MHGanainy/16-clusters-imbalanced-0

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # 16-clusters-imbalanced-0
 
 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: 1.9280
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.9279512166976929,
+    "eval_runtime": 9.703,
+    "eval_samples_per_second": 13.604,
+    "eval_steps_per_second": 1.752,
+    "perplexity": 6.875409577572064,
+    "total_flos": 1.80550985908224e+16,
+    "train_loss": 2.145273788114429,
+    "train_runtime": 315.4776,
+    "train_samples_per_second": 6.298,
+    "train_steps_per_second": 3.151
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.9279512166976929,
+    "eval_runtime": 9.703,
+    "eval_samples_per_second": 13.604,
+    "eval_steps_per_second": 1.752,
+    "perplexity": 6.875409577572064
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 1.80550985908224e+16,
+    "train_loss": 2.145273788114429,
+    "train_runtime": 315.4776,
+    "train_samples_per_second": 6.298,
+    "train_steps_per_second": 3.151
+}

trainer_state.json

@@ -0,0 +1,105 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 994,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1006036217303823,
+      "grad_norm": 0.12222979962825775,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.3372,
+      "step": 100
+    },
+    {
+      "epoch": 0.2012072434607646,
+      "grad_norm": 0.1821768581867218,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.3306,
+      "step": 200
+    },
+    {
+      "epoch": 0.30181086519114686,
+      "grad_norm": 0.3504989445209503,
+      "learning_rate": 2e-05,
+      "loss": 2.2636,
+      "step": 300
+    },
+    {
+      "epoch": 0.4024144869215292,
+      "grad_norm": 0.48155415058135986,
+      "learning_rate": 1.8992785750046866e-05,
+      "loss": 2.1763,
+      "step": 400
+    },
+    {
+      "epoch": 0.5030181086519114,
+      "grad_norm": 0.4961913526058197,
+      "learning_rate": 1.617403910924919e-05,
+      "loss": 2.1291,
+      "step": 500
+    },
+    {
+      "epoch": 0.6036217303822937,
+      "grad_norm": 0.6081059575080872,
+      "learning_rate": 1.2111576434330767e-05,
+      "loss": 2.0842,
+      "step": 600
+    },
+    {
+      "epoch": 0.704225352112676,
+      "grad_norm": 0.6098687648773193,
+      "learning_rate": 7.623751784507707e-06,
+      "loss": 2.0605,
+      "step": 700
+    },
+    {
+      "epoch": 0.8048289738430584,
+      "grad_norm": 0.7064446806907654,
+      "learning_rate": 3.6146053474985565e-06,
+      "loss": 2.018,
+      "step": 800
+    },
+    {
+      "epoch": 0.9054325955734407,
+      "grad_norm": 0.6957663297653198,
+      "learning_rate": 8.917510076042058e-07,
+      "loss": 2.0279,
+      "step": 900
+    },
+    {
+      "epoch": 1.0,
+      "step": 994,
+      "total_flos": 1.80550985908224e+16,
+      "train_loss": 2.145273788114429,
+      "train_runtime": 315.4776,
+      "train_samples_per_second": 6.298,
+      "train_steps_per_second": 3.151
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 994,
+  "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": 1.80550985908224e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}