End of training

README.md

@@ -1,7 +1,6 @@
 ---
 library_name: transformers
-license: apache-2.0
-base_model: JackFram/llama-68m
+base_model: Xenova/tiny-random-Phi3ForCausalLM
 tags:
 - axolotl
 - generated_from_trainer
@@ -20,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 axolotl version: `0.6.0`
 ```yaml
-base_model: JackFram/llama-68m
+base_model: Xenova/tiny-random-Phi3ForCausalLM
 batch_size: 32
 bf16: true
 chat_template: tokenizer_default_fallback_alpaca
@@ -58,15 +57,13 @@ sample_packing: false
 save_steps: 400
 save_total_limit: 1
 sequence_len: 2048
-special_tokens:
-  pad_token: </s>
 tokenizer_type: LlamaTokenizerFast
 torch_dtype: bf16
 trust_remote_code: true
 val_set_size: 0.1
 wandb_entity: ''
 wandb_mode: online
-wandb_name: JackFram/llama-68m-argilla/databricks-dolly-15k-curated-en
+wandb_name: Xenova/tiny-random-Phi3ForCausalLM-argilla/databricks-dolly-15k-curated-en
 wandb_project: Gradients-On-Demand
 wandb_run: your_name
 wandb_runid: default
@@ -78,9 +75,9 @@ warmup_ratio: 0.05
 
 # test-repo
 
-This model is a fine-tuned version of [JackFram/llama-68m](https://huggingface.co/JackFram/llama-68m) on the argilla/databricks-dolly-15k-curated-en dataset.
+This model is a fine-tuned version of [Xenova/tiny-random-Phi3ForCausalLM](https://huggingface.co/Xenova/tiny-random-Phi3ForCausalLM) on the argilla/databricks-dolly-15k-curated-en dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.9544
+- Loss: 8.0331
 
 ## Model description
 
@@ -112,19 +109,19 @@ The following hyperparameters were used during training:
 
 | Training Loss | Epoch  | Step | Validation Loss |
 |:-------------:|:------:|:----:|:---------------:|
-| No log        | 0.0003 | 1    | 4.0313          |
-| 3.4674        | 0.0592 | 200  | 3.5561          |
-| 2.9871        | 0.1184 | 400  | 3.5949          |
-| 3.1757        | 0.1776 | 600  | 3.3786          |
-| 3.3312        | 0.2368 | 800  | 3.4476          |
-| 2.6814        | 0.2959 | 1000 | 3.1961          |
-| 2.7786        | 0.3551 | 1200 | 3.1063          |
-| 2.9228        | 0.4143 | 1400 | 3.0346          |
-| 3.1288        | 0.4735 | 1600 | 2.9915          |
-| 3.1214        | 0.5327 | 1800 | 2.9728          |
-| 3.1533        | 0.5919 | 2000 | 2.9505          |
-| 2.4877        | 0.6511 | 2200 | 2.9438          |
-| 2.8664        | 0.7103 | 2400 | 2.9544          |
+| No log        | 0.0003 | 1    | 10.3773         |
+| 9.2412        | 0.0592 | 200  | 9.2247          |
+| 8.2947        | 0.1184 | 400  | 8.4011          |
+| 8.107         | 0.1776 | 600  | 8.1491          |
+| 8.0544        | 0.2368 | 800  | 8.0751          |
+| 7.8343        | 0.2959 | 1000 | 8.0513          |
+| 7.9614        | 0.3551 | 1200 | 8.0328          |
+| 8.0718        | 0.4143 | 1400 | 8.0292          |
+| 8.0845        | 0.4735 | 1600 | 8.0296          |
+| 7.9257        | 0.5327 | 1800 | 8.0282          |
+| 7.8742        | 0.5919 | 2000 | 8.0276          |
+| 8.0265        | 0.6511 | 2200 | 8.0276          |
+| 7.8113        | 0.7103 | 2400 | 8.0331          |
 
 
 ### Framework versions

generation_config.json

@@ -1,8 +1,8 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
+  "bos_token_id": 1,
   "do_sample": true,
-  "eos_token_id": 2,
-  "pad_token_id": 1,
+  "eos_token_id": 32000,
+  "pad_token_id": 32000,
   "transformers_version": "4.48.1"
 }