Model save

README.md

@@ -0,0 +1,68 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: EleutherAI/pythia-160m
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: pythia-160m-tulu-v2-mix
+  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. -->
+
+# pythia-160m-tulu-v2-mix
+
+This model is a fine-tuned version of [EleutherAI/pythia-160m](https://huggingface.co/EleutherAI/pythia-160m) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.4481
+
+## 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: 0.0002
+- train_batch_size: 16
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 3
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.9976        | 0.9999 | 2548 | 2.8137          |
+| 2.5794        | 1.9998 | 5096 | 2.4651          |
+| 2.5149        | 2.9997 | 7644 | 2.4481          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.6
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.999705680368881,
+    "total_flos": 5.656192905023324e+17,
+    "train_loss": 2.742037247513552,
+    "train_runtime": 9381.445,
+    "train_samples": 326149,
+    "train_samples_per_second": 104.296,
+    "train_steps_per_second": 0.815
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.44.2",
+  "use_cache": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.999705680368881,
+    "total_flos": 5.656192905023324e+17,
+    "train_loss": 2.742037247513552,
+    "train_runtime": 9381.445,
+    "train_samples": 326149,
+    "train_samples_per_second": 104.296,
+    "train_steps_per_second": 0.815
+}