Hugging Face's logo

mgh6
/
TCS_MLM_All

Fill-Mask
Transformers
TensorBoard
Safetensors
esm
Model card Files
xet
 Metrics Community
mgh6 commited on
Commit
2493627
·
verified ·
1 Parent(s): b0c3a4e

Training in progress, step 900, 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 +19 -4
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57ed8507cba571672723e651b2ad2a2f4162369ef3e5f3bcef011bb02fd42532
3
  size 136000488
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd3f9d192f5a816e59fb112bb1b2bf884e9355b4c87749592150eb4e3ca63999
3
  size 136000488
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:df255327f8390b65bc51b95b87e6d714178d2b89f1498dc5fe13d91fe4e70f70
3
  size 268176506
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfc839f69c5de2d1b7b9fa0fbb77dba2374cd6db2e764c061208fa6aac20118e
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 sha256:11b2d09f29c19f9b835e50802bef90522f0cd424941352bab4add1b2071c9ef1
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:850fdb4a4c5ca926a1d2d289abd08e04af5e5a7720f1895ef9773ba33f82e5da
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 sha256:2b858a1083e6305555ad6248393e7824f5c1494c3ae09db8d65339a34a8fa324
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea31b43fad77e528bb398791d33c59471b96f3e351d60e5432e2dc6e9bfc6c71
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 sha256:0b61495d21ac3bc3f03e123369a24257a831ff25abc9dd149ee250d02589497c
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:981f653c329838c2984567bec763c5d51584a3bc2569713648bb11a9bab0a732
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 sha256:57c12301b0341347f4468f16645e8afe020ff48eae5729a0687af53b018e61da
3
  size 15024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f19bd524a4b5807f003926535dbbc8387b715186e497583a1d544522d618d3c2
3
  size 15024
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d334b29ea982f165897a8bd2704fecb4ee283e4d9702b8be82a196505cc46cc9
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36d4923f2032c364a94f4eb28ac470bd0071fde9669df68c8f0e5888ff61a040
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 1.0223731994628906,
3
  "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-700",
4
- "epoch": 7.619047619047619,
5
  "eval_steps": 100,
6
- "global_step": 800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -127,6 +127,21 @@
127
  "eval_samples_per_second": 85.156,
128
  "eval_steps_per_second": 4.482,
129
  "step": 800
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
  }
131
  ],
132
  "logging_steps": 100,
@@ -141,7 +156,7 @@
141
  "early_stopping_threshold": 0.0
142
  },
143
  "attributes": {
144
- "early_stopping_patience_counter": 1
145
  }
146
  },
147
  "TrainerControl": {
@@ -155,7 +170,7 @@
155
  "attributes": {}
156
  }
157
  },
158
- "total_flos": 2.345381782355968e+16,
159
  "train_batch_size": 64,
160
  "trial_name": null,
161
  "trial_params": null
 
1
  {
2
  "best_metric": 1.0223731994628906,
3
  "best_model_checkpoint": "mgh6/TCS_MLM_All/checkpoint-700",
4
+ "epoch": 8.571428571428571,
5
  "eval_steps": 100,
6
+ "global_step": 900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
127
  "eval_samples_per_second": 85.156,
128
  "eval_steps_per_second": 4.482,
129
  "step": 800
130
+ },
131
+ {
132
+ "epoch": 8.571428571428571,
133
+ "grad_norm": 0.182796448469162,
134
+ "learning_rate": 0.00014285714285714284,
135
+ "loss": 1.1605,
136
+ "step": 900
137
+ },
138
+ {
139
+ "epoch": 8.571428571428571,
140
+ "eval_loss": 1.0446473360061646,
141
+ "eval_runtime": 0.2185,
142
+ "eval_samples_per_second": 86.964,
143
+ "eval_steps_per_second": 4.577,
144
+ "step": 900
145
  }
146
  ],
147
  "logging_steps": 100,
 
156
  "early_stopping_threshold": 0.0
157
  },
158
  "attributes": {
159
+ "early_stopping_patience_counter": 2
160
  }
161
  },
162
  "TrainerControl": {
 
170
  "attributes": {}
171
  }
172
  },
173
+ "total_flos": 2.638554505150464e+16,
174
  "train_batch_size": 64,
175
  "trial_name": null,
176
  "trial_params": null