Hugging Face's logo

mgh6
/
HTH

TensorBoard
Safetensors
esm
Model card Files
xet
Metrics Community
mgh6 commited on
Commit
ecc1b50
·
verified ·
1 Parent(s): da44106

Training in progress, step 2100, 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 +17 -3
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:caf96f2d62cddc6fc7aef86afed7385860dc88331433a83ae6b7e9403b958447
3
  size 2682482800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a785245b9db918f8075f864bb71b2ef94bdafb7e3dfb6d5b8ae27897b53e5856
3
  size 2682482800
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7918ffccb124a064f589acf5d911356d6c8d6e0a5a05a633194d0317ff5b135
3
  size 5365108834
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f18aa6e97bfed0261afda1f92b597f5249cac28141302e759a490137ffb174ed
3
  size 5365108834
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f6e41fc7393e4681202895f12ea2bdd6fcdbe52f58f01d5a51f67dfdd0eb7cf4
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b73bcda2af2a8653a39b5acd3cf8db4779d11cc560ce05a1ed022d03a6467c6
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 sha256:47970a80ccd55cd9b1e285608a69c5a852edb532757a89198968e982fdaea9d0
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7669ee2b753b4a1b38f068a799eadb312c8a89e69d877b91860a8c132c26bd0d
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 sha256:72985cd90a25d0c462ffc57bcd399b30b144c7fb5a1dd290d1cafafcbd2772ae
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5fc7daea5a1677f0ca4be841f484245a233687c2c91d61d675ad21da37b200
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:b232b8c73f42212c2ad02445b917ce897a3fa48fa4fb0b636a2fec7bc9464b23
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bd36615d87deabb9ffc7df98612a630cff63482f076572324115b3e7de11263
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79835d376c5ef7814504b05c236a39cb31e7978e87454f4c1983636759268bec
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:891dcd976a2cfcf266a598c09521a8a1af39423c8f98b39c83ad1e33e92dfeb2
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.1535046429158207,
5
  "eval_steps": 100,
6
- "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -287,6 +287,20 @@
287
  "learning_rate": 0.0008464844949339884,
288
  "loss": 1.7085,
289
  "step": 2000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
290
  }
291
  ],
292
  "logging_steps": 50,
@@ -306,7 +320,7 @@
306
  "attributes": {}
307
  }
308
  },
309
- "total_flos": 3.4283095449696993e+18,
310
  "train_batch_size": 2,
311
  "trial_name": null,
312
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.16117987506161172,
5
  "eval_steps": 100,
6
+ "global_step": 2100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
287
  "learning_rate": 0.0008464844949339884,
288
  "loss": 1.7085,
289
  "step": 2000
290
+ },
291
+ {
292
+ "epoch": 0.1573422589887162,
293
+ "grad_norm": 0.6814237833023071,
294
+ "learning_rate": 0.0008426466073073382,
295
+ "loss": 1.7057,
296
+ "step": 2050
297
+ },
298
+ {
299
+ "epoch": 0.16117987506161172,
300
+ "grad_norm": 0.453630268573761,
301
+ "learning_rate": 0.0008388087196806877,
302
+ "loss": 1.705,
303
+ "step": 2100
304
  }
305
  ],
306
  "logging_steps": 50,
 
320
  "attributes": {}
321
  }
322
  },
323
+ "total_flos": 3.599673019183661e+18,
324
  "train_batch_size": 2,
325
  "trial_name": null,
326
  "trial_params": null