ccore commited on
Commit
99ce10f
·
verified ·
1 Parent(s): dfc9a55

Training in progress, epoch 4, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7fdf2d59e57fc4e587e94217f6fdb81da01f8c5944a532209e4e1c87a1208fc6
3
  size 1447317080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d88f375c58d8ecf6070a3a48664a302ed8dbf0dad2ffd826a2ad6db509b872e9
3
  size 1447317080
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:068d45c4a9094167ca5b785f421ce65a9eced45e4c8d8be5074eacf100d3ec7b
3
  size 2894813242
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:904aabd09e5ab2d4842541ff4a64ea0652371fcb9abb5ec68b195bb9f350b357
3
  size 2894813242
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c062f7f375beded48b5337f5a3f3a5cb38807fa3e85dbf3e294c0ab6b627bfc2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de3eef1652b01db08dd46ec44854324e826d340084c89d03ced172fee01ac119
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d252aa4fd4abcdd6921ac9bca5da24468d71664fb81e0357f080da3a33cfddad
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.5410714745521545,
3
- "best_model_checkpoint": "./opt_trained2/checkpoint-129",
4
- "epoch": 3.0,
5
  "eval_steps": 500,
6
- "global_step": 129,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -31,6 +31,14 @@
31
  "eval_samples_per_second": 17.74,
32
  "eval_steps_per_second": 4.435,
33
  "step": 129
 
 
 
 
 
 
 
 
34
  }
35
  ],
36
  "logging_steps": 500,
@@ -50,7 +58,7 @@
50
  "attributes": {}
51
  }
52
  },
53
- "total_flos": 5904571275820800.0,
54
  "train_batch_size": 8,
55
  "trial_name": null,
56
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5371374487876892,
3
+ "best_model_checkpoint": "./opt_trained2/checkpoint-172",
4
+ "epoch": 4.0,
5
  "eval_steps": 500,
6
+ "global_step": 172,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
31
  "eval_samples_per_second": 17.74,
32
  "eval_steps_per_second": 4.435,
33
  "step": 129
34
+ },
35
+ {
36
+ "epoch": 4.0,
37
+ "eval_loss": 0.5371374487876892,
38
+ "eval_runtime": 16.8955,
39
+ "eval_samples_per_second": 17.756,
40
+ "eval_steps_per_second": 4.439,
41
+ "step": 172
42
  }
43
  ],
44
  "logging_steps": 500,
 
58
  "attributes": {}
59
  }
60
  },
61
+ "total_flos": 7872761701094400.0,
62
  "train_batch_size": 8,
63
  "trial_name": null,
64
  "trial_params": null