MHGanainy/gpt2-xl-lora-ecthr-random-imbalanced-uniform-cluster-8-id-2

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-2
 
 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: 1.9139
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.9138996601104736,
+    "eval_runtime": 18.0721,
+    "eval_samples_per_second": 22.3,
+    "eval_steps_per_second": 2.822,
+    "perplexity": 6.779474964642504,
+    "total_flos": 5.101950959616e+16,
+    "train_loss": 2.200730042472902,
+    "train_runtime": 742.2239,
+    "train_samples_per_second": 7.548,
+    "train_steps_per_second": 3.774
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.9138996601104736,
+    "eval_runtime": 18.0721,
+    "eval_samples_per_second": 22.3,
+    "eval_steps_per_second": 2.822,
+    "perplexity": 6.779474964642504
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 5.101950959616e+16,
+    "train_loss": 2.200730042472902,
+    "train_runtime": 742.2239,
+    "train_samples_per_second": 7.548,
+    "train_steps_per_second": 3.774
+}

trainer_state.json

@@ -0,0 +1,238 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2801,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03570153516601214,
+      "grad_norm": 0.2108674943447113,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.4571,
+      "step": 100
+    },
+    {
+      "epoch": 0.07140307033202428,
+      "grad_norm": 0.15163728594779968,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.4552,
+      "step": 200
+    },
+    {
+      "epoch": 0.10710460549803641,
+      "grad_norm": 0.17332352697849274,
+      "learning_rate": 6e-06,
+      "loss": 2.4174,
+      "step": 300
+    },
+    {
+      "epoch": 0.14280614066404856,
+      "grad_norm": 0.3060334026813507,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.3997,
+      "step": 400
+    },
+    {
+      "epoch": 0.1785076758300607,
+      "grad_norm": 0.428406298160553,
+      "learning_rate": 1e-05,
+      "loss": 2.3187,
+      "step": 500
+    },
+    {
+      "epoch": 0.21420921099607282,
+      "grad_norm": 0.4128827750682831,
+      "learning_rate": 1.2e-05,
+      "loss": 2.3424,
+      "step": 600
+    },
+    {
+      "epoch": 0.24991074616208497,
+      "grad_norm": 0.4762149453163147,
+      "learning_rate": 1.4e-05,
+      "loss": 2.3007,
+      "step": 700
+    },
+    {
+      "epoch": 0.28561228132809713,
+      "grad_norm": 0.5369089841842651,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.2439,
+      "step": 800
+    },
+    {
+      "epoch": 0.32131381649410923,
+      "grad_norm": 0.571308970451355,
+      "learning_rate": 1.8e-05,
+      "loss": 2.2439,
+      "step": 900
+    },
+    {
+      "epoch": 0.3570153516601214,
+      "grad_norm": 0.6733306646347046,
+      "learning_rate": 2e-05,
+      "loss": 2.2095,
+      "step": 1000
+    },
+    {
+      "epoch": 0.39271688682613354,
+      "grad_norm": 0.6039965748786926,
+      "learning_rate": 1.98482457644138e-05,
+      "loss": 2.1783,
+      "step": 1100
+    },
+    {
+      "epoch": 0.42841842199214564,
+      "grad_norm": 0.6283470988273621,
+      "learning_rate": 1.9397588927258876e-05,
+      "loss": 2.2147,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4641199571581578,
+      "grad_norm": 0.632673978805542,
+      "learning_rate": 1.8661707305302052e-05,
+      "loss": 2.1789,
+      "step": 1300
+    },
+    {
+      "epoch": 0.49982149232416995,
+      "grad_norm": 0.6215189099311829,
+      "learning_rate": 1.7662935529147725e-05,
+      "loss": 2.1142,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5355230274901821,
+      "grad_norm": 0.8266947865486145,
+      "learning_rate": 1.643158716827897e-05,
+      "loss": 2.1424,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5712245626561943,
+      "grad_norm": 0.7430416941642761,
+      "learning_rate": 1.500503468854458e-05,
+      "loss": 2.1583,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6069260978222063,
+      "grad_norm": 0.7989104986190796,
+      "learning_rate": 1.342657516616169e-05,
+      "loss": 2.1317,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6426276329882185,
+      "grad_norm": 0.8354244828224182,
+      "learning_rate": 1.1744116184774898e-05,
+      "loss": 2.0803,
+      "step": 1800
+    },
+    {
+      "epoch": 0.6783291681542306,
+      "grad_norm": 0.7150327563285828,
+      "learning_rate": 1.00087217997093e-05,
+      "loss": 2.1178,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7140307033202428,
+      "grad_norm": 0.876121461391449,
+      "learning_rate": 8.273062700634137e-06,
+      "loss": 2.108,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7497322384862549,
+      "grad_norm": 0.7151755094528198,
+      "learning_rate": 6.589817611513086e-06,
+      "loss": 2.0972,
+      "step": 2100
+    },
+    {
+      "epoch": 0.7854337736522671,
+      "grad_norm": 0.7741402387619019,
+      "learning_rate": 5.010074446706905e-06,
+      "loss": 2.1213,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8211353088182792,
+      "grad_norm": 0.7411683201789856,
+      "learning_rate": 3.5817797494951313e-06,
+      "loss": 2.1148,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8568368439842913,
+      "grad_norm": 0.7820664048194885,
+      "learning_rate": 2.3482834738712023e-06,
+      "loss": 2.0735,
+      "step": 2400
+    },
+    {
+      "epoch": 0.8925383791503034,
+      "grad_norm": 1.1447112560272217,
+      "learning_rate": 1.347023276716265e-06,
+      "loss": 2.0943,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9282399143163156,
+      "grad_norm": 0.8601149916648865,
+      "learning_rate": 6.083882531987495e-07,
+      "loss": 2.1139,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9639414494823277,
+      "grad_norm": 1.064378261566162,
+      "learning_rate": 1.5479660199286927e-07,
+      "loss": 2.0897,
+      "step": 2700
+    },
+    {
+      "epoch": 0.9996429846483399,
+      "grad_norm": 0.8209490180015564,
+      "learning_rate": 1.5213958033388766e-11,
+      "loss": 2.1036,
+      "step": 2800
+    },
+    {
+      "epoch": 1.0,
+      "step": 2801,
+      "total_flos": 5.101950959616e+16,
+      "train_loss": 2.200730042472902,
+      "train_runtime": 742.2239,
+      "train_samples_per_second": 7.548,
+      "train_steps_per_second": 3.774
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2801,
+  "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": 5.101950959616e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}