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
+- martimfasantos/openai-summarize-tldr
 model-index:
 - name: tinyllama-1.1b-sum-sft-full_LR1e-5
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-sum-sft-full_LR1e-5
 
-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 martimfasantos/openai-summarize-tldr dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.1608
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9996613613274636,
+    "eval_loss": 2.1607718467712402,
+    "eval_runtime": 84.8582,
+    "eval_samples": 6447,
+    "eval_samples_per_second": 15.379,
+    "eval_steps_per_second": 1.933,
     "total_flos": 3.002086743311647e+17,
     "train_loss": 2.1796100780892824,
     "train_runtime": 6613.0875,

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

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9996613613274636,
+    "eval_loss": 2.1607718467712402,
+    "eval_runtime": 84.8582,
+    "eval_samples": 6447,
+    "eval_samples_per_second": 15.379,
+    "eval_steps_per_second": 1.933
+}

runs/Jun30_18-28-24_poseidon/events.out.tfevents.1719778954.poseidon.1025385.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:abaa6b86672188c5293da074b726dd1e28875a0e44fc8c1f569b40b28c99eaa9
+size 359