MHGanainy/16-clusters-imbalanced-14

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # 16-clusters-imbalanced-14
 
 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: 1.6334
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.6334210634231567,
+    "eval_runtime": 29.1651,
+    "eval_samples_per_second": 13.784,
+    "eval_steps_per_second": 1.749,
+    "perplexity": 5.121365298786188,
+    "total_flos": 4.12623063416832e+16,
+    "train_loss": 1.9041457484861346,
+    "train_runtime": 710.2567,
+    "train_samples_per_second": 6.393,
+    "train_steps_per_second": 3.197
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.6334210634231567,
+    "eval_runtime": 29.1651,
+    "eval_samples_per_second": 13.784,
+    "eval_steps_per_second": 1.749,
+    "perplexity": 5.121365298786188
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.12623063416832e+16,
+    "train_loss": 1.9041457484861346,
+    "train_runtime": 710.2567,
+    "train_samples_per_second": 6.393,
+    "train_steps_per_second": 3.197
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2271,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.044033465433729636,
+      "grad_norm": 0.2539120316505432,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.3905,
+      "step": 100
+    },
+    {
+      "epoch": 0.08806693086745927,
+      "grad_norm": 0.18973161280155182,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.3635,
+      "step": 200
+    },
+    {
+      "epoch": 0.13210039630118892,
+      "grad_norm": 0.33373120427131653,
+      "learning_rate": 2e-05,
+      "loss": 2.3032,
+      "step": 300
+    },
+    {
+      "epoch": 0.17613386173491855,
+      "grad_norm": 0.5147584676742554,
+      "learning_rate": 1.9873241569449534e-05,
+      "loss": 2.2076,
+      "step": 400
+    },
+    {
+      "epoch": 0.22016732716864817,
+      "grad_norm": 0.7373507022857666,
+      "learning_rate": 1.9496179817741254e-05,
+      "loss": 2.0565,
+      "step": 500
+    },
+    {
+      "epoch": 0.26420079260237783,
+      "grad_norm": 0.8075642585754395,
+      "learning_rate": 1.8878373896048594e-05,
+      "loss": 1.9512,
+      "step": 600
+    },
+    {
+      "epoch": 0.30823425803610743,
+      "grad_norm": 0.841400146484375,
+      "learning_rate": 1.803548622617526e-05,
+      "loss": 1.9705,
+      "step": 700
+    },
+    {
+      "epoch": 0.3522677234698371,
+      "grad_norm": 0.8930725455284119,
+      "learning_rate": 1.6988885431753952e-05,
+      "loss": 1.9029,
+      "step": 800
+    },
+    {
+      "epoch": 0.3963011889035667,
+      "grad_norm": 1.2450770139694214,
+      "learning_rate": 1.576510460760741e-05,
+      "loss": 1.877,
+      "step": 900
+    },
+    {
+      "epoch": 0.44033465433729635,
+      "grad_norm": 1.1327598094940186,
+      "learning_rate": 1.4395168661056955e-05,
+      "loss": 1.8358,
+      "step": 1000
+    },
+    {
+      "epoch": 0.484368119771026,
+      "grad_norm": 0.9410036206245422,
+      "learning_rate": 1.291380777821046e-05,
+      "loss": 1.794,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5284015852047557,
+      "grad_norm": 1.0832405090332031,
+      "learning_rate": 1.135857695518563e-05,
+      "loss": 1.8101,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5724350506384852,
+      "grad_norm": 0.9094879627227783,
+      "learning_rate": 9.768903915636521e-06,
+      "loss": 1.7717,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6164685160722149,
+      "grad_norm": 1.0884590148925781,
+      "learning_rate": 8.185089551479471e-06,
+      "loss": 1.7574,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6605019815059445,
+      "grad_norm": 1.038459062576294,
+      "learning_rate": 6.64728622733124e-06,
+      "loss": 1.7631,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7045354469396742,
+      "grad_norm": 1.1634732484817505,
+      "learning_rate": 5.194479850364697e-06,
+      "loss": 1.7296,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7485689123734038,
+      "grad_norm": 1.2946337461471558,
+      "learning_rate": 3.8635015118274364e-06,
+      "loss": 1.7421,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7926023778071334,
+      "grad_norm": 1.4221519231796265,
+      "learning_rate": 2.6880937567773903e-06,
+      "loss": 1.7738,
+      "step": 1800
+    },
+    {
+      "epoch": 0.836635843240863,
+      "grad_norm": 1.1156340837478638,
+      "learning_rate": 1.698055153671957e-06,
+      "loss": 1.7244,
+      "step": 1900
+    },
+    {
+      "epoch": 0.8806693086745927,
+      "grad_norm": 1.144950032234192,
+      "learning_rate": 9.184848504139409e-07,
+      "loss": 1.7987,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9247027741083224,
+      "grad_norm": 1.3288109302520752,
+      "learning_rate": 3.6914626863229e-07,
+      "loss": 1.7435,
+      "step": 2100
+    },
+    {
+      "epoch": 0.968736239542052,
+      "grad_norm": 1.1599087715148926,
+      "learning_rate": 6.396606762049674e-08,
+      "loss": 1.7227,
+      "step": 2200
+    },
+    {
+      "epoch": 1.0,
+      "step": 2271,
+      "total_flos": 4.12623063416832e+16,
+      "train_loss": 1.9041457484861346,
+      "train_runtime": 710.2567,
+      "train_samples_per_second": 6.393,
+      "train_steps_per_second": 3.197
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2271,
+  "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": 4.12623063416832e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}