ccore commited on
Commit
5432bb7
·
verified ·
1 Parent(s): aff65fb

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 sha256:1cf838e3ff323c964eb5a4dee4ae78ba71fccae1da29d2c6a9985c8659ec6bb5
3
  size 500979600
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f00e4597998e55cafa408d8a1e4e4ef62df5a18a226afd78d0136a995b0d85bd
3
  size 500979600
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8a4b8a7b84fc6343c6e5b3e1205d99cf1f4d89fc0e154ead6925688e32f06d98
3
  size 1002078330
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2841394e8d6c898bb403b2ac60eae1d7441658b3749425e82e9dde2df020d84
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:bc6e5cd2c091b4585fc31f2d0cbaa4fbd4cf6742985497907ec782666561b99b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e653114ccde232511166099d78954eb3daa5cc0445d848672d8fdac90be7ab2a
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3c58dbbd3cecda8f2dfc7804aaaaf824e11309e3d3a4b7d443e12f4e38a7013f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c0fcbdc65eb352ffe087cab64034c5191a1f92f0e757083498251743820810e
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.8587957620620728,
3
- "best_model_checkpoint": "./opt_trained/checkpoint-22",
4
- "epoch": 1.0,
5
  "eval_steps": 500,
6
- "global_step": 22,
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": 37.212,
16
  "eval_steps_per_second": 9.303,
17
  "step": 22
 
 
 
 
 
 
 
 
18
  }
19
  ],
20
  "logging_steps": 500,
@@ -34,7 +42,7 @@
34
  "attributes": {}
35
  }
36
  },
37
- "total_flos": 709420114944000.0,
38
  "train_batch_size": 16,
39
  "trial_name": null,
40
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.4884560108184814,
3
+ "best_model_checkpoint": "./opt_trained/checkpoint-44",
4
+ "epoch": 2.0,
5
  "eval_steps": 500,
6
+ "global_step": 44,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
15
  "eval_samples_per_second": 37.212,
16
  "eval_steps_per_second": 9.303,
17
  "step": 22
18
+ },
19
+ {
20
+ "epoch": 2.0,
21
+ "eval_loss": 1.4884560108184814,
22
+ "eval_runtime": 8.0476,
23
+ "eval_samples_per_second": 37.278,
24
+ "eval_steps_per_second": 9.32,
25
+ "step": 44
26
  }
27
  ],
28
  "logging_steps": 500,
 
42
  "attributes": {}
43
  }
44
  },
45
+ "total_flos": 1418840229888000.0,
46
  "train_batch_size": 16,
47
  "trial_name": null,
48
  "trial_params": null