End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: TinyLlama/TinyLlama-1.1B-step-50K-105b
 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: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # zephyr-7b-sft-full
 
-This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-step-50K-105b](https://huggingface.co/TinyLlama/TinyLlama-1.1B-step-50K-105b) on the generator dataset.
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-step-50K-105b](https://huggingface.co/TinyLlama/TinyLlama-1.1B-step-50K-105b) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.3203
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.320330262184143,
+    "eval_runtime": 948.5474,
+    "eval_samples": 124719,
+    "eval_samples_per_second": 92.359,
+    "eval_steps_per_second": 5.773,
     "total_flos": 66190143651840.0,
     "train_loss": 1.3573657579367173,
     "train_runtime": 8062.8425,

config.json

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.0320301055908203,
-    "eval_runtime": 4528.944,
+    "eval_loss": 1.320330262184143,
+    "eval_runtime": 948.5474,
     "eval_samples": 124719,
-    "eval_samples_per_second": 18.466,
-    "eval_steps_per_second": 1.154
+    "eval_samples_per_second": 92.359,
+    "eval_steps_per_second": 5.773
 }

runs/Jul02_08-04-09_ishant-gpu/events.out.tfevents.1719917538.ishant-gpu.55464.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a7630fb01e0e59ab7becbe68e05fa2b5653a64db6a048d248aa45deba1a774
+size 359