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
+- haoranxu/ALMA-Human-Parallel
 model-index:
 - name: tinyllama-1.1b-mt-sft-full
   results: []
@@ -17,7 +21,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinyllama-1.1b-mt-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 haoranxu/ALMA-Human-Parallel dataset.
 It achieves the following results on the evaluation set:
 - Loss: 1.6920
 

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 2.0,
+    "eval_loss": 1.691962480545044,
+    "eval_runtime": 28.3813,
+    "eval_samples": 8016,
+    "eval_samples_per_second": 15.327,
+    "eval_steps_per_second": 1.938,
     "total_flos": 1.502823063832494e+17,
     "train_loss": 1.5822677802652403,
     "train_runtime": 3974.9532,

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

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.9918809201623815,
-    "eval_loss": 1.697079062461853,
-    "eval_runtime": 28.4431,
+    "epoch": 2.0,
+    "eval_loss": 1.691962480545044,
+    "eval_runtime": 28.3813,
     "eval_samples": 8016,
-    "eval_samples_per_second": 15.294,
-    "eval_steps_per_second": 1.934
+    "eval_samples_per_second": 15.327,
+    "eval_steps_per_second": 1.938
 }

runs/May30_13-37-43_poseidon/events.out.tfevents.1717080391.poseidon.2020252.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e18d3491a02f0982d6d10206298203e2d7897e6cf71f3b34968c390d6617ac4
+size 359