End of training

README.md

@@ -1,6 +1,6 @@
 ---
 license: apache-2.0
-base_model: EleutherAI/pythia-1b-deduped
+base_model: EleutherAI/pythia-70m
 tags:
 - generated_from_trainer
 model-index:
@@ -11,10 +11,10 @@ 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/costa-huang/huggingface/runs/novc5rvg)
+[<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/costa-huang/huggingface/runs/ef1zomwu)
 # ppo1
 
-This model is a fine-tuned version of [EleutherAI/pythia-1b-deduped](https://huggingface.co/EleutherAI/pythia-1b-deduped) on an unknown dataset.
+This model is a fine-tuned version of [EleutherAI/pythia-70m](https://huggingface.co/EleutherAI/pythia-70m) on an unknown dataset.
 
 ## Model description
 
@@ -34,18 +34,16 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 3e-06
-- train_batch_size: 32
-- eval_batch_size: 8
+- train_batch_size: 64
+- eval_batch_size: 16
 - seed: 42
-- gradient_accumulation_steps: 16
-- total_train_batch_size: 512
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: linear
 - num_epochs: 3.0
 
 ### Framework versions
 
-- Transformers 4.42.1
-- Pytorch 2.2.1+cu121
-- Datasets 2.18.0
+- Transformers 4.42.0.dev0
+- Pytorch 2.2.0+cu121
+- Datasets 2.19.0
 - Tokenizers 0.19.1

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "EleutherAI/pythia-1b-deduped",
+  "_name_or_path": "EleutherAI/pythia-70m",
   "architectures": [
     "GPTNeoXForCausalLM"
   ],
@@ -10,20 +10,20 @@
   "eos_token_id": 0,
   "hidden_act": "gelu",
   "hidden_dropout": 0.0,
-  "hidden_size": 2048,
+  "hidden_size": 512,
   "initializer_range": 0.02,
-  "intermediate_size": 8192,
+  "intermediate_size": 2048,
   "layer_norm_eps": 1e-05,
   "max_position_embeddings": 2048,
   "model_type": "gpt_neox",
   "num_attention_heads": 8,
-  "num_hidden_layers": 16,
+  "num_hidden_layers": 6,
   "rope_scaling": null,
   "rotary_emb_base": 10000,
   "rotary_pct": 0.25,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.42.1",
+  "transformers_version": "4.42.0.dev0",
   "use_cache": true,
   "use_parallel_residual": true,
   "vocab_size": 50304

generation_config.json

@@ -1,5 +1,5 @@
 {
   "_from_model_config": true,
   "bos_token_id": 0,
-  "transformers_version": "4.42.1"
+  "transformers_version": "4.42.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5604db3fce72006551bc34a2700cb3d8306e7474ff960760e8a5f6fbc50adc3
-size 4047149576
+oid sha256:62c0625ca6e34d4cd7bf6ade0002a88bc7ad3433e0d4c89cfa50cee33b8adfe8
+size 281715176

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08a772ef9628c4f5874238aeba7be501acb44e435b09793c998f97466b79a846
-size 6072
+oid sha256:2184eb3039eb07aff2d8935a9194be75e655ac1e69537a5aa11d4976094e8a46
+size 6008