Hugging Face's logo

mgh6
/
TCS_MLM_All

Fill-Mask
Transformers
TensorBoard
Safetensors
esm
Model card Files
xet
Metrics Community
mgh6 commited on
Commit
2ee3dad
·
verified ·
1 Parent(s): 0f6a0a0

Training in progress, step 200, checkpoint

Browse files
Files changed (8) hide show
  1. last-checkpoint/model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state_0.pth +1 -1
  4. last-checkpoint/rng_state_1.pth +1 -1
  5. last-checkpoint/rng_state_2.pth +1 -1
  6. last-checkpoint/rng_state_3.pth +1 -1
  7. last-checkpoint/scheduler.pt +1 -1
  8. last-checkpoint/trainer_state.json +20 -5
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:260f33e18a57d6a52a92153fced5f4433b825cbae7e74e13a6bc31c6c3890bb7
3
  size 136000488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:506f8ace0b66b066b1cb32f1d21957707da08ba16a463c5399f3f40d378da3c3
3
  size 136000488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90a09eabfc08ce01b91af2e622183e0ef79e272762919610e00fff525c6e193b
3
  size 268176506
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0afce708c736beaf7f4f34f21ad39779f9ddd67099a7adf0ab23d01a883538d
3
  size 268176506
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8dcfee971f88c3cda33b81baee0cbbee275ada59edce084b10f143d24d1066de
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d64835eb19f46a9b22f6aa58bb2f3f1dc3002d1bc5be3f3bc276dc53687563b0
3
  size 15024
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cf7fb54143717feb75da48fb46d5104be02f6922f4165bb1f8dc901d2d29dfe4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc3093efecbd6e27a65d810e2de233c67bdd05d5cf4c80744604fe7b0b3a4572
3
  size 15024
last-checkpoint/rng_state_2.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e20d60dc689485036fab9f46d0c8f9988c61adf50aea162ec6b58003dc5f271
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:867fe0ea87c80e44b60860e2807e83aa43f5e41a0cbfbcfc1a71131022813998
3
  size 15024
last-checkpoint/rng_state_3.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9cd11604e085d709114e3ae610473be24a56ca9f858b53106ddf99cb2d836153
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:10ecbe193d41c269d7e2ce8215b2dea9bbdfc768d928e2f8d4cf4684fdf034d2
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:507aa2c5f1b24139884502ecf564787c3e6d78876a1f9bae04804ba26898f238
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f234c0b485586aa78088ec64e6ba5f29d51e09fcb17f9fa5ddd33f7056bf45e0
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.250386118888855,
3
- "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-100",
4
- "epoch": 0.9523809523809523,
5
  "eval_steps": 100,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -22,6 +22,21 @@
22
  "eval_samples_per_second": 87.168,
23
  "eval_steps_per_second": 4.588,
24
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
25
  }
26
  ],
27
  "logging_steps": 100,
@@ -50,7 +65,7 @@
50
  "attributes": {}
51
  }
52
  },
53
- "total_flos": 2931727227944960.0,
54
  "train_batch_size": 64,
55
  "trial_name": null,
56
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.1765815019607544,
3
+ "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-200",
4
+ "epoch": 1.9047619047619047,
5
  "eval_steps": 100,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
22
  "eval_samples_per_second": 87.168,
23
  "eval_steps_per_second": 4.588,
24
  "step": 100
25
+ },
26
+ {
27
+ "epoch": 1.9047619047619047,
28
+ "grad_norm": 0.17264288663864136,
29
+ "learning_rate": 0.0008095238095238096,
30
+ "loss": 1.3281,
31
+ "step": 200
32
+ },
33
+ {
34
+ "epoch": 1.9047619047619047,
35
+ "eval_loss": 1.1765815019607544,
36
+ "eval_runtime": 0.2181,
37
+ "eval_samples_per_second": 87.116,
38
+ "eval_steps_per_second": 4.585,
39
+ "step": 200
40
  }
41
  ],
42
  "logging_steps": 100,
 
65
  "attributes": {}
66
  }
67
  },
68
+ "total_flos": 5863454455889920.0,
69
  "train_batch_size": 64,
70
  "trial_name": null,
71
  "trial_params": null