smilemikan commited on
Commit
523d2d1
1 Parent(s): 667b0c2

Training in progress, step 4500, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:738fe809067ec27fe3c901868d7de44ce62aeb2f32711ce135f92d17c0b810a8
3
  size 5125261
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:463726582e2d7562b778e4a4b90d8ffa3352a69de3a7c14b8d59ea6166e1cd0d
3
  size 5125261
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:74322843b1da9a146c9851ea836c1bebd2d834e2c66c879e38e21abc44eb38ca
3
  size 2460465086
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:715a40701452d8e5f388e2a89d0086fe4afb6788b5a0b6f89eeb580d025558e7
3
  size 2460465086
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1255a4808803555132c31bf2257b79123162df6c92908f3a84b09e150d37cd61
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b941a0e10dbaedd9cd8ace21c739fcaa6789ec2d6441df4027143f375ca054f1
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5a2e5ff60d578727c0bc9cc9ae5e543398968c07cf3ea974c025608e21631cd0
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0025a0ef3b18b2981b675888ae3ea4bc9928ef870722a42d093d3b700b398808
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.2251899242401123,
3
- "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-4000",
4
- "epoch": 0.8812513769552764,
5
  "eval_steps": 500,
6
- "global_step": 4000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -119,13 +119,27 @@
119
  "eval_samples_per_second": 212.082,
120
  "eval_steps_per_second": 13.27,
121
  "step": 4000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
122
  }
123
  ],
124
  "logging_steps": 500,
125
  "max_steps": 60000,
126
  "num_train_epochs": 14,
127
  "save_steps": 500,
128
- "total_flos": 4045442515992576.0,
129
  "trial_name": null,
130
  "trial_params": null
131
  }
 
1
  {
2
+ "best_metric": 2.148716449737549,
3
+ "best_model_checkpoint": "smilemikan/nllb-finetuned-jpn-to-ain-2/checkpoint-4500",
4
+ "epoch": 0.991407799074686,
5
  "eval_steps": 500,
6
+ "global_step": 4500,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
119
  "eval_samples_per_second": 212.082,
120
  "eval_steps_per_second": 13.27,
121
  "step": 4000
122
+ },
123
+ {
124
+ "epoch": 0.99,
125
+ "learning_rate": 1.8500333333333337e-05,
126
+ "loss": 2.3391,
127
+ "step": 4500
128
+ },
129
+ {
130
+ "epoch": 0.99,
131
+ "eval_loss": 2.148716449737549,
132
+ "eval_runtime": 43.0552,
133
+ "eval_samples_per_second": 210.845,
134
+ "eval_steps_per_second": 13.192,
135
+ "step": 4500
136
  }
137
  ],
138
  "logging_steps": 500,
139
  "max_steps": 60000,
140
  "num_train_epochs": 14,
141
  "save_steps": 500,
142
+ "total_flos": 4561856770473984.0,
143
  "trial_name": null,
144
  "trial_params": null
145
  }