Model save

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+license: llama3.1
+base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: l3.1-8b-inst-fft-induction-barc-heavy-200k-lr1e-5-ep2
+  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. -->
+
+# l3.1-8b-inst-fft-induction-barc-heavy-200k-lr1e-5-ep2
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B-Instruct) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.2765
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 128
+- total_eval_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.2944        | 1.0   | 1478 | 0.2865          |
+| 0.2388        | 2.0   | 2956 | 0.2765          |
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.1+cu124
+- Datasets 3.0.2
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1086769682448384.0,
+    "train_loss": 0.29042090329370573,
+    "train_runtime": 13931.3179,
+    "train_samples": 189121,
+    "train_samples_per_second": 27.15,
+    "train_steps_per_second": 0.212
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.0.dev0"
+}

runs/Oct27_03-43-11_4e9b761ee88c/events.out.tfevents.1730000622.4e9b761ee88c.24275.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c81b9b93b28d7adc6ebc7ce532857b042c4afc60a10518555686c2dff4e72e
-size 629469
+oid sha256:19d3283ad38c6c975ed2609298b4794e5103c0996e5c21143113288fccdd8c13
+size 630094

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1086769682448384.0,
+    "train_loss": 0.29042090329370573,
+    "train_runtime": 13931.3179,
+    "train_samples": 189121,
+    "train_samples_per_second": 27.15,
+    "train_steps_per_second": 0.212
+}