Model save

README.md

@@ -0,0 +1,61 @@
+---
+license: apache-2.0
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+tags:
+- generated_from_trainer
+model-index:
+- name: TinyLlama-1.1B-Chat-v1.0-reasoning-sft-full
+  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-Chat-v1.0-reasoning-sft-full
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.8959
+
+## 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: 2
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 10
+- total_train_batch_size: 40
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.9354        | 0.22  | 92   | 0.9211          |
+| 0.8646        | 1.22  | 185  | 0.8959          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.3.0.dev20231228+rocm5.7
+- Datasets 2.14.6
+- Tokenizers 0.14.1

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.22,
+    "eval_loss": 0.8958835601806641,
+    "eval_runtime": 48.8992,
+    "eval_samples": 956,
+    "eval_samples_per_second": 19.55,
+    "eval_steps_per_second": 9.775,
+    "train_loss": 0.9214719901213775,
+    "train_runtime": 5680.6096,
+    "train_samples": 16676,
+    "train_samples_per_second": 5.871,
+    "train_steps_per_second": 0.146
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.22,
+    "eval_loss": 0.8958835601806641,
+    "eval_runtime": 48.8992,
+    "eval_samples": 956,
+    "eval_samples_per_second": 19.55,
+    "eval_steps_per_second": 9.775
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.35.0"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5b4a8b00e80da4a4f477d0a7fadf3070997cbe3c773723ea5ec93d52f5f1c18
+oid sha256:edfe5952a27c911cfcc36d4ba07c5433974e54140263c4f1aaba3f9835aeaf0b
 size 2200119864

runs/Jan03_13-41-04_ml-xtx-machine/events.out.tfevents.1704285709.ml-xtx-machine.9179.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3f72a20d3560b0e8f14e7b80e8ccc8971fa93459276d19b4cf4ff5b7be87321
-size 5768
+oid sha256:998528459a796a25c2f34e5f5a1e71c423b7115a4c44957d3eca7b9a9f0951ee
+size 6864

runs/Jan03_13-41-04_ml-xtx-machine/events.out.tfevents.1704291439.ml-xtx-machine.9179.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5912287f3c1afa9010418b07d3eba33f811583f5f72ddc65c7768150edeb4e74
+size 359

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.22,
+    "train_loss": 0.9214719901213775,
+    "train_runtime": 5680.6096,
+    "train_samples": 16676,
+    "train_samples_per_second": 5.871,
+    "train_steps_per_second": 0.146
+}

trainer_state.json

@@ -0,0 +1,104 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.2213960182297914,
+  "eval_steps": 500,
+  "global_step": 185,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.9999928710990414e-05,
+      "loss": 1.3025,
+      "step": 1
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9971497912068014e-05,
+      "loss": 1.0331,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9886154122075344e-05,
+      "loss": 0.9573,
+      "step": 40
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.974445512526336e-05,
+      "loss": 0.9535,
+      "step": 60
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 1.954720866508546e-05,
+      "loss": 0.9354,
+      "step": 80
+    },
+    {
+      "epoch": 0.22,
+      "eval_loss": 0.9210964441299438,
+      "eval_runtime": 48.914,
+      "eval_samples_per_second": 19.544,
+      "eval_steps_per_second": 9.772,
+      "step": 92
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 1.9295539128732096e-05,
+      "loss": 0.8984,
+      "step": 100
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 1.899088113765426e-05,
+      "loss": 0.8842,
+      "step": 120
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 1.863497136962213e-05,
+      "loss": 0.8736,
+      "step": 140
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 1.8229838658936566e-05,
+      "loss": 0.8752,
+      "step": 160
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 1.7777792431226384e-05,
+      "loss": 0.8646,
+      "step": 180
+    },
+    {
+      "epoch": 1.22,
+      "eval_loss": 0.8958887457847595,
+      "eval_runtime": 48.9138,
+      "eval_samples_per_second": 19.545,
+      "eval_steps_per_second": 9.772,
+      "step": 185
+    },
+    {
+      "epoch": 1.22,
+      "step": 185,
+      "total_flos": 9.424742439400243e+16,
+      "train_loss": 0.9214719901213775,
+      "train_runtime": 5680.6096,
+      "train_samples_per_second": 5.871,
+      "train_steps_per_second": 0.146
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 832,
+  "num_train_epochs": 2,
+  "save_steps": 40,
+  "total_flos": 9.424742439400243e+16,
+  "trial_name": null,
+  "trial_params": null
+}