rizkyjun commited on
Commit
317c298
1 Parent(s): fae2253

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:c239b50c953cdf1dd821707df8a93b797a88c7eac6fc48aeab3a0725787d24b1
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4762589cf992a191af7292f30bc13977a9512d9b218f8d7ea130e17b147ade4d
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3eb199e083fd51e6aa7a7d64c660ff7d56de711426d4815187974eec2de65259
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a6da0be17de099f994cca1436f9246943b6627f3da1e34584a71a82fcd5c297
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be78a4950643aa2c0f7f3e14329f834829bfe49fb52a0d080a54375bd9ada6a0
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad8deb18f625e20e598fde86410ebc6bf9ded1508a486c75694db51ede76751e
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": 2.380272150039673,
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": 30.443,
134
  "eval_steps_per_second": 3.809,
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": 2.64265735974912e+16,
143
  "trial_name": null,
144
  "trial_params": null
145
  }
 
1
  {
2
+ "best_metric": 2.361511707305908,
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": 30.443,
134
  "eval_steps_per_second": 3.809,
135
  "step": 900
136
+ },
137
+ {
138
+ "epoch": 0.73,
139
+ "learning_rate": 0.0002,
140
+ "loss": 2.3663,
141
+ "step": 1000
142
+ },
143
+ {
144
+ "epoch": 0.73,
145
+ "eval_loss": 2.361511707305908,
146
+ "eval_runtime": 206.0953,
147
+ "eval_samples_per_second": 30.442,
148
+ "eval_steps_per_second": 3.809,
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": 2.936670420934656e+16,
157
  "trial_name": null,
158
  "trial_params": null
159
  }