End of training

README.md

@@ -3,6 +3,8 @@ license: mit
 base_model: openai-community/gpt2
 tags:
 - generated_from_trainer
+metrics:
+- accuracy
 model-index:
 - name: test-clm
   results: []
@@ -14,6 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
 # test-clm
 
 This model is a fine-tuned version of [openai-community/gpt2](https://huggingface.co/openai-community/gpt2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.3172
+- Accuracy: 0.4016
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.401569968863746,
+    "eval_loss": 2.3171780109405518,
+    "eval_runtime": 44.5797,
+    "eval_samples": 2073,
+    "eval_samples_per_second": 46.501,
+    "eval_steps_per_second": 5.832,
+    "perplexity": 10.146999144035705,
+    "total_flos": 863831457792000.0,
+    "train_loss": 2.8772476859714673,
+    "train_runtime": 100.158,
+    "train_samples": 551,
+    "train_samples_per_second": 16.504,
+    "train_steps_per_second": 2.067
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.401569968863746,
+    "eval_loss": 2.3171780109405518,
+    "eval_runtime": 44.5797,
+    "eval_samples": 2073,
+    "eval_samples_per_second": 46.501,
+    "eval_steps_per_second": 5.832,
+    "perplexity": 10.146999144035705
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 863831457792000.0,
+    "train_loss": 2.8772476859714673,
+    "train_runtime": 100.158,
+    "train_samples": 551,
+    "train_samples_per_second": 16.504,
+    "train_steps_per_second": 2.067
+}

trainer_state.json

@@ -0,0 +1,42 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 207,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 3.0,
+      "step": 207,
+      "total_flos": 863831457792000.0,
+      "train_loss": 2.8772476859714673,
+      "train_runtime": 100.158,
+      "train_samples_per_second": 16.504,
+      "train_steps_per_second": 2.067
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 207,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 863831457792000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}