ramdhanfirdaus commited on
Commit
2670386
1 Parent(s): 51289cc

Training in progress, step 1000, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c327d5945c4e02ff4f63b8a838cd1edeb8bc5e0971709c80713280abee3b525
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddec43fdcca785358f5cb4ad973bf0ca2824ef0ebff50bc9e3f9d7069d2fbe77
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:65aafa816b059c56057e4355527c1b409efb463fde0809c9b38b4dd74529bed3
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b6fa0cbe2717b5ef91232b6e1e09cbce7a1b5a0dbcea10e12df4c8c78e2ade4
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99f1c1111b8d1f0cb2cc4b559a49a0a42b0bb5df350eda9361510f1ff2ab08e2
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:367394aed610ff7068eaf27da3eb89a6cd4769f26c2abeadffb65a7a6d3952cd
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.6576156616210938,
3
- "best_model_checkpoint": "./outputs/checkpoint-900",
4
- "epoch": 0.6557377049180327,
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,
@@ -133,13 +133,27 @@
133
  "eval_samples_per_second": 43.661,
134
  "eval_steps_per_second": 5.463,
135
  "step": 900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
136
  }
137
  ],
138
  "logging_steps": 100,
139
  "max_steps": 4116,
140
  "num_train_epochs": 3,
141
  "save_steps": 100,
142
- "total_flos": 5.365902922462003e+16,
143
  "trial_name": null,
144
  "trial_params": null
145
  }
 
1
  {
2
+ "best_metric": 1.6344480514526367,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1000",
4
+ "epoch": 0.7285974499089253,
5
  "eval_steps": 100,
6
+ "global_step": 1000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
133
  "eval_samples_per_second": 43.661,
134
  "eval_steps_per_second": 5.463,
135
  "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.73,
139
+ "learning_rate": 0.0002,
140
+ "loss": 1.6475,
141
+ "step": 1000
142
+ },
143
+ {
144
+ "epoch": 0.73,
145
+ "eval_loss": 1.6344480514526367,
146
+ "eval_runtime": 143.8656,
147
+ "eval_samples_per_second": 43.61,
148
+ "eval_steps_per_second": 5.456,
149
+ "step": 1000
150
  }
151
  ],
152
  "logging_steps": 100,
153
  "max_steps": 4116,
154
  "num_train_epochs": 3,
155
  "save_steps": 100,
156
+ "total_flos": 5.962359246697267e+16,
157
  "trial_name": null,
158
  "trial_params": null
159
  }