mgh6 commited on
Commit
5f3aa5b
·
verified ·
1 Parent(s): 2fd15f0

Training in progress, epoch 47, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca80642c9b2eb0edea041d866449264a60143f830a52f1a807e1f910cc27ceb4
3
  size 2708740080
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfbeace76bad79f7c6628c637abd93ce504f5aa470c4294135b43b936bab9bb8
3
  size 2708740080
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d136068ff1f1178ed92e32909ce280b71644c1ff075577f7ce0d278645777b64
3
  size 52521338
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf3f558301428efd2533a61f4699af079fa3376059a2832afa8a4e46d835ee3b
3
  size 52521338
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34bc161e39a2d74e8b0b7477459eaeb0bd1bb49033b696f2a20d5a3942823532
3
  size 15006
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:349bb12aecda94ec39ff59ee155699b6cd6a64740f8fa5d85f9af0db679bb61c
3
  size 15006
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:45475fc26009bc2c2f17e0c9c92374736897394ffa72187217e90aeaa39097ce
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e0a51561ac1af8ca6aad98879fe42f05bcb76d5fed68b29166c9165ce2ed6da
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.6738462448120117,
3
- "best_model_checkpoint": "mgh6/HTH_biCLIP_mean/checkpoint-5934",
4
- "epoch": 46.0,
5
  "eval_steps": 500,
6
- "global_step": 5934,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -743,6 +743,22 @@
743
  "eval_samples_per_second": 22.927,
744
  "eval_steps_per_second": 1.433,
745
  "step": 5934
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
746
  }
747
  ],
748
  "logging_steps": 500,
 
1
  {
2
+ "best_metric": 2.673060894012451,
3
+ "best_model_checkpoint": "mgh6/HTH_biCLIP_mean/checkpoint-6063",
4
+ "epoch": 47.0,
5
  "eval_steps": 500,
6
+ "global_step": 6063,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
743
  "eval_samples_per_second": 22.927,
744
  "eval_steps_per_second": 1.433,
745
  "step": 5934
746
+ },
747
+ {
748
+ "epoch": 47.0,
749
+ "grad_norm": 0.3535211384296417,
750
+ "learning_rate": 2.10546875e-05,
751
+ "loss": 2.6388,
752
+ "step": 6063
753
+ },
754
+ {
755
+ "epoch": 47.0,
756
+ "eval_cosine_similarity": 0.7922196984291077,
757
+ "eval_loss": 2.673060894012451,
758
+ "eval_runtime": 18.8542,
759
+ "eval_samples_per_second": 22.913,
760
+ "eval_steps_per_second": 1.432,
761
+ "step": 6063
762
  }
763
  ],
764
  "logging_steps": 500,