MHGanainy/16-clusters-imbalanced-3

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # 16-clusters-imbalanced-3
 
 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: 1.8535
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.8534812927246094,
+    "eval_runtime": 31.7929,
+    "eval_samples_per_second": 13.745,
+    "eval_steps_per_second": 1.73,
+    "perplexity": 6.381998499391311,
+    "total_flos": 4.13804323012608e+16,
+    "train_loss": 2.0515993006877538,
+    "train_runtime": 708.674,
+    "train_samples_per_second": 6.426,
+    "train_steps_per_second": 3.213
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.8534812927246094,
+    "eval_runtime": 31.7929,
+    "eval_samples_per_second": 13.745,
+    "eval_steps_per_second": 1.73,
+    "perplexity": 6.381998499391311
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.13804323012608e+16,
+    "train_loss": 2.0515993006877538,
+    "train_runtime": 708.674,
+    "train_samples_per_second": 6.426,
+    "train_steps_per_second": 3.213
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2277,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04391743522178305,
+      "grad_norm": 0.08186139911413193,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.3443,
+      "step": 100
+    },
+    {
+      "epoch": 0.0878348704435661,
+      "grad_norm": 0.18966266512870789,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.2978,
+      "step": 200
+    },
+    {
+      "epoch": 0.13175230566534915,
+      "grad_norm": 0.36546170711517334,
+      "learning_rate": 2e-05,
+      "loss": 2.2561,
+      "step": 300
+    },
+    {
+      "epoch": 0.1756697408871322,
+      "grad_norm": 0.4150899052619934,
+      "learning_rate": 1.987400818332026e-05,
+      "loss": 2.1827,
+      "step": 400
+    },
+    {
+      "epoch": 0.21958717610891523,
+      "grad_norm": 0.5007146000862122,
+      "learning_rate": 1.9499207520855085e-05,
+      "loss": 2.1245,
+      "step": 500
+    },
+    {
+      "epoch": 0.2635046113306983,
+      "grad_norm": 0.6546090245246887,
+      "learning_rate": 1.8885042375875825e-05,
+      "loss": 2.1053,
+      "step": 600
+    },
+    {
+      "epoch": 0.30742204655248134,
+      "grad_norm": 0.708943247795105,
+      "learning_rate": 1.8046988704853946e-05,
+      "loss": 2.0842,
+      "step": 700
+    },
+    {
+      "epoch": 0.3513394817742644,
+      "grad_norm": 0.5875030159950256,
+      "learning_rate": 1.700616408868689e-05,
+      "loss": 2.0717,
+      "step": 800
+    },
+    {
+      "epoch": 0.3952569169960474,
+      "grad_norm": 0.60301673412323,
+      "learning_rate": 1.578879560422182e-05,
+      "loss": 2.0419,
+      "step": 900
+    },
+    {
+      "epoch": 0.43917435221783047,
+      "grad_norm": 0.5948824882507324,
+      "learning_rate": 1.4425558944844027e-05,
+      "loss": 2.0202,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4830917874396135,
+      "grad_norm": 0.7956698536872864,
+      "learning_rate": 1.29508054432094e-05,
+      "loss": 2.0113,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5270092226613966,
+      "grad_norm": 0.7147735953330994,
+      "learning_rate": 1.1401696473883086e-05,
+      "loss": 1.9828,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5709266578831796,
+      "grad_norm": 0.8019099235534668,
+      "learning_rate": 9.81726704752115e-06,
+      "loss": 1.9665,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6148440931049627,
+      "grad_norm": 0.7160748243331909,
+      "learning_rate": 8.237442192489225e-06,
+      "loss": 2.0038,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6587615283267457,
+      "grad_norm": 0.7949112057685852,
+      "learning_rate": 6.70203090949157e-06,
+      "loss": 1.977,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7026789635485288,
+      "grad_norm": 0.978585958480835,
+      "learning_rate": 5.249723049907276e-06,
+      "loss": 1.959,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7465963987703118,
+      "grad_norm": 1.2144778966903687,
+      "learning_rate": 3.917114394857796e-06,
+      "loss": 1.9782,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7905138339920948,
+      "grad_norm": 0.7180888652801514,
+      "learning_rate": 2.737784501417702e-06,
+      "loss": 1.95,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8344312692138779,
+      "grad_norm": 0.7736744284629822,
+      "learning_rate": 1.7414505527348436e-06,
+      "loss": 1.9551,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8783487044356609,
+      "grad_norm": 0.7984046936035156,
+      "learning_rate": 9.532185336520706e-07,
+      "loss": 1.9713,
+      "step": 2000
+    },
+    {
+      "epoch": 0.922266139657444,
+      "grad_norm": 0.9639809727668762,
+      "learning_rate": 3.92950600979255e-07,
+      "loss": 1.9249,
+      "step": 2100
+    },
+    {
+      "epoch": 0.966183574879227,
+      "grad_norm": 0.799350917339325,
+      "learning_rate": 7.476458964937316e-08,
+      "loss": 1.9758,
+      "step": 2200
+    },
+    {
+      "epoch": 1.0,
+      "step": 2277,
+      "total_flos": 4.13804323012608e+16,
+      "train_loss": 2.0515993006877538,
+      "train_runtime": 708.674,
+      "train_samples_per_second": 6.426,
+      "train_steps_per_second": 3.213
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2277,
+  "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": 4.13804323012608e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}