End of training

README.md

@@ -1,10 +1,11 @@
 ---
 base_model: facebook/opt-350m
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 library_name: peft
 license: other
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
@@ -18,7 +19,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # opt350
 
-This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the generator dataset.
+This model is a fine-tuned version of [facebook/opt-350m](https://huggingface.co/facebook/opt-350m) on the HuggingFaceH4/ultrachat_200k dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7869
 
 ## Model description
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9999380306128772,
+    "eval_loss": 1.7869231700897217,
+    "eval_runtime": 154.2674,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 92.56,
+    "eval_steps_per_second": 5.789,
     "total_flos": 4248659495485440.0,
     "train_loss": 0.0,
     "train_runtime": 0.0126,

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-350m",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": false,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
+  "init_std": 0.02,
+  "layer_norm_elementwise_affine": true,
+  "layerdrop": 0.0,
+  "max_position_embeddings": 2048,
+  "model_type": "opt",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9999380306128772,
+    "eval_loss": 1.7869231700897217,
+    "eval_runtime": 154.2674,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 92.56,
+    "eval_steps_per_second": 5.789
+}

runs/Nov05_10-54-00_gnode007.cluster/events.out.tfevents.1730833007.gnode007.cluster.1852419.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e5f892e2c2f2ab7ac09de4d3480e7b2c6180399c2977c0987af7082f2a46fe4
+size 359