End of training

README.md

@@ -1,11 +1,24 @@
 ---
+base_model: roneneldan/TinyStories-1Layer-21M
 tags:
 - generated_from_trainer
+datasets:
+- roneneldan/TinyStories
 metrics:
 - accuracy
 model-index:
 - name: tinystories_1layer_attn_mlp_C25k_k16_mse_weighted
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: roneneldan/TinyStories
+      type: roneneldan/TinyStories
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5193506309245984
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -13,7 +26,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # tinystories_1layer_attn_mlp_C25k_k16_mse_weighted
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+This model is a fine-tuned version of [roneneldan/TinyStories-1Layer-21M](https://huggingface.co/roneneldan/TinyStories-1Layer-21M) on the roneneldan/TinyStories dataset.
 It achieves the following results on the evaluation set:
 - Loss: 2.0353
 - Accuracy: 0.5194

all_results.json

@@ -0,0 +1,31 @@
+{
+    "MSE": 0.0,
+    "MSE/layer0": 0.0,
+    "dead_code_fraction": 1.0,
+    "dead_code_fraction/layer0": 1.0,
+    "epoch": 2.04,
+    "eval_MSE/layer0": 501.8128262733759,
+    "eval_accuracy": 0.5193506309245984,
+    "eval_dead_code_fraction/layer0": 0.16395,
+    "eval_input_norm/layer0": 31.998895487949337,
+    "eval_loss": 2.0353407859802246,
+    "eval_multicode_k": 1,
+    "eval_output_norm/layer0": 22.80092038433711,
+    "eval_runtime": 159.0824,
+    "eval_samples_per_second": 29.06,
+    "eval_steps_per_second": 1.817,
+    "input_norm": 0.0,
+    "input_norm/layer0": 0.0,
+    "loss": 2.205516522693634,
+    "max_norm": 220.5869903564453,
+    "max_norm/layer0": 220.5869903564453,
+    "mean_norm": 69.14492416381836,
+    "mean_norm/layer0": 69.14492416381836,
+    "multicode_k": 1,
+    "output_norm": 0.0,
+    "output_norm/layer0": 0.0,
+    "perplexity": 7.6548603501181,
+    "runtime": 15654.0479,
+    "samples_per_second": 61.326,
+    "steps_per_second": 0.639
+}

eval_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.04,
+    "eval_MSE/layer0": 501.8128262733759,
+    "eval_accuracy": 0.5193506309245984,
+    "eval_dead_code_fraction/layer0": 0.16395,
+    "eval_input_norm/layer0": 31.998895487949337,
+    "eval_loss": 2.0353407859802246,
+    "eval_multicode_k": 1,
+    "eval_output_norm/layer0": 22.80092038433711,
+    "eval_runtime": 159.0824,
+    "eval_samples_per_second": 29.06,
+    "eval_steps_per_second": 1.817,
+    "perplexity": 7.6548603501181
+}

train_results.json

@@ -0,0 +1,20 @@
+{
+    "MSE": 0.0,
+    "MSE/layer0": 0.0,
+    "dead_code_fraction": 1.0,
+    "dead_code_fraction/layer0": 1.0,
+    "epoch": 2.04,
+    "input_norm": 0.0,
+    "input_norm/layer0": 0.0,
+    "loss": 2.205516522693634,
+    "max_norm": 220.5869903564453,
+    "max_norm/layer0": 220.5869903564453,
+    "mean_norm": 69.14492416381836,
+    "mean_norm/layer0": 69.14492416381836,
+    "multicode_k": 1,
+    "output_norm": 0.0,
+    "output_norm/layer0": 0.0,
+    "runtime": 15654.0479,
+    "samples_per_second": 61.326,
+    "steps_per_second": 0.639
+}