Hanzalwi commited on
Commit
2a6f552
1 Parent(s): a793fd0

Training in progress, step 1300, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57989e1fd10b56b2bab72708fbd6d79b6ecad73cf4f91cd5e396a74c212ec955
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a8588f303560416dc6ac7978e949a2e994a770d8713b2c2430ebd48bc92b9d
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a0835ff9d6fab8a0b2490c1330449db90f28256320f9b26781a1f514715699ff
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d32c720a9aafb7e90df761c566cc6272013213fb381ca06833dd34cbb79a35
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1aab6ee5ef938a85af4adff67c8efb0931b96509caa2c6ce3bd47b07a26ea0a3
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33aa1ec500d684fb1fdc58c5b0a24d5d7f978ce714c4fb6b371ee377a90400a8
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d8d6be7898f87772ccbc5c732e900fe63a643c4595ce6af3d6bc6f811ba4b65
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d52a4d67627993645e1cea71ef09276f4b0a2f5bba92959ce9a1a76893653978
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.9781661033630371,
3
- "best_model_checkpoint": "./outputs/checkpoint-1200",
4
- "epoch": 1.7045454545454546,
5
  "eval_steps": 100,
6
- "global_step": 1200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -175,6 +175,20 @@
175
  "eval_samples_per_second": 12.463,
176
  "eval_steps_per_second": 1.562,
177
  "step": 1200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
178
  }
179
  ],
180
  "logging_steps": 100,
@@ -182,7 +196,7 @@
182
  "num_input_tokens_seen": 0,
183
  "num_train_epochs": 3,
184
  "save_steps": 100,
185
- "total_flos": 6.7446395960832e+16,
186
  "trial_name": null,
187
  "trial_params": null
188
  }
 
1
  {
2
+ "best_metric": 0.9716654419898987,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1300",
4
+ "epoch": 1.8465909090909092,
5
  "eval_steps": 100,
6
+ "global_step": 1300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
175
  "eval_samples_per_second": 12.463,
176
  "eval_steps_per_second": 1.562,
177
  "step": 1200
178
+ },
179
+ {
180
+ "epoch": 1.85,
181
+ "learning_rate": 0.0002,
182
+ "loss": 1.099,
183
+ "step": 1300
184
+ },
185
+ {
186
+ "epoch": 1.85,
187
+ "eval_loss": 0.9716654419898987,
188
+ "eval_runtime": 119.6105,
189
+ "eval_samples_per_second": 12.474,
190
+ "eval_steps_per_second": 1.563,
191
+ "step": 1300
192
  }
193
  ],
194
  "logging_steps": 100,
 
196
  "num_input_tokens_seen": 0,
197
  "num_train_epochs": 3,
198
  "save_steps": 100,
199
+ "total_flos": 7.307569918236672e+16,
200
  "trial_name": null,
201
  "trial_params": null
202
  }