k4black commited on
Commit
462d731
·
1 Parent(s): b5a2a1c

Training in progress, step 3000

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0eda2c9ead81cfb1a812635c9d7de15a350744a053613a639dc81512c0c74253
3
  size 484015877
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:118f11e0d84ce3412f0281c67abd06b029f3d4d07a72438ba7182ce0f59d4e32
3
  size 484015877
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0d6f4640c903e0f0669d50504d120d7f20a16f6ea8fc7385bc1b439787f9b35
3
  size 242014297
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14065493d9c0cd89909a4479c6adb4522d23ff4fbcc1c3c0ac202a7603403dc3
3
  size 242014297
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6270ad342856a44bfc69ae067667c0aa9e39cf62a7ef48fd011fa5833882d18c
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cba09060d4e5c0be85a1d41e58c89ab09d39f09122d03e1bc8222b013265c96
3
  size 14575
last-checkpoint/scaler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:724c5c345a2598ba22276949bc38bd00636516d48062ab00877ed639d4c8feb5
3
  size 557
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d821d43f1f40a9df79baae3da2b634f271a408f300c294f73c823b49cd908ce5
3
  size 557
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f379486ceb3fb849525dba52ed4ad9a3e41cbb661ec1dc05803f28a51cde0e8e
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c87425c169975acef42a6cd137204ef2ac5b636056155eafc97d710301d2b0c
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "best_metric": 0.5524556612739725,
3
- "best_model_checkpoint": "results/checkpoint-2500",
4
- "epoch": 0.5,
5
- "global_step": 2500,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -106,11 +106,31 @@
106
  "eval_samples_per_second": 35.99,
107
  "eval_steps_per_second": 1.8,
108
  "step": 2500
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
109
  }
110
  ],
111
  "max_steps": 15000,
112
  "num_train_epochs": 3,
113
- "total_flos": 6418569074442240.0,
114
  "trial_name": null,
115
  "trial_params": null
116
  }
 
1
  {
2
+ "best_metric": 0.5571591325212851,
3
+ "best_model_checkpoint": "results/checkpoint-3000",
4
+ "epoch": 0.6,
5
+ "global_step": 3000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
106
  "eval_samples_per_second": 35.99,
107
  "eval_steps_per_second": 1.8,
108
  "step": 2500
109
+ },
110
+ {
111
+ "epoch": 0.6,
112
+ "learning_rate": 8.424561403508773e-05,
113
+ "loss": 0.7097,
114
+ "step": 3000
115
+ },
116
+ {
117
+ "epoch": 0.6,
118
+ "eval_bleu": 0.12307160579590622,
119
+ "eval_exact_match": 0.155,
120
+ "eval_loss": 0.8275034427642822,
121
+ "eval_rouge1": 0.5571591325212851,
122
+ "eval_rouge2": 0.3846841785043018,
123
+ "eval_rougeL": 0.5390722174679519,
124
+ "eval_rougeLsum": 0.5456202385734745,
125
+ "eval_runtime": 56.9486,
126
+ "eval_samples_per_second": 35.119,
127
+ "eval_steps_per_second": 1.756,
128
+ "step": 3000
129
  }
130
  ],
131
  "max_steps": 15000,
132
  "num_train_epochs": 3,
133
+ "total_flos": 7695000865996800.0,
134
  "trial_name": null,
135
  "trial_params": null
136
  }
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0d6f4640c903e0f0669d50504d120d7f20a16f6ea8fc7385bc1b439787f9b35
3
  size 242014297
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14065493d9c0cd89909a4479c6adb4522d23ff4fbcc1c3c0ac202a7603403dc3
3
  size 242014297