MHGanainy/16-clusters-balanced-10

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # 16-clusters-balanced-10
 
 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: 1.8874
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.887420654296875,
+    "eval_runtime": 30.0268,
+    "eval_samples_per_second": 13.788,
+    "eval_steps_per_second": 1.732,
+    "perplexity": 6.602317041368738,
+    "total_flos": 7.32108351012864e+16,
+    "train_loss": 2.103881771554424,
+    "train_runtime": 1250.9785,
+    "train_samples_per_second": 6.441,
+    "train_steps_per_second": 3.221
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.887420654296875,
+    "eval_runtime": 30.0268,
+    "eval_samples_per_second": 13.788,
+    "eval_steps_per_second": 1.732,
+    "perplexity": 6.602317041368738
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 7.32108351012864e+16,
+    "train_loss": 2.103881771554424,
+    "train_runtime": 1250.9785,
+    "train_samples_per_second": 6.441,
+    "train_steps_per_second": 3.221
+}

trainer_state.json

@@ -0,0 +1,322 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4029,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02482005460412013,
+      "grad_norm": 0.13781653344631195,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.4042,
+      "step": 100
+    },
+    {
+      "epoch": 0.04964010920824026,
+      "grad_norm": 0.16998766362667084,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 2.3579,
+      "step": 200
+    },
+    {
+      "epoch": 0.07446016381236038,
+      "grad_norm": 0.2991155982017517,
+      "learning_rate": 2e-05,
+      "loss": 2.2975,
+      "step": 300
+    },
+    {
+      "epoch": 0.09928021841648052,
+      "grad_norm": 0.4158655107021332,
+      "learning_rate": 1.9964532702725803e-05,
+      "loss": 2.2728,
+      "step": 400
+    },
+    {
+      "epoch": 0.12410027302060064,
+      "grad_norm": 0.4808669984340668,
+      "learning_rate": 1.9858382396738395e-05,
+      "loss": 2.2344,
+      "step": 500
+    },
+    {
+      "epoch": 0.14892032762472077,
+      "grad_norm": 0.5469107031822205,
+      "learning_rate": 1.9682302054929414e-05,
+      "loss": 2.194,
+      "step": 600
+    },
+    {
+      "epoch": 0.17374038222884092,
+      "grad_norm": 0.5828746557235718,
+      "learning_rate": 1.943754069606428e-05,
+      "loss": 2.1653,
+      "step": 700
+    },
+    {
+      "epoch": 0.19856043683296104,
+      "grad_norm": 0.5619407892227173,
+      "learning_rate": 1.9125834524918215e-05,
+      "loss": 2.1805,
+      "step": 800
+    },
+    {
+      "epoch": 0.22338049143708116,
+      "grad_norm": 0.6732242107391357,
+      "learning_rate": 1.8749394616578068e-05,
+      "loss": 2.1666,
+      "step": 900
+    },
+    {
+      "epoch": 0.2482005460412013,
+      "grad_norm": 0.6464433670043945,
+      "learning_rate": 1.8310891232270827e-05,
+      "loss": 2.1392,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2730206006453214,
+      "grad_norm": 0.6885677576065063,
+      "learning_rate": 1.781343487797389e-05,
+      "loss": 2.1322,
+      "step": 1100
+    },
+    {
+      "epoch": 0.29784065524944153,
+      "grad_norm": 0.7929017543792725,
+      "learning_rate": 1.7260554240167017e-05,
+      "loss": 2.1284,
+      "step": 1200
+    },
+    {
+      "epoch": 0.32266070985356166,
+      "grad_norm": 0.7100329399108887,
+      "learning_rate": 1.665617115523785e-05,
+      "loss": 2.122,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34748076445768183,
+      "grad_norm": 0.7074483633041382,
+      "learning_rate": 1.6004572790094535e-05,
+      "loss": 2.1137,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37230081906180196,
+      "grad_norm": 0.769305408000946,
+      "learning_rate": 1.531038123132105e-05,
+      "loss": 2.0861,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3971208736659221,
+      "grad_norm": 0.7742049098014832,
+      "learning_rate": 1.4578520698593441e-05,
+      "loss": 2.1159,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4219409282700422,
+      "grad_norm": 0.78520268201828,
+      "learning_rate": 1.3814182614927217e-05,
+      "loss": 2.0698,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4467609828741623,
+      "grad_norm": 0.6703968644142151,
+      "learning_rate": 1.3022788781528653e-05,
+      "loss": 2.0624,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47158103747828245,
