MHGanainy/16-clusters-imbalanced-11

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # 16-clusters-imbalanced-11
 
 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: 1.7617
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.7617119550704956,
+    "eval_runtime": 10.1058,
+    "eval_samples_per_second": 13.754,
+    "eval_steps_per_second": 1.781,
+    "perplexity": 5.822396548451661,
+    "total_flos": 1.17580762841088e+16,
+    "train_loss": 2.0752741063396565,
+    "train_runtime": 203.1277,
+    "train_samples_per_second": 6.37,
+    "train_steps_per_second": 3.185
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.7617119550704956,
+    "eval_runtime": 10.1058,
+    "eval_samples_per_second": 13.754,
+    "eval_steps_per_second": 1.781,
+    "perplexity": 5.822396548451661
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.17580762841088e+16,
+    "train_loss": 2.0752741063396565,
+    "train_runtime": 203.1277,
+    "train_samples_per_second": 6.37,
+    "train_steps_per_second": 3.185
+}

trainer_state.json

@@ -0,0 +1,84 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 647,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1545595054095827,
+      "grad_norm": 0.2346014678478241,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.2952,
+      "step": 100
+    },
+    {
+      "epoch": 0.3091190108191654,
+      "grad_norm": 0.17673051357269287,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.2563,
+      "step": 200
+    },
+    {
+      "epoch": 0.46367851622874806,
+      "grad_norm": 0.30051079392433167,
+      "learning_rate": 2e-05,
+      "loss": 2.1728,
+      "step": 300
+    },
+    {
+      "epoch": 0.6182380216383307,
+      "grad_norm": 0.4798201024532318,
+      "learning_rate": 1.617403910924919e-05,
+      "loss": 2.0259,
+      "step": 400
+    },
+    {
+      "epoch": 0.7727975270479135,
+      "grad_norm": 0.611906886100769,
+      "learning_rate": 7.623751784507707e-06,
+      "loss": 1.9245,
+      "step": 500
+    },
+    {
+      "epoch": 0.9273570324574961,
+      "grad_norm": 0.652037501335144,
+      "learning_rate": 8.917510076042058e-07,
+      "loss": 1.8847,
+      "step": 600
+    },
+    {
+      "epoch": 1.0,
+      "step": 647,
+      "total_flos": 1.17580762841088e+16,
+      "train_loss": 2.0752741063396565,
+      "train_runtime": 203.1277,
+      "train_samples_per_second": 6.37,
+      "train_steps_per_second": 3.185
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 647,
+  "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": 1.17580762841088e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}