MHGanainy/gpt2-xl-lora-ecthr-random-imbalanced-uniform-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-uniform-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: 2.0565
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.0564818382263184,
+    "eval_runtime": 17.4644,
+    "eval_samples_per_second": 22.217,
+    "eval_steps_per_second": 2.806,
+    "perplexity": 7.818414918958686,
+    "total_flos": 4.092853911552e+16,
+    "train_loss": 2.2367699406228705,
+    "train_runtime": 595.6661,
+    "train_samples_per_second": 7.544,
+    "train_steps_per_second": 3.772
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.0564818382263184,
+    "eval_runtime": 17.4644,
+    "eval_samples_per_second": 22.217,
+    "eval_steps_per_second": 2.806,
+    "perplexity": 7.818414918958686
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.092853911552e+16,
+    "train_loss": 2.2367699406228705,
+    "train_runtime": 595.6661,
+    "train_samples_per_second": 7.544,
+    "train_steps_per_second": 3.772
+}

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": 0.10439448803663254,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.4616,
+      "step": 100
+    },
+    {
+      "epoch": 0.08900756564307966,
+      "grad_norm": 0.3315769135951996,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.4064,
+      "step": 200
+    },
+    {
+      "epoch": 0.13351134846461948,
+      "grad_norm": 0.17002928256988525,
+      "learning_rate": 6e-06,
+      "loss": 2.4087,
+      "step": 300
+    },
+    {
+      "epoch": 0.1780151312861593,
+      "grad_norm": 0.2480064183473587,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.391,
+      "step": 400
+    },
+    {
+      "epoch": 0.22251891410769917,
+      "grad_norm": 0.31948867440223694,
+      "learning_rate": 1e-05,
+      "loss": 2.3498,
+      "step": 500
+    },
+    {
+      "epoch": 0.26702269692923897,
+      "grad_norm": 0.44854363799095154,
+      "learning_rate": 1.2e-05,
+      "loss": 2.3259,
+      "step": 600
+    },
+    {
+      "epoch": 0.3115264797507788,
+      "grad_norm": 0.4176611602306366,
+      "learning_rate": 1.4e-05,
+      "loss": 2.2623,
+      "step": 700
+    },
+    {
+      "epoch": 0.3560302625723186,
+      "grad_norm": 0.5019781589508057,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.3104,
+      "step": 800
+    },
+    {
+      "epoch": 0.40053404539385845,
+      "grad_norm": 0.5389865040779114,
+      "learning_rate": 1.8e-05,
+      "loss": 2.2427,
+      "step": 900
+    },
+    {
+      "epoch": 0.44503782821539833,
+      "grad_norm": 0.6703211665153503,
+      "learning_rate": 2e-05,
+      "loss": 2.237,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48954161103693816,
+      "grad_norm": 0.5000207424163818,
+      "learning_rate": 1.9684326170007365e-05,
+      "loss": 2.2528,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5340453938584779,
+      "grad_norm": 0.5917981266975403,
+      "learning_rate": 1.8757234673417892e-05,
+      "loss": 2.2048,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5785491766800178,
+      "grad_norm": 0.7215768098831177,
+      "learning_rate": 1.7277257214927987e-05,
+      "loss": 2.1566,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6230529595015576,
+      "grad_norm": 0.7531530857086182,
+      "learning_rate": 1.5337831825062507e-05,
+      "loss": 2.1577,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6675567423230975,
+      "grad_norm": 0.6708113551139832,
+      "learning_rate": 1.306140367198221e-05,
+      "loss": 2.1245,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7120605251446372,
+      "grad_norm": 0.7053218483924866,
+      "learning_rate": 1.0591694514444284e-05,
+      "loss": 2.1642,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7565643079661771,
+      "grad_norm": 0.740707516670227,
+      "learning_rate": 8.084628862194305e-06,
+      "loss": 2.157,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8010680907877169,
+      "grad_norm": 0.7268549203872681,
+      "learning_rate": 5.698489718530022e-06,
+      "loss": 2.141,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8455718736092568,
+      "grad_norm": 0.7531184554100037,
+      "learning_rate": 3.583925419926607e-06,
+      "loss": 2.1528,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8900756564307967,
+      "grad_norm": 0.7767016291618347,
+      "learning_rate": 1.874438488565231e-06,
+      "loss": 2.1218,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9345794392523364,
+      "grad_norm": 0.7806171178817749,
+      "learning_rate": 6.779569818349296e-07,
+      "loss": 2.1313,
+      "step": 2100
+    },
+    {
+      "epoch": 0.9790832220738763,
+      "grad_norm": 0.8500974178314209,
+      "learning_rate": 7.00204796846915e-08,
+      "loss": 2.111,
+      "step": 2200
+    },
+    {
+      "epoch": 1.0,
+      "step": 2247,
+      "total_flos": 4.092853911552e+16,
+      "train_loss": 2.2367699406228705,
+      "train_runtime": 595.6661,
+      "train_samples_per_second": 7.544,
+      "train_steps_per_second": 3.772
+    }
+  ],
+  "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": 4.092853911552e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}