End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: EleutherAI/pythia-410m-deduped-v0
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: pythia-410m-sft-full
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # pythia-410m-sft-full
 
-This model is a fine-tuned version of [EleutherAI/pythia-410m-deduped-v0](https://huggingface.co/EleutherAI/pythia-410m-deduped-v0) on the generator dataset.
+This model is a fine-tuned version of [EleutherAI/pythia-410m-deduped-v0](https://huggingface.co/EleutherAI/pythia-410m-deduped-v0) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.6286
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.628558874130249,
+    "eval_runtime": 657.7588,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 21.435,
+    "eval_steps_per_second": 1.341,
     "train_loss": 1.6493343958478666,
     "train_runtime": 16072.2247,
     "train_samples": 207865,

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "EleutherAI/pythia-410m-deduped-v0",
+  "architectures": [
+    "GPTNeoXForCausalLM"
+  ],
+  "attention_bias": true,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "classifier_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.0,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.25,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "use_parallel_residual": true,
+  "vocab_size": 50304
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.628558874130249,
+    "eval_runtime": 657.7588,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 21.435,
+    "eval_steps_per_second": 1.341
+}