furmaniak commited on
Commit
b95e3e6
·
verified ·
1 Parent(s): 800a5e2

End of training

Browse files
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
16
 
17
  # phi-4-openalex
18
 
19
- This model is a fine-tuned version of [microsoft/phi-4](https://huggingface.co/microsoft/phi-4) on an unknown dataset.
20
 
21
  ## Model description
22
 
 
16
 
17
  # phi-4-openalex
18
 
19
+ This model is a fine-tuned version of [microsoft/phi-4](https://huggingface.co/microsoft/phi-4) on the openalex dataset.
20
 
21
  ## Model description
22
 
all_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.0,
3
- "total_flos": 609898777804800.0,
4
- "train_loss": 1.8114001343392918,
5
- "train_runtime": 22537.3565,
6
- "train_samples_per_second": 1.328,
7
- "train_steps_per_second": 0.005
8
  }
 
1
  {
2
+ "epoch": 0.9997727789138832,
3
+ "total_flos": 2868807299235840.0,
4
+ "train_loss": 0.7944060720096935,
5
+ "train_runtime": 47914.0805,
6
+ "train_samples_per_second": 2.939,
7
+ "train_steps_per_second": 0.011
8
  }
train_results.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
- "epoch": 1.0,
3
- "total_flos": 609898777804800.0,
4
- "train_loss": 1.8114001343392918,
5
- "train_runtime": 22537.3565,
6
- "train_samples_per_second": 1.328,
7
- "train_steps_per_second": 0.005
8
  }
 
1
  {
2
+ "epoch": 0.9997727789138832,
3
+ "total_flos": 2868807299235840.0,
4
+ "train_loss": 0.7944060720096935,
5
+ "train_runtime": 47914.0805,
6
+ "train_samples_per_second": 2.939,
7
+ "train_steps_per_second": 0.011
8
  }
trainer_state.json CHANGED
The diff for this file is too large to render. See raw diff
 
training_loss.png CHANGED