flytech commited on
Commit
fe16d95
1 Parent(s): 95d1ba2

Training in progress, step 900, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dc0dec55c3008c4e06b05c2c6399fd0b2087d83a1959d6bd37c0b30ab55397c
3
  size 40036040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:224f4266e6748e11b7edf9179d9304cff648b4827d8e30486417966ce5bc59f4
3
  size 40036040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:406f0543a6da379c3a07397e363fea8776e66421d39ca05d9149e520a54e989a
3
  size 20524127
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5fd17fda63dbe1b1398727e69ecb48adc4692b5027d29809520c675ceffa633
3
  size 20524127
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4ed6b2ccb6b511d4a5b0a951ff64fe81b3f72732119d339d43b6ec843aa012e1
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7cabf24117f3a5183f9dec64be021c40974def1eda597b0447be09546cb1b5a
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1fa67daeb64419974086372ba8aca20c65ba993b273167e2568257f8e5992653
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cf3d71e92538f8852c28d0ab56db4f9cd9e4b98c0e807cde568075961dd5196
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.507836990595611,
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,
@@ -111,13 +111,26 @@
111
  "eval_samples_per_second": 1.753,
112
  "eval_steps_per_second": 0.22,
113
  "step": 800
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 100,
117
  "max_steps": 957,
118
  "num_train_epochs": 3,
119
  "save_steps": 100,
120
- "total_flos": 1.3279781520094003e+17,
121
  "trial_name": null,
122
  "trial_params": null
123
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.8213166144200628,
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,
 
111
  "eval_samples_per_second": 1.753,
112
  "eval_steps_per_second": 0.22,
113
  "step": 800
114
+ },
115
+ {
116
+ "epoch": 2.82,
117
+ "learning_rate": 0.0002,
118
+ "loss": 0.493,
119
+ "step": 900
120
+ },
121
+ {
122
+ "epoch": 2.82,
123
+ "eval_runtime": 512.3415,
124
+ "eval_samples_per_second": 1.757,
125
+ "eval_steps_per_second": 0.221,
126
+ "step": 900
127
  }
128
  ],
129
  "logging_steps": 100,
130
  "max_steps": 957,
131
  "num_train_epochs": 3,
132
  "save_steps": 100,
133
+ "total_flos": 1.4940792341869363e+17,
134
  "trial_name": null,
135
  "trial_params": null
136
  }