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_C10k_k100
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: roneneldan/TinyStories
+      type: roneneldan/TinyStories
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.5429091526514649
 ---
 
 <!-- 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_C10k_k100
 
-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: 1.8957
 - Accuracy: 0.5429

all_results.json

@@ -0,0 +1,33 @@
+{
+    "MSE": 0.0,
+    "MSE/layer0": 0.0,
+    "dead_code_fraction": 1.0,
+    "dead_code_fraction/layer0": 1.0,
+    "epoch": 1.04,
+    "eval_MSE/layer0": 611.1571513346564,
+    "eval_accuracy": 0.5429091526514649,
+    "eval_dead_code_fraction/layer0": 0.0,
+    "eval_input_norm/layer0": 31.997479090978388,
+    "eval_loss": 1.89570152759552,
+    "eval_multicode_k": 1,
+    "eval_output_norm/layer0": 15.087154228553715,
+    "eval_runtime": 73.291,
+    "eval_samples": 4623,
+    "eval_samples_per_second": 63.077,
+    "eval_steps_per_second": 7.886,
+    "input_norm": 0.0,
+    "input_norm/layer0": 0.0,
+    "loss": 2.0762174885749816,
+    "max_norm": 79.63946533203125,
+    "max_norm/layer0": 79.63946533203125,
+    "mean_norm": 68.03947448730469,
+    "mean_norm/layer0": 68.03947448730469,
+    "multicode_k": 1,
+    "output_norm": 0.0,
+    "output_norm/layer0": 0.0,
+    "perplexity": 6.657216988297924,
+    "runtime": 12054.7701,
+    "samples_per_second": 39.818,
+    "steps_per_second": 0.83,
+    "train_samples": 459760
+}

eval_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.04,
+    "eval_MSE/layer0": 611.1571513346564,
+    "eval_accuracy": 0.5429091526514649,
+    "eval_dead_code_fraction/layer0": 0.0,
+    "eval_input_norm/layer0": 31.997479090978388,
+    "eval_loss": 1.89570152759552,
+    "eval_multicode_k": 1,
+    "eval_output_norm/layer0": 15.087154228553715,
+    "eval_runtime": 73.291,
+    "eval_samples": 4623,
+    "eval_samples_per_second": 63.077,
+    "eval_steps_per_second": 7.886,
+    "perplexity": 6.657216988297924
+}

train_results.json

@@ -0,0 +1,21 @@
+{
+    "MSE": 0.0,
+    "MSE/layer0": 0.0,
+    "dead_code_fraction": 1.0,
+    "dead_code_fraction/layer0": 1.0,
+    "epoch": 1.04,
+    "input_norm": 0.0,
+    "input_norm/layer0": 0.0,
+    "loss": 2.0762174885749816,
+    "max_norm": 79.63946533203125,
+    "max_norm/layer0": 79.63946533203125,
+    "mean_norm": 68.03947448730469,
+    "mean_norm/layer0": 68.03947448730469,
+    "multicode_k": 1,
+    "output_norm": 0.0,
+    "output_norm/layer0": 0.0,
+    "runtime": 12054.7701,
+    "samples_per_second": 39.818,
+    "steps_per_second": 0.83,
+    "train_samples": 459760
+}