+      "grad_norm": 0.8425729274749756,
+      "learning_rate": 1.220995291846777e-05,
+      "loss": 2.0517,
+      "step": 1900
+    },
+    {
+      "epoch": 0.4964010920824026,
+      "grad_norm": 0.7934256196022034,
+      "learning_rate": 1.1381440843982634e-05,
+      "loss": 2.0424,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5212211466865228,
+      "grad_norm": 0.8032339811325073,
+      "learning_rate": 1.0543129574881446e-05,
+      "loss": 2.0675,
+      "step": 2100
+    },
+    {
+      "epoch": 0.5460412012906428,
+      "grad_norm": 0.8439006805419922,
+      "learning_rate": 9.700965638162112e-06,
+      "loss": 2.0462,
+      "step": 2200
+    },
+    {
+      "epoch": 0.570861255894763,
+      "grad_norm": 0.7389697432518005,
+      "learning_rate": 8.860922889564078e-06,
+      "loss": 2.0415,
+      "step": 2300
+    },
+    {
+      "epoch": 0.5956813104988831,
+      "grad_norm": 1.0543524026870728,
+      "learning_rate": 8.028960138264857e-06,
+      "loss": 2.0374,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6205013651030032,
+      "grad_norm": 0.8730601072311401,
+      "learning_rate": 7.21097887830873e-06,
+      "loss": 2.0446,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6453214197071233,
+      "grad_norm": 0.9236976504325867,
+      "learning_rate": 6.4127814265980095e-06,
+      "loss": 2.0229,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6701414743112435,
+      "grad_norm": 1.163818120956421,
+      "learning_rate": 5.640029764393366e-06,
+      "loss": 2.0498,
+      "step": 2700
+    },
+    {
+      "epoch": 0.6949615289153637,
+      "grad_norm": 0.8231688737869263,
+      "learning_rate": 4.8982053742793025e-06,
+      "loss": 2.0217,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7197815835194837,
+      "grad_norm": 0.72389817237854,
+      "learning_rate": 4.1925703574897115e-06,
+      "loss": 2.0483,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7446016381236039,
+      "grad_norm": 0.7828938364982605,
+      "learning_rate": 3.528130107406099e-06,
+      "loss": 2.0134,
+      "step": 3000
+    },
+    {
+      "epoch": 0.769421692727724,
+      "grad_norm": 0.9030676484107971,
+      "learning_rate": 2.909597804002603e-06,
+      "loss": 2.0427,
+      "step": 3100
+    },
+    {
+      "epoch": 0.7942417473318442,
+      "grad_norm": 1.255286693572998,
+      "learning_rate": 2.341360981094921e-06,
+      "loss": 2.043,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8190618019359642,
+      "grad_norm": 0.7835339307785034,
+      "learning_rate": 1.8274504035470942e-06,
+      "loss": 2.0554,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8438818565400844,
+      "grad_norm": 0.8897650241851807,
+      "learning_rate": 1.3715114752043746e-06,
+      "loss": 2.0773,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8687019111442045,
+      "grad_norm": 1.0972046852111816,
+      "learning_rate": 9.767783803688414e-07,
+      "loss": 2.0435,
+      "step": 3500
+    },
+    {
+      "epoch": 0.8935219657483247,
+      "grad_norm": 0.794748067855835,
+      "learning_rate": 6.460511422441984e-07,
+      "loss": 2.0153,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9183420203524447,
+      "grad_norm": 0.9059362411499023,
+      "learning_rate": 3.8167576108468994e-07,
+      "loss": 2.0554,
+      "step": 3700
+    },
+    {
+      "epoch": 0.9431620749565649,
+      "grad_norm": 0.8400096893310547,
+      "learning_rate": 1.855275729374284e-07,
+      "loss": 2.0414,
+      "step": 3800
+    },
+    {
+      "epoch": 0.9679821295606851,
+      "grad_norm": 0.8562043309211731,
+      "learning_rate": 5.89979470221802e-08,
+      "loss": 2.0197,
+      "step": 3900
+    },
+    {
+      "epoch": 0.9928021841648051,
+      "grad_norm": 0.8947063684463501,
+      "learning_rate": 2.9844161102077218e-09,
+      "loss": 2.0502,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0,
+      "step": 4029,
+      "total_flos": 7.32108351012864e+16,
+      "train_loss": 2.103881771554424,
+      "train_runtime": 1250.9785,
+      "train_samples_per_second": 6.441,
+      "train_steps_per_second": 3.221
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4029,
+  "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": 7.32108351012864e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}