Model save

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: RyanYr/reflect_llama8B_om2-300k_sft-t1_lr1e-6
+base_model: RyanYr/reflect_llama8B_om2-300k460k_sft-t1_lr1e-6
 library_name: transformers
-model_name: reflect_llama8B_om2-llama-t0-mstlrg-300k-llama33-130k-t12_sft-t1_lr1e-6
+model_name: reflect_llama8B_om2-mixed-t0-mstlrg-300k460k-t12_llama33-130k-t12_sft-t1_lr1e-6
 tags:
 - generated_from_trainer
 - trl
@@ -9,9 +9,9 @@ tags:
 licence: license
 ---
 
-# Model Card for reflect_llama8B_om2-llama-t0-mstlrg-300k-llama33-130k-t12_sft-t1_lr1e-6
+# Model Card for reflect_llama8B_om2-mixed-t0-mstlrg-300k460k-t12_llama33-130k-t12_sft-t1_lr1e-6
 
-This model is a fine-tuned version of [RyanYr/reflect_llama8B_om2-300k_sft-t1_lr1e-6](https://huggingface.co/RyanYr/reflect_llama8B_om2-300k_sft-t1_lr1e-6).
+This model is a fine-tuned version of [RyanYr/reflect_llama8B_om2-300k460k_sft-t1_lr1e-6](https://huggingface.co/RyanYr/reflect_llama8B_om2-300k460k_sft-t1_lr1e-6).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -20,14 +20,14 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="RyanYr/reflect_llama8B_om2-llama-t0-mstlrg-300k-llama33-130k-t12_sft-t1_lr1e-6", device="cuda")
+generator = pipeline("text-generation", model="RyanYr/reflect_llama8B_om2-mixed-t0-mstlrg-300k460k-t12_llama33-130k-t12_sft-t1_lr1e-6", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 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/yyr/huggingface/runs/l8rz3k9a)
+[<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/yyr/huggingface/runs/s1697tax)
 
 This model was trained with SFT.
 

last_checkpoint/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "RyanYr/reflect_llama8B_om2-300k_sft-t1_lr1e-6",
+  "_name_or_path": "RyanYr/reflect_llama8B_om2-300k460k_sft-t1_lr1e-6",
   "architectures": [
     "LlamaForCausalLM"
   ],

last_checkpoint/model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31b2f170487eaaa7462a6740a4074030f3abf31860fa10dcd498d0b0c0c80837
+oid sha256:27277005dad6d94a8f6fe5d18a959104994da4abe04bd584ad4fbec347bfc2d5
 size 4976706864

last_checkpoint/model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0cdf05e971aabeb38e85eb7d4bb201595db6e98d31a381af5b94b1ecd248e45
+oid sha256:63225fc5995cd3fb88019ad7183aecf5885d574f076216f598e4789ba3da8264
 size 4999802720

last_checkpoint/model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1767de457bb7e45a1fd6a4a35de63672e0bf11efbc9f519d3366e8413f4f9096
+oid sha256:c4f02483e95fd27c8032034fe0e69e34fcb991d4818083a6391b3057d1c499cb
 size 4915916176

last_checkpoint/model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a7802cd7d384ab455a44c57297fcea9c7298a5e93a5b55e0372c9580aba0db
+oid sha256:81f75e06a527e939dd16cef857f15380009423e46d5c09a533205285594981ed
 size 1168147000

last_checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10897690953d6e67df1b5d2af3f8618d40ac4523129c81be891b7fcf9416ae6d
+oid sha256:f2b77149e545080fc603f53c9dbb97649cbaf7e108edd22ed1e7077e8c68b76a
 size 6968