Model save

README.md

@@ -0,0 +1,66 @@
+---
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
+tags:
+- trl
+- sft
+- generated_from_trainer
+datasets:
+- generator
+model-index:
+- name: tinyllama-1.1b-sum-sft-full_final
+  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. -->
+
+# tinyllama-1.1b-sum-sft-full_final
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T](https://huggingface.co/TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.1231
+
+## 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: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.1211        | 0.9997 | 1476 | 2.1252          |
+| 2.0984        | 1.9993 | 2952 | 2.1231          |
+
+
+### Framework versions
+
+- Transformers 4.43.3
+- Pytorch 2.1.2+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.9993227226549273,
+    "total_flos": 6.003537882466222e+17,
+    "train_loss": 2.1295973070591767,
+    "train_runtime": 13069.623,
+    "train_samples": 116722,
+    "train_samples_per_second": 3.614,
+    "train_steps_per_second": 0.226
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.43.3"
+}

runs/Aug10_21-47-05_poseidon/events.out.tfevents.1723326438.poseidon.1993678.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb4451fa7934789e6e0c2403a8e90a9a53032ba18355c3308ac4f7d5f99d946e
-size 130019
+oid sha256:9ecadb0960d4388e755e7c44162b37ccc2e514ef85924874a9f7bf2a7bac8c85
+size 130644

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.9993227226549273,
+    "total_flos": 6.003537882466222e+17,
+    "train_loss": 2.1295973070591767,
+    "train_runtime": 13069.623,
+    "train_samples": 116722,
+    "train_samples_per_second": 3.614,
+    "train_steps_per_second": 0.226
+}