MHGanainy/16-clusters-imbalanced-13

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # 16-clusters-imbalanced-13
 
 This model is a fine-tuned version of [openai-community/gpt2-xl](https://huggingface.co/openai-community/gpt2-xl) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0455
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.045531749725342,
+    "eval_runtime": 1.3751,
+    "eval_samples_per_second": 13.817,
+    "eval_steps_per_second": 2.182,
+    "perplexity": 7.733269608773069,
+    "total_flos": 1871842128691200.0,
+    "train_loss": 2.217028238240955,
+    "train_runtime": 32.3745,
+    "train_samples_per_second": 6.363,
+    "train_steps_per_second": 3.182
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.045531749725342,
+    "eval_runtime": 1.3751,
+    "eval_samples_per_second": 13.817,
+    "eval_steps_per_second": 2.182,
+    "perplexity": 7.733269608773069
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1871842128691200.0,
+    "train_loss": 2.217028238240955,
+    "train_runtime": 32.3745,
+    "train_samples_per_second": 6.363,
+    "train_steps_per_second": 3.182
+}

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 103,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.27493762969970703,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.2175,
+      "step": 100
+    },
+    {
+      "epoch": 1.0,
+      "step": 103,
+      "total_flos": 1871842128691200.0,
+      "train_loss": 2.217028238240955,
+      "train_runtime": 32.3745,
+      "train_samples_per_second": 6.363,
+      "train_steps_per_second": 3.182
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 103,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 1871842128691200.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}