Model save

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+tags:
+- trl
+- generated_from_trainer
+model-index:
+- name: dpo-baseline
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# dpo-baseline
+
+This model was trained from scratch on an unknown dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-07
+- train_batch_size: 2
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9981298423724285,
+    "total_flos": 0.0,
+    "train_loss": 0.0,
+    "train_runtime": 0.0077,
+    "train_samples": 59876,
+    "train_samples_per_second": 7740188.199,
+    "train_steps_per_second": 60369.228
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:143ce7247059f70cbae40310144b4c1ef505849075c4d0b4cfaaf811bb7640f2
+oid sha256:8d78fea78a52793c9140edfa6bcab4f695fa9009d128c9246b1798f4cde12557
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef46a685665f62589832654238fb59df0b3599dfa643f7e4f1867c7930f1adb3
+oid sha256:a2bd9b23dc1253a53e4f9603853ec847eaccbab6e4d1cef812cf51c9af76af22
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:651319f74e8a9c3cb43655934afc8e95159f619f338e4bf3875d030a89d76837
+oid sha256:6a3b49a08763be4cccd53f7f7129fb4a38c2afd672dba564c115c37258896666
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c91f9265c2591e8532440f96cd94cb811889936e7aa73aaab60d99d0a8e137d
+oid sha256:8bfd774a24fdae79b8a27b1718767faab579eb8b39e952877010a9bc55bbd84c
 size 1168138808

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9981298423724285,
+    "total_flos": 0.0,
+    "train_loss": 0.0,
+    "train_runtime": 0.0077,
+    "train_samples": 59876,
+    "train_samples_per_second": 7740188.199,
+    "train_steps_per_second": 60369.228
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12812aaff4b49a56276fe0f6cb8c5b7b39a85ddbc4314179363e4acaa16cd656
+oid sha256:646523fbb2103e127cf623f005ea91ed48f0ecf6c6ce92f43f8b8cea956251d6
 size 7224