MHGanainy/gpt2-xl-lora-ecthr-random-imbalanced-skewed-cluster-8-id-0

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # gpt2-xl-lora-ecthr-random-imbalanced-skewed-cluster-8-id-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: 2.1801
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.18013596534729,
+    "eval_runtime": 9.846,
+    "eval_samples_per_second": 22.141,
+    "eval_steps_per_second": 2.844,
+    "perplexity": 8.847509131596244,
+    "total_flos": 2.42426139967488e+16,
+    "train_loss": 2.3308336977473276,
+    "train_runtime": 355.7712,
+    "train_samples_per_second": 7.508,
+    "train_steps_per_second": 3.755
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.18013596534729,
+    "eval_runtime": 9.846,
+    "eval_samples_per_second": 22.141,
+    "eval_steps_per_second": 2.844,
+    "perplexity": 8.847509131596244
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 2.42426139967488e+16,
+    "train_loss": 2.3308336977473276,
+    "train_runtime": 355.7712,
+    "train_samples_per_second": 7.508,
+    "train_steps_per_second": 3.755
+}

trainer_state.json

@@ -0,0 +1,133 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1336,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0748502994011976,
+      "grad_norm": 0.05376848578453064,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.4256,
+      "step": 100
+    },
+    {
+      "epoch": 0.1497005988023952,
+      "grad_norm": 0.10420384258031845,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.4157,
+      "step": 200
+    },
+    {
+      "epoch": 0.2245508982035928,
+      "grad_norm": 0.10769318789243698,
+      "learning_rate": 6e-06,
+      "loss": 2.4214,
+      "step": 300
+    },
+    {
+      "epoch": 0.2994011976047904,
+      "grad_norm": 0.22069992125034332,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.4348,
+      "step": 400
+    },
+    {
+      "epoch": 0.37425149700598803,
+      "grad_norm": 0.22704525291919708,
+      "learning_rate": 1e-05,
+      "loss": 2.3753,
+      "step": 500
+    },
+    {
+      "epoch": 0.4491017964071856,
+      "grad_norm": 0.26333746314048767,
+      "learning_rate": 1.2e-05,
+      "loss": 2.3588,
+      "step": 600
+    },
+    {
+      "epoch": 0.5239520958083832,
+      "grad_norm": 0.2797996699810028,
+      "learning_rate": 1.4e-05,
+      "loss": 2.3308,
+      "step": 700
+    },
+    {
+      "epoch": 0.5988023952095808,
+      "grad_norm": 0.3928057551383972,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.3049,
+      "step": 800
+    },
+    {
+      "epoch": 0.6736526946107785,
+      "grad_norm": 0.4333711564540863,
+      "learning_rate": 1.8e-05,
+      "loss": 2.2758,
+      "step": 900
+    },
+    {
+      "epoch": 0.7485029940119761,
+      "grad_norm": 0.7743755578994751,
+      "learning_rate": 2e-05,
+      "loss": 2.2787,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8233532934131736,
+      "grad_norm": 0.5272874236106873,
+      "learning_rate": 1.5938201855735017e-05,
+      "loss": 2.2501,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8982035928143712,
+      "grad_norm": 0.5362841486930847,
+      "learning_rate": 7.052448255890958e-06,
+      "loss": 2.2681,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9730538922155688,
+      "grad_norm": 0.5505067110061646,
+      "learning_rate": 5.611666969163243e-07,
+      "loss": 2.1974,
+      "step": 1300
+    },
+    {
+      "epoch": 1.0,
+      "step": 1336,
+      "total_flos": 2.42426139967488e+16,
+      "train_loss": 2.3308336977473276,
+      "train_runtime": 355.7712,
+      "train_samples_per_second": 7.508,
+      "train_steps_per_second": 3.755
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1336,
+  "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": 2.42426139967488e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}