Model save

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: llama3
+base_model: Dynosaur/llama3-8b-math-sft
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: llama3-8b-math-sft-subtask-1
+  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. -->
+
+# llama3-8b-math-sft-subtask-1
+
+This model is a fine-tuned version of [Dynosaur/llama3-8b-math-sft](https://huggingface.co/Dynosaur/llama3-8b-math-sft) 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: 2e-05
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- 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
+
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 3.0.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 2.234764237115228e+17,
+    "train_loss": 0.3796640654083894,
+    "train_runtime": 2677.3586,
+    "train_samples": 67328,
+    "train_samples_per_second": 50.294,
+    "train_steps_per_second": 0.393
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

runs/Sep14_22-33-10_e6586848210e/events.out.tfevents.1726353255.e6586848210e.34904.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:910914a2b86305a5f66c8f6638ed044a22ee8ab1ca031691a96e58f29c741e2c
-size 227038
+oid sha256:cb16ab17a40a7aeff86796d5874470140a495860b3fb403f92fe9052b9a4c654
+size 227392

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 2.234764237115228e+17,
+    "train_loss": 0.3796640654083894,
+    "train_runtime": 2677.3586,
+    "train_samples": 67328,
+    "train_samples_per_second": 50.294,
+    "train_steps_per_second": 0.393
+}