End of training

README.md

@@ -2,11 +2,15 @@
 license: apache-2.0
 base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
 tags:
+- alignment-handbook
+- trl
+- sft
+- generated_from_trainer
 - trl
 - sft
 - generated_from_trainer
 datasets:
-- generator
+- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: tinyllama-1.1b-chat-sft-full
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-chat-sft-full
 
-This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the generator dataset.
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the HuggingFaceH4/ultrachat_200k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.1566
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9999452264884702,
+    "eval_loss": 1.1566358804702759,
+    "eval_runtime": 1070.8282,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 15.097,
+    "eval_steps_per_second": 1.887,
     "total_flos": 1.8565750537228124e+18,
     "train_loss": 1.1714502769954156,
     "train_runtime": 42415.0484,

config.json

@@ -24,6 +24,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.41.1",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9999452264884702,
+    "eval_loss": 1.1566358804702759,
+    "eval_runtime": 1070.8282,
+    "eval_samples": 23109,
+    "eval_samples_per_second": 15.097,
+    "eval_steps_per_second": 1.887
+}

runs/Jun01_12-55-19_poseidon/events.out.tfevents.1717290161.poseidon.2286092.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7d8cddc7f5fef44f627de3667455cada57964e17d559be73d8b7d86496ef6d5
+size 359