Hugging Face's logo

mgh6
/
HTH_prob

TensorBoard
Safetensors
Model card Files
xet
Metrics Community
mgh6 commited on
Commit
8570ba9
·
verified ·
1 Parent(s): 3fc4e90

Training in progress, epoch 3, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +19 -4
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db6bd1201607af974459ccd4065cd330ecc74220d99d6027ee518c958182b92a
3
  size 2610104820
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05ac4f10040e66e431df938b7856d13f664df0b46d6101710def3a334fcb9ba6
3
  size 2610104820
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2f72765dc0f4a81f457004ec2c30aed32c0ee47c8bf90accb3c37cdf1cdade6f
3
  size 5210004271
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75140785cd75a1282efaf5e3f8124ffe807377629f03660cc850719c0ef15a2b
3
  size 5210004271
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ed8d71e0753140beb986a58bf8f7796a167131509a31d6bb830cbf6a6613e20
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d01c0856a6fb316f12ae7b5a00934bd3a02b2c39928e0f3f92795aaa541bbc2
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa16028b3a94e761d69303edbfc8b5005e3b0ea737921fd8bfef31f57a9dd3df
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9885f6cee74ee5ecf8b98902b21218a1e0a6e8b4b6018e56d76ad82d9af7fb58
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.3529444932937622,
3
- "best_model_checkpoint": "mgh6/HTH_prob/checkpoint-732",
4
- "epoch": 2.9960454139558617,
5
  "eval_steps": 500,
6
- "global_step": 732,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,21 @@
52
  "eval_samples_per_second": 32.815,
53
  "eval_steps_per_second": 16.408,
54
  "step": 732
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 500,
 
1
  {
2
+ "best_metric": 1.3419935703277588,
3
+ "best_model_checkpoint": "mgh6/HTH_prob/checkpoint-976",
4
+ "epoch": 3.9960454139558617,
5
  "eval_steps": 500,
6
+ "global_step": 976,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 32.815,
53
  "eval_steps_per_second": 16.408,
54
  "step": 732
55
+ },
56
+ {
57
+ "epoch": 3.9960454139558617,
58
+ "grad_norm": 0.13273808360099792,
59
+ "learning_rate": 0.0009333333333333333,
60
+ "loss": 1.3542,
61
+ "step": 976
62
+ },
63
+ {
64
+ "epoch": 3.9960454139558617,
65
+ "eval_loss": 1.3419935703277588,
66
+ "eval_runtime": 25.2204,
67
+ "eval_samples_per_second": 32.751,
68
+ "eval_steps_per_second": 16.376,
69
+ "step": 976
70
  }
71
  ],
72
  "logging_steps": 500,