MHGanainy/16-clusters-balanced-15

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # 16-clusters-balanced-15
 
 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: 1.5769
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.5768862962722778,
+    "eval_runtime": 12.3203,
+    "eval_samples_per_second": 13.798,
+    "eval_steps_per_second": 1.786,
+    "perplexity": 4.839862427586909,
+    "total_flos": 2.11899798257664e+16,
+    "train_loss": 1.9699366064055297,
+    "train_runtime": 363.1708,
+    "train_samples_per_second": 6.421,
+    "train_steps_per_second": 3.211
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.5768862962722778,
+    "eval_runtime": 12.3203,
+    "eval_samples_per_second": 13.798,
+    "eval_steps_per_second": 1.786,
+    "perplexity": 4.839862427586909
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.11899798257664e+16,
+    "train_loss": 1.9699366064055297,
+    "train_runtime": 363.1708,
+    "train_samples_per_second": 6.421,
+    "train_steps_per_second": 3.211
+}

trainer_state.json

@@ -0,0 +1,119 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1166,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.08576329331046312,
+      "grad_norm": 0.1369553655385971,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.3302,
+      "step": 100
+    },
+    {
+      "epoch": 0.17152658662092624,
+      "grad_norm": 0.1438201665878296,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.2922,
+      "step": 200
+    },
+    {
+      "epoch": 0.25728987993138935,
+      "grad_norm": 0.28228944540023804,
+      "learning_rate": 2e-05,
+      "loss": 2.2043,
+      "step": 300
+    },
+    {
+      "epoch": 0.34305317324185247,
+      "grad_norm": 0.5485918521881104,
+      "learning_rate": 1.9349172522833747e-05,
+      "loss": 2.0864,
+      "step": 400
+    },
+    {
+      "epoch": 0.4288164665523156,
+      "grad_norm": 0.592337965965271,
+      "learning_rate": 1.748140537234191e-05,
+      "loss": 2.0281,
+      "step": 500
+    },
+    {
+      "epoch": 0.5145797598627787,
+      "grad_norm": 0.6518536806106567,
+      "learning_rate": 1.4639817385022206e-05,
+      "loss": 1.9181,
+      "step": 600
+    },
+    {
+      "epoch": 0.6003430531732419,
+      "grad_norm": 0.9288659691810608,
+      "learning_rate": 1.1194285269061277e-05,
+      "loss": 1.7875,
+      "step": 700
+    },
+    {
+      "epoch": 0.6861063464837049,
+      "grad_norm": 0.9042983651161194,
+      "learning_rate": 7.593298419364355e-06,
+      "loss": 1.8126,
+      "step": 800
+    },
+    {
+      "epoch": 0.7718696397941681,
+      "grad_norm": 1.000226378440857,
+      "learning_rate": 4.3055810732708584e-06,
+      "loss": 1.8197,
+      "step": 900
+    },
+    {
+      "epoch": 0.8576329331046312,
+      "grad_norm": 0.927306056022644,
+      "learning_rate": 1.7590805879795358e-06,
+      "loss": 1.7825,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 0.9187927842140198,
+      "learning_rate": 2.8526346077935253e-07,
+      "loss": 1.7441,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0,
+      "step": 1166,
+      "total_flos": 2.11899798257664e+16,
+      "train_loss": 1.9699366064055297,
+      "train_runtime": 363.1708,
+      "train_samples_per_second": 6.421,
+      "train_steps_per_second": 3.211
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1166,
+  "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": 2.11899798257664e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}