Model save

README.md

@@ -1,11 +1,9 @@
 ---
 base_model: meta-llama/Llama-3.1-8B-Instruct
-datasets: Tonic/MiniF2F
 library_name: transformers
 model_name: Llama-3.1-8B-Instruct-Open-R1-Distill-Lean
 tags:
 - generated_from_trainer
-- open-r1
 - trl
 - sft
 licence: license
@@ -13,7 +11,7 @@ licence: license
 
 # Model Card for Llama-3.1-8B-Instruct-Open-R1-Distill-Lean
 
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the [Tonic/MiniF2F](https://huggingface.co/datasets/Tonic/MiniF2F) dataset.
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -29,7 +27,7 @@ print(output["generated_text"])
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/rohanbayya1205-san-jose-state-university/huggingface/runs/ws8rmwff) 
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/rohanbayya1205-san-jose-state-university/huggingface/runs/rl8xdbu7) 
 
 
 This model was trained with SFT.

adapter_config.json

@@ -24,9 +24,9 @@
   "revision": null,
   "target_modules": [
     "o_proj",
+    "q_proj",
     "k_proj",
-    "v_proj",
-    "q_proj"
+    "v_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": true,

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f9b528d33a706136dec74218a64d50402715fa9285eb6f9d674a1b99a1184e5
+oid sha256:d80adfc6a5efc9cfe88bcdaf9fee15d1da4c8e085b7b344176dd37d21f39eb80
 size 7522752

all_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 196696080384.0,
-    "train_loss": 3363.7795448303223,
-    "train_runtime": 10.1807,
+    "total_flos": 3737225527296.0,
+    "train_loss": 33168.128967285156,
+    "train_runtime": 78.7129,
     "train_samples": 488,
-    "train_samples_per_second": 1.768,
-    "train_steps_per_second": 0.196
+    "train_samples_per_second": 2.287,
+    "train_steps_per_second": 0.254
 }

runs/Mar03_21-17-14_ip-10-192-12-214/events.out.tfevents.1741036644.ip-10-192-12-214.31425.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df0ca1acb1f86d1f3e1d89675ba8a6f99f2ab6dfcd414fad91a483b8e19a063b
+size 6506

train_results.json

@@ -1,8 +1,8 @@
 {
-    "total_flos": 196696080384.0,
-    "train_loss": 3363.7795448303223,
-    "train_runtime": 10.1807,
+    "total_flos": 3737225527296.0,
+    "train_loss": 33168.128967285156,
+    "train_runtime": 78.7129,
     "train_samples": 488,
-    "train_samples_per_second": 1.768,
-    "train_steps_per_second": 0.196
+    "train_samples_per_second": 2.287,
+    "train_steps_per_second": 0.254
 }

trainer_state.json

@@ -10,19 +10,19 @@
   "log_history": [
     {
       "epoch": 0,
-      "mean_token_accuracy": 0.6600732803344727,
+      "mean_token_accuracy": 0.6642943471670151,
       "step": 0,
-      "total_flos": 196696080384.0,
-      "train_loss": 3363.7795448303223,
-      "train_runtime": 10.1807,
-      "train_samples_per_second": 1.768,
-      "train_steps_per_second": 0.196
+      "total_flos": 3737225527296.0,
+      "train_loss": 33168.128967285156,
+      "train_runtime": 78.7129,
+      "train_samples_per_second": 2.287,
+      "train_steps_per_second": 0.254
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2,
+  "max_steps": 20,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 20,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -36,7 +36,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 196696080384.0,
+  "total_flos": 3737225527296.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02d9addc654a14dc4841e1d019ae713ceb25955f72671e8521e85905de27bf43
+oid sha256:fe6a1413db8bfaa2c249f4c9a06e39b05fc03a29e90894f1e1a020a801111c97
 size 7352