028381348,
3
- "best_model_checkpoint": "./opt_trained/checkpoint-201",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 201,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -15,6 +15,14 @@
15
  "eval_samples_per_second": 37.055,
16
  "eval_steps_per_second": 9.264,
17
  "step": 201
 
 
 
 
 
 
 
 
18
  }
19
  ],
20
  "logging_steps": 500,
@@ -34,7 +42,7 @@
34
  "attributes": {}
35
  }
36
  },
37
- "total_flos": 6766351096320000.0,
38
  "train_batch_size": 16,
39
  "trial_name": null,
40
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.0106526613235474,
3
+ "best_model_checkpoint": "./opt_trained/checkpoint-402",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
+ "global_step": 402,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
15
  "eval_samples_per_second": 37.055,
16
  "eval_steps_per_second": 9.264,
17
  "step": 201
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_loss": 1.0106526613235474,
22
+ "eval_runtime": 77.338,
23
+ "eval_samples_per_second": 36.929,
24
+ "eval_steps_per_second": 9.232,
25
+ "step": 402
26
  }
27
  ],
28
  "logging_steps": 500,
 
42
  "attributes": {}
43
  }
44
  },
45
+ "total_flos": 1.353270219264e+16,
46
  "train_batch_size": 16,
47
  "trial_name": null,
48
  "trial_params": null