End of training

README.md

@@ -3,11 +3,15 @@ library_name: transformers
 license: apache-2.0
 base_model: mistralai/Mistral-7B-v0.1
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: zephyr-7b-sft-full
   results: []
@@ -18,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-sft-full
 
-This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the generator dataset.
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.9934
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 3.0,
+    "eval_loss": 0.9934042692184448,
+    "eval_runtime": 518.8262,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 29.586,
+    "eval_steps_per_second": 0.116,
     "total_flos": 1361805280542720.0,
     "train_loss": 0.713569560815634,
     "train_runtime": 59769.2599,

config.json

@@ -22,6 +22,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.0,
-    "eval_loss": 0.9419716000556946,
-    "eval_runtime": 916.5084,
+    "epoch": 3.0,
+    "eval_loss": 0.9934042692184448,
+    "eval_runtime": 518.8262,
     "eval_samples": 23109,
-    "eval_samples_per_second": 16.748,
-    "eval_steps_per_second": 0.262
+    "eval_samples_per_second": 29.586,
+    "eval_steps_per_second": 0.116
 }

runs/Jan07_18-01-34_nid002934/events.out.tfevents.1736304558.nid002934.2968402.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f76ac4a10adae44736d5ba77be5e11b9e6540d3a0ed67c26b1b6411e27b329c
+size 359