Model save

README.md

@@ -0,0 +1,65 @@
+---
+license: apache-2.0
+base_model: Isotonic/smol_llama-4x220M-MoE
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: smol_llama_x
+  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. -->
+
+# smol_llama_x
+
+This model is a fine-tuned version of [Isotonic/smol_llama-4x220M-MoE](https://huggingface.co/Isotonic/smol_llama-4x220M-MoE) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5906
+- Accuracy: 0.6799
+
+## 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: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine_with_restarts
+- lr_scheduler_warmup_ratio: 0.2
+- num_epochs: 4
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 211  | 1.4545          | 0.6908   |
+| No log        | 2.0   | 422  | 1.4871          | 0.6881   |
+| 1.4748        | 3.0   | 633  | 1.5353          | 0.6841   |
+| 1.4748        | 4.0   | 844  | 1.5906          | 0.6799   |
+
+
+### Framework versions
+
+- Transformers 4.37.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.17.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.6798846867100433,
+    "eval_loss": 1.5906230211257935,
+    "eval_runtime": 69.9412,
+    "eval_samples": 1123,
+    "eval_samples_per_second": 16.056,
+    "eval_steps_per_second": 4.018,
+    "total_flos": 2.3279302128697344e+16,
+    "train_loss": 1.2069585357232115,
+    "train_runtime": 779.6175,
+    "train_samples": 842,
+    "train_samples_per_second": 4.32,
+    "train_steps_per_second": 1.083
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "eval_accuracy": 0.6798846867100433,
+    "eval_loss": 1.5906230211257935,
+    "eval_runtime": 69.9412,
+    "eval_samples": 1123,
+    "eval_samples_per_second": 16.056,
+    "eval_steps_per_second": 4.018
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.37.2",
+  "use_cache": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 4.0,
+    "total_flos": 2.3279302128697344e+16,
+    "train_loss": 1.2069585357232115,
+    "train_runtime": 779.6175,
+    "train_samples": 842,
+    "train_samples_per_second": 4.32,
+    "train_steps_per_second": 1.083
+}

trainer_state.json

@@ -0,0 +1,81 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 844,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6907926418393052,
+      "eval_loss": 1.4545308351516724,
+      "eval_runtime": 71.1157,
+      "eval_samples_per_second": 15.791,
+      "eval_steps_per_second": 3.951,
+      "step": 211
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6881468917656793,
+      "eval_loss": 1.4871423244476318,
+      "eval_runtime": 71.2388,
+      "eval_samples_per_second": 15.764,
+      "eval_steps_per_second": 3.944,
+      "step": 422
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.6221244244890336e-05,
+      "loss": 1.4748,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6840786486403011,
+      "eval_loss": 1.5352827310562134,
+      "eval_runtime": 70.948,
+      "eval_samples_per_second": 15.828,
+      "eval_steps_per_second": 3.961,
+      "step": 633
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6798846867100433,
+      "eval_loss": 1.5906230211257935,
+      "eval_runtime": 70.949,
+      "eval_samples_per_second": 15.828,
+      "eval_steps_per_second": 3.961,
+      "step": 844
+    },
+    {
+      "epoch": 4.0,
+      "step": 844,
+      "total_flos": 2.3279302128697344e+16,
+      "train_loss": 1.2069585357232115,
+      "train_runtime": 779.6175,
+      "train_samples_per_second": 4.32,
+      "train_steps_per_second": 1.083
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6798846867100433,
+      "eval_loss": 1.5906230211257935,
+      "eval_runtime": 69.9412,
+      "eval_samples_per_second": 16.056,
+      "eval_steps_per_second": 4.018,
+      "step": 844
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 844,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "total_flos": 2.3279302128697344e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}