rakhman-llm commited on
Commit
03970f6
1 Parent(s): 156940a

Training in progress, step 14436, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:514bb0441f99a013f70524090a088bad3b14ed9220a6dd892303aff6d3ee7758
3
  size 891558696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bd4e652d8ba7159a55eef65ccc2abf4194c331631d3222cc330227413042d6fd
3
  size 891558696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb5e538319b0f7ea0cf5a9ed56937c70d6fb75c12684d35dc1e7ca46d4de6481
3
  size 1783272762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d9bff324c51beebab7ae13698893c506abe18328d4d94797a89064fe01f5e088
3
  size 1783272762
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b0ce2de382b41458c0c0fc1269979e7a9757e9fe2cd348dd394069beba1a4f05
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d492ae092e6f5b76a2098bc809b3c1bf0702a65bf8be974795457efc1921df9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8987f2b058801a699d1b84a633feccab5c6170d4609f25febe6d9d8ed35ef270
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32ed8f7e313bb93709f94e944fc8cc81a5cde7370033d4c148cc7bbc922ddb47
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.9093931837073983,
5
  "eval_steps": 500,
6
- "global_step": 14000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -233,12 +233,12 @@
233
  "should_evaluate": false,
234
  "should_log": false,
235
  "should_save": true,
236
- "should_training_stop": false
237
  },
238
  "attributes": {}
239
  }
240
  },
241
- "total_flos": 1.704960301989888e+16,
242
  "train_batch_size": 2,
243
  "trial_name": null,
244
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.0,
5
  "eval_steps": 500,
6
+ "global_step": 14436,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
233
  "should_evaluate": false,
234
  "should_log": false,
235
  "should_save": true,
236
+ "should_training_stop": true
237
  },
238
  "attributes": {}
239
  }
240
  },
241
+ "total_flos": 1.758000534257664e+16,
242
  "train_batch_size": 2,
243
  "trial_name": null,
244
  "trial_params": null