MHGanainy/best-performing-clustering-0

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # best-performing-clustering-0
 
 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: 1.5489
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+ "epoch": 1.0,
+ "eval_loss": 1.5488653182983398,
+ "eval_runtime": 48.6887,
+ "eval_samples_per_second": 10.906,
+ "eval_steps_per_second": 1.376,
+ "perplexity": 4.706127195454765,
+ "total_flos": 4.381557669888e+16,
+ "train_loss": 1.8077541630365208,
+ "train_runtime": 1256.4921,
+ "train_samples_per_second": 3.829,
+ "train_steps_per_second": 1.915
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+ "epoch": 1.0,
+ "eval_loss": 1.5488653182983398,
+ "eval_runtime": 48.6887,
+ "eval_samples_per_second": 10.906,
+ "eval_steps_per_second": 1.376,
+ "perplexity": 4.706127195454765
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+ "epoch": 1.0,
+ "total_flos": 4.381557669888e+16,
+ "train_loss": 1.8077541630365208,
+ "train_runtime": 1256.4921,
+ "train_samples_per_second": 3.829,
+ "train_steps_per_second": 1.915
+}

trainer_state.json

@@ -0,0 +1,210 @@
+{
+ "best_metric": null,
+ "best_model_checkpoint": null,
+ "epoch": 1.0,
+ "eval_steps": 500,
+ "global_step": 2406,
+ "is_hyper_param_search": false,
+ "is_local_process_zero": true,
+ "is_world_process_zero": true,
+ "log_history": [
+ {
+ "epoch": 0.04156275976724855,
+ "grad_norm": 0.14744289219379425,
+ "learning_rate": 6.666666666666667e-06,
+ "loss": 2.4022,
+ "step": 100
+ },
+ {
+ "epoch": 0.0831255195344971,
+ "grad_norm": 0.3039261996746063,
+ "learning_rate": 1.3333333333333333e-05,
+ "loss": 2.3503,
+ "step": 200
+ },
+ {
+ "epoch": 0.12468827930174564,
+ "grad_norm": 0.410941481590271,
+ "learning_rate": 2e-05,
+ "loss": 2.2434,
+ "step": 300
+ },
+ {
+ "epoch": 0.1662510390689942,
+ "grad_norm": 0.7095025181770325,
+ "learning_rate": 1.9888942596891267e-05,
+ "loss": 2.1069,
+ "step": 400
+ },
+ {
+ "epoch": 0.20781379883624274,
+ "grad_norm": 0.9124996066093445,
+ "learning_rate": 1.9558237136922117e-05,
+ "loss": 1.9604,
+ "step": 500
+ },
+ {
+ "epoch": 0.24937655860349128,
+ "grad_norm": 0.8121271133422852,
+ "learning_rate": 1.9015229078008163e-05,
+ "loss": 1.9188,
+ "step": 600
+ },
+ {
+ "epoch": 0.29093931837073983,
+ "grad_norm": 1.5083343982696533,
+ "learning_rate": 1.827197943312742e-05,
+ "loss": 1.8201,
+ "step": 700
+ },
+ {
+ "epoch": 0.3325020781379884,
+ "grad_norm": 1.17859947681427,
+ "learning_rate": 1.7344996877364282e-05,
+ "loss": 1.7504,
+ "step": 800
+ },
+ {
+ "epoch": 0.3740648379052369,
+ "grad_norm": 0.9727289080619812,
+ "learning_rate": 1.6254871065792776e-05,
+ "loss": 1.7776,
+ "step": 900
+ },
+ {
+ "epoch": 0.41562759767248547,
+ "grad_norm": 1.3123071193695068,
+ "learning_rate": 1.5025815306751888e-05,
+ "loss": 1.7882,
+ "step": 1000
+ },
+ {
+ "epoch": 0.457190357439734,
+ "grad_norm": 1.1380528211593628,
+ "learning_rate": 1.3685128748416603e-05,
+ "loss": 1.7312,
+ "step": 1100
+ },
+ {
+ "epoch": 0.49875311720698257,
+ "grad_norm": 0.923092246055603,
+ "learning_rate": 1.2262590024297226e-05,
+ "loss": 1.7124,
+ "step": 1200
+ },
+ {
+ "epoch": 0.5403158769742311,
+ "grad_norm": 1.1041200160980225,
+ "learning_rate": 1.0789795825698206e-05,
+ "loss": 1.7234,
+ "step": 1300
+ },
+ {
+ "epoch": 0.5818786367414797,
+ "grad_norm": 1.2354481220245361,
+ "learning_rate": 9.299459092421558e-06,
+ "loss": 1.6699,
+ "step": 1400
+ },
+ {
+ "epoch": 0.6234413965087282,
+ "grad_norm": 1.216248869895935,
+ "learning_rate": 7.824682409938328e-06,
+ "loss": 1.6909,
+ "step": 1500
+ },
+ {
+ "epoch": 0.6650041562759768,
+ "grad_norm": 1.411401629447937,
+ "learning_rate": 6.3982227519528986e-06,
+ "loss": 1.6546,
+ "step": 1600
+ },
+ {
+ "epoch": 0.7065669160432253,
+ "grad_norm": 1.126512050628662,
+ "learning_rate": 5.051763899516313e-06,
+ "loss": 1.6731,
+ "step": 1700
+ },
+ {
+ "epoch": 0.7481296758104738,
+ "grad_norm": 1.1200768947601318,
+ "learning_rate": 3.815212697337451e-06,
+ "loss": 1.6337,
+ "step": 1800
+ },
+ {
+ "epoch": 0.7896924355777224,
+ "grad_norm": 1.3716657161712646,
+ "learning_rate": 2.716034778481301e-06,
+ "loss": 1.595,
+ "step": 1900
+ },
+ {
+ "epoch": 0.8312551953449709,
+ "grad_norm": 1.393244743347168,
+ "learning_rate": 1.7786445119923967e-06,
+ "loss": 1.6661,
+ "step": 2000
+ },
+ {
+ "epoch": 0.8728179551122195,
+ "grad_norm": 1.6690272092819214,
+ "learning_rate": 1.0238627236098619e-06,
+ "loss": 1.6413,
+ "step": 2100
+ },
+ {
+ "epoch": 0.914380714879468,
+ "grad_norm": 1.564997673034668,
+ "learning_rate": 4.6845423440000315e-07,
+ "loss": 1.6164,
+ "step": 2200
+ },
+ {
+ "epoch": 0.9559434746467166,
+ "grad_norm": 1.2120723724365234,
+ "learning_rate": 1.247554892580616e-07,
+ "loss": 1.6461,
+ "step": 2300
+ },
+ {
+ "epoch": 0.9975062344139651,
+ "grad_norm": 1.2864446640014648,
+ "learning_rate": 4.005462014766703e-10,
+ "loss": 1.6259,
+ "step": 2400
+ },
+ {
+ "epoch": 1.0,
+ "step": 2406,
+ "total_flos": 4.381557669888e+16,
+ "train_loss": 1.8077541630365208,
+ "train_runtime": 1256.4921,
+ "train_samples_per_second": 3.829,
+ "train_steps_per_second": 1.915
+ }
+ ],
+ "logging_steps": 100,
+ "max_steps": 2406,
+ "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": 4.381557669888e+16,
+ "train_batch_size": 2,
+ "trial_name": null,
+ "trial_params": null
+}