Update README.md

README.md

@@ -65,10 +65,14 @@ The following hyperparameters were used during training:
 
 ### Training results
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 1.7917        | 0.72  | 5    | 1.7604          |
-| 1.7743        | 1.44  | 10   | 1.7217          |
+| Step | Training Loss | Validation Loss |
+|------|---------------|-----------------|
+| 5    | 1.802800      | 1.848371        |
+| 10   | 1.605800      | 1.803416        |
+| 15   | 1.844800      | 1.762276        |
+| 20   | 1.752600      | 1.754042        |
+| 25   | 1.512400      | 1.750550        |
+
 
 
 ### Usage
@@ -76,13 +80,10 @@ The following hyperparameters were used during training:
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
 
-model_id = "mrm8488/limstral-7B-v0.1"
-tokenizer = "mrm8488/limstral-7B-v0.1"
-
-model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16)
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+repo_id = "mrm8488/limstral-7B-v0.1"
 
-model.resize_token_embeddings(len(tokenizer))
+model = AutoModelForCausalLM.from_pretrained(repo_id, torch_dtype=torch.bfloat16)
+tokenizer = AutoTokenizer.from_pretrained(repo_id)
 
 gen = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0)