Hugging Face's logo

Nekofox
/
M2M100-ja-zh

Text2Text Generation
Transformers
PyTorch
TensorBoard
m2m_100
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
5
Nekofox commited on
Commit
99356d1
•
1 Parent(s): 80c9646

Training in progress, step 597000

Browse files
Files changed (11) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/pytorch_model.bin +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scaler.pt +1 -1
  5. last-checkpoint/scheduler.pt +1 -1
  6. last-checkpoint/trainer_state.json +39 -3
  7. last-checkpoint/training_args.bin +1 -1
  8. pytorch_model.bin +1 -1
  9. runs/Jun02_00-39-49_138e59608869/1685668028.9118278/events.out.tfevents.1685668028.138e59608869.1307.1 +3 -0
  10. runs/Jun02_00-39-49_138e59608869/events.out.tfevents.1685668028.138e59608869.1307.0 +3 -0
  11. training_args.bin +1 -1
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe0d9f56726daf6b16bb8d5d4f4ade97bb5cc7e60a7f11eb05a8e66f54c42e0f
3
  size 3871544599
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d50e70f554eb188534935fd7909d648a293a6459a6b08fb795f89d4b99b56d3
3
  size 3871544599
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:650171e8ad578ef8686cb7eda72ac3586fdcc3a1cb73b9e45f5553776bec0a1b
3
  size 1944201353
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b7c41f1dd1fe09e5edbc6dde6212884240e407d1845e563c5f3b4dc645e0c8c
3
  size 1944201353
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26c8c95b482dc20288935c89df5726ca51c516105c7e5f74e609c7af3177d0c8
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f13282abbf7fd053ee4fe6be05fa78fe3b39f9f4687f3d241e7e649eca4d78be
3
  size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e77e56a2ba56c21827ec91d155588126ec53ab90307574dd6bbda5b13092a2f8
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81e510f8e25cf139f6febe3cdf067c5193934d192326aa6b7345eb94b2015331
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:64ce8d836ce27c39f0d4109ce68497decb68e999658c622e881394a4eb6c288a
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a86b6bd5cda860a250f0b8282ba91a7303c4f8c8676b50ffc257a329d6605a0
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 15.570917784232105,
5
- "global_step": 594000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -7134,11 +7134,47 @@
7134
  "learning_rate": 5.825375304011768e-07,
7135
  "loss": 1.0333,
7136
  "step": 594000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7137
  }
7138
  ],
7139
  "max_steps": 762960,
7140
  "num_train_epochs": 20,
7141
- "total_flos": 7.103152678841303e+17,
7142
  "trial_name": null,
7143
  "trial_params": null
7144
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 15.649568527120403,
5
+ "global_step": 597000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
7134
  "learning_rate": 5.825375304011768e-07,
7135
  "loss": 1.0333,
7136
  "step": 594000
7137
+ },
7138
+ {
7139
+ "epoch": 15.58,
7140
+ "learning_rate": 5.792455056448578e-07,
7141
+ "loss": 1.039,
7142
+ "step": 594500
7143
+ },
7144
+ {
7145
+ "epoch": 15.6,
7146
+ "learning_rate": 5.759550170777461e-07,
7147
+ "loss": 1.0357,
7148
+ "step": 595000
7149
+ },
7150
+ {
7151
+ "epoch": 15.61,
7152
+ "learning_rate": 5.726726840236046e-07,
7153
+ "loss": 1.0314,
7154
+ "step": 595500
7155
+ },
7156
+ {
7157
+ "epoch": 15.62,
7158
+ "learning_rate": 5.693985203953675e-07,
7159
+ "loss": 1.0136,
7160
+ "step": 596000
7161
+ },
7162
+ {
7163
+ "epoch": 15.64,
7164
+ "learning_rate": 5.661325400713397e-07,
7165
+ "loss": 1.012,
7166
+ "step": 596500
7167
+ },
7168
+ {
7169
+ "epoch": 15.65,
7170
+ "learning_rate": 5.628747568951393e-07,
7171
+ "loss": 1.0314,
7172
+ "step": 597000
7173
  }
7174
  ],
7175
  "max_steps": 762960,
7176
  "num_train_epochs": 20,
7177
+ "total_flos": 7.136369757666017e+17,
7178
  "trial_name": null,
7179
  "trial_params": null
7180
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46b3a87459854f08d80f4fb8cbdd6dbf69afb36e65aeb8868750af0e1c3b25c3
3
  size 3771
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aff8c84135a54e324ae32bff714d5120f1b7c9cf148f719f0922ca32d7966dc
3
  size 3771
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:650171e8ad578ef8686cb7eda72ac3586fdcc3a1cb73b9e45f5553776bec0a1b
3
  size 1944201353
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b7c41f1dd1fe09e5edbc6dde6212884240e407d1845e563c5f3b4dc645e0c8c
3
  size 1944201353
runs/Jun02_00-39-49_138e59608869/1685668028.9118278/events.out.tfevents.1685668028.138e59608869.1307.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ffd1ee339247b8d01c5a784b1abf60214959607e844381fe61a9e4b97fe4fd
3
+ size 6184
runs/Jun02_00-39-49_138e59608869/events.out.tfevents.1685668028.138e59608869.1307.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde10911f1a5a06553b08b6521d1601b8f9f8f9aa97b33235b07c786ca876155
3
+ size 5421
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46b3a87459854f08d80f4fb8cbdd6dbf69afb36e65aeb8868750af0e1c3b25c3
3
  size 3771
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7aff8c84135a54e324ae32bff714d5120f1b7c9cf148f719f0922ca32d7966dc
3
  size 3771