amnae/tinyllamatest

README.md

@@ -1,6 +1,7 @@
 ---
-base_model: amnae/base_edu_llm_damex
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 library_name: peft
+license: apache-2.0
 tags:
 - trl
 - sft
@@ -13,10 +14,10 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/maai/huggingface/runs/8tkph8gh)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/maai/huggingface/runs/4fb8pi7n)
 # output
 
-This model is a fine-tuned version of [amnae/base_edu_llm_damex](https://huggingface.co/amnae/base_edu_llm_damex) on the None dataset.
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the None dataset.
 
 ## Model description
 
@@ -36,12 +37,12 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 5e-05
-- train_batch_size: 5
+- train_batch_size: 20
 - eval_batch_size: 8
 - seed: 42
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
-- num_epochs: 4
+- num_epochs: 1
 
 ### Training results
 

adapter_config.json

@@ -1,7 +1,7 @@
 {
   "alpha_pattern": {},
   "auto_mapping": null,
-  "base_model_name_or_path": "amnae/base_edu_llm_damex",
+  "base_model_name_or_path": "TinyLlama/TinyLlama-1.1B-Chat-v1.0",
   "bias": "none",
   "fan_in_fan_out": false,
   "inference_mode": true,
@@ -20,8 +20,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "v_proj"
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f9dd127e283df55b6572559e52dfbfe0fbaea0c90a98427e75bef9c42962b2f
-size 109069176
+oid sha256:dde9baadcdf518f56417297950edd9d5617bfe21a6212f6373db1f7c331fbfb6
+size 36056608

runs/Jul29_13-40-13_canada.cs.ucl.ac.uk/events.out.tfevents.1722256820.canada.cs.ucl.ac.uk.30220.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05021a9c05e00a6d69841ec4330586f74ef5b7e568400b7cf28d7078f1fab99b
+size 11094

runs/Jul29_13-42-44_canada.cs.ucl.ac.uk/events.out.tfevents.1722256965.canada.cs.ucl.ac.uk.30674.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66f59ccf9ad17d7f683a132305e6308a24a8c3b8c1605c0787fb07c1c5b195d0
+size 7107

tokenizer.model

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
-size 587404
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cbd65b9dd9d28033fd160274402e50a218e9d629e8ebf173214e2582467d339
+oid sha256:ff91ab78be0c23bdbd4c682a4a3a9c62857deca9752cfcc19f35b11369b01c40
 size 5368