End of training

README.md

@@ -2,9 +2,16 @@
 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:
+- ucla-cmllab/WizardLM_evol_instruct_V2_100k-chat-format
+- ucla-cmllab/RedPajama_100k
 model-index:
 - name: tinyllama-sft-wizardlm_evol_instruct_v2-mix
   results: []
@@ -15,7 +22,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-sft-wizardlm_evol_instruct_v2-mix
 
-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 an unknown 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 ucla-cmllab/WizardLM_evol_instruct_V2_100k-chat-format and the ucla-cmllab/RedPajama_100k datasets.
 It achieves the following results on the evaluation set:
 - Loss: 0.7211
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.999360204734485,
+    "eval_loss": 0.7211461067199707,
+    "eval_runtime": 618.7093,
+    "eval_samples": 43000,
+    "eval_samples_per_second": 69.5,
+    "eval_steps_per_second": 2.172,
     "total_flos": 80545737277440.0,
     "train_loss": 0.7457574072476386,
     "train_runtime": 7303.4461,

config.json

@@ -23,6 +23,6 @@
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.40.2",
-  "use_cache": false,
+  "use_cache": true,
   "vocab_size": 32000
 }

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.999360204734485,
+    "eval_loss": 0.7211461067199707,
+    "eval_runtime": 618.7093,
+    "eval_samples": 43000,
+    "eval_samples_per_second": 69.5,
+    "eval_steps_per_second": 2.172
+}

runs/May07_01-10-03_illidan.cs.ucla.edu/events.out.tfevents.1715077455.illidan.cs.ucla.edu.3443160.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e76af6bc52f1f61f60bcf82cd0f6c07eea963ee0d5cd642a836f819494ec544
+size 359