Model save

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+tags:
+- trl
+- generated_from_trainer
+model-index:
+- name: simpo-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. -->
+
+# simpo-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": 0.0036,
+    "train_samples": 59876,
+    "train_samples_per_second": 16407823.488,
+    "train_steps_per_second": 127972.035
+}

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 sha256:38653f5059d741736bca75d8f411120e4a95ce26c800db5fb914f9fe1814ba55
+oid sha256:c3d152ae57b39060dbb13192a52f111fbd8106885aea53f266598d5e96b4b8be
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c076401f04d7465838eef08cd52c168ad4903d015698a9691a5ca4a1bb01cc3
+oid sha256:eb44e764b0cb0abd67a73302c526aa24a8e39066e6d2cdce81d8a4ec09f495fc
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c2672a21ca27ed1e190ae88bf42da2db58679fcd9475741d9c2b204db569ed5
+oid sha256:2739be52198d2302f3c2fbf3341376380ea7f03d30965606db17a54bb887382d
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13fb9fc859e7177a8cb7da8ec0eb144623d62528ef66e3208b0676a4faefe667
+oid sha256:24555c0dd356e631b15663edc77202a3705d6cdcec5eb893949a320fd85c6ac7
 size 1168138808

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9981298423724285,
+    "total_flos": 0.0,
+    "train_loss": 0.0,
+    "train_runtime": 0.0036,
+    "train_samples": 59876,
+    "train_samples_per_second": 16407823.488,
+    "train_steps_per_second": 127972.035
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3746bb6ea253e09235beb3b529f88410997763590c4974f1755b7c2de9b25d11
+oid sha256:d3eef39a256167f50154ecb114d0b67952bcbfc9b54ea84c4e68e956b3dc4e57
 size 7224