End of training

README.md

@@ -2,10 +2,13 @@
 license: apache-2.0
 library_name: peft
 tags:
+- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: alignment-handbook/zephyr-7b-sft-full
+datasets:
+- EllieS/TempReason-L1
 model-index:
 - name: TempReason-L1
   results: []
@@ -16,7 +19,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # TempReason-L1
 
-This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on the EllieS/TempReason-L1 dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.2934
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.29339778423309326,
+    "eval_runtime": 0.0982,
+    "eval_samples": 5,
+    "eval_samples_per_second": 50.9,
+    "eval_steps_per_second": 20.36,
     "train_loss": 0.291647286939621,
     "train_runtime": 13916.3013,
     "train_samples": 400000,

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.39.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.29339778423309326,
+    "eval_runtime": 0.0982,
+    "eval_samples": 5,
+    "eval_samples_per_second": 50.9,
+    "eval_steps_per_second": 20.36
+}

runs/Apr30_16-50-31_612e66badb5c/events.out.tfevents.1714509780.612e66badb5c.18823.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b9b6a42887c758f8e0fb6edb67c4e26df6373db5bbad5dda07006d2cdcfb70b
+size 364