MHGanainy/gpt2-xl-lora-ecthr-random-imbalanced-skewed-cluster-8-id-1

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-1
 
 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: 2.1177
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.1176705360412598,
+    "eval_runtime": 17.6904,
+    "eval_samples_per_second": 21.933,
+    "eval_steps_per_second": 2.77,
+    "perplexity": 8.311752989685214,
+    "total_flos": 4.0811909677056e+16,
+    "train_loss": 2.277450401941086,
+    "train_runtime": 768.7092,
+    "train_samples_per_second": 5.846,
+    "train_steps_per_second": 2.923
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.1176705360412598,
+    "eval_runtime": 17.6904,
+    "eval_samples_per_second": 21.933,
+    "eval_steps_per_second": 2.77,
+    "perplexity": 8.311752989685214
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.0811909677056e+16,
+    "train_loss": 2.277450401941086,
+    "train_runtime": 768.7092,
+    "train_samples_per_second": 5.846,
+    "train_steps_per_second": 2.923
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2247,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04450378282153983,
+      "grad_norm": 0.06308697909116745,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.4617,
+      "step": 100
+    },
+    {
+      "epoch": 0.08900756564307966,
+      "grad_norm": 0.21112093329429626,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.409,
+      "step": 200
+    },
+    {
+      "epoch": 0.13351134846461948,
+      "grad_norm": 0.11030363291501999,
+      "learning_rate": 6e-06,
+      "loss": 2.4205,
+      "step": 300
+    },
+    {
+      "epoch": 0.1780151312861593,
+      "grad_norm": 0.17011764645576477,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.4131,
+      "step": 400
+    },
+    {
+      "epoch": 0.22251891410769917,
+      "grad_norm": 0.22362767159938812,
+      "learning_rate": 1e-05,
+      "loss": 2.3804,
+      "step": 500
+    },
+    {
+      "epoch": 0.26702269692923897,
+      "grad_norm": 0.32320550084114075,
+      "learning_rate": 1.2e-05,
+      "loss": 2.3659,
+      "step": 600
+    },
+    {
+      "epoch": 0.3115264797507788,
+      "grad_norm": 0.32712113857269287,
+      "learning_rate": 1.4e-05,
+      "loss": 2.3029,
+      "step": 700
+    },
+    {
+      "epoch": 0.3560302625723186,
+      "grad_norm": 0.38736435770988464,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.3496,
+      "step": 800
+    },
+    {
+      "epoch": 0.40053404539385845,
+      "grad_norm": 0.4244949221611023,
+      "learning_rate": 1.8e-05,
+      "loss": 2.2843,
+      "step": 900
+    },
+    {
+      "epoch": 0.44503782821539833,
+      "grad_norm": 0.49101588129997253,
+      "learning_rate": 2e-05,
+      "loss": 2.2834,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48954161103693816,
+      "grad_norm": 0.4508339464664459,
+      "learning_rate": 1.9684326170007365e-05,
+      "loss": 2.2931,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5340453938584779,
+      "grad_norm": 0.5122171640396118,
+      "learning_rate": 1.8757234673417892e-05,
+      "loss": 2.2511,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5785491766800178,
+      "grad_norm": 0.6065627932548523,
+      "learning_rate": 1.7277257214927987e-05,
+      "loss": 2.2066,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 0.6051321625709534,
+      "learning_rate": 1.5337831825062507e-05,
+      "loss": 2.2075,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6675567423230975,
+      "grad_norm": 0.5663103461265564,
+      "learning_rate": 1.306140367198221e-05,
+      "loss": 2.1812,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7120605251446372,
+      "grad_norm": 0.5918604135513306,
+      "learning_rate": 1.0591694514444284e-05,
+      "loss": 2.2136,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7565643079661771,
+      "grad_norm": 0.6402628421783447,
+      "learning_rate": 8.084628862194305e-06,
+      "loss": 2.2092,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8010680907877169,
+      "grad_norm": 0.6389249563217163,
+      "learning_rate": 5.698489718530022e-06,
+      "loss": 2.1903,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8455718736092568,
+      "grad_norm": 0.6246665716171265,
+      "learning_rate": 3.583925419926607e-06,
+      "loss": 2.1972,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8900756564307967,
+      "grad_norm": 0.6263630986213684,
+      "learning_rate": 1.874438488565231e-06,
+      "loss": 2.1803,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.636464536190033,
+      "learning_rate": 6.779569818349296e-07,
+      "loss": 2.1867,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9790832220738763,
+      "grad_norm": 0.6826080083847046,
+      "learning_rate": 7.00204796846915e-08,
+      "loss": 2.1696,
+      "step": 2200
+    },
+    {
+      "epoch": 1.0,
+      "step": 2247,
+      "total_flos": 4.0811909677056e+16,
+      "train_loss": 2.277450401941086,
+      "train_runtime": 768.7092,
+      "train_samples_per_second": 5.846,
+      "train_steps_per_second": 2.923
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2247,
+  "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": 4.0811909677056e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}