MHGanainy/gpt2-xl-lora-ecthr-random-imbalanced-uniform-cluster-8-id-3

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-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: 1.9548
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.954843282699585,
+    "eval_runtime": 30.2843,
+    "eval_samples_per_second": 22.025,
+    "eval_steps_per_second": 2.774,
+    "perplexity": 7.062812072122963,
+    "total_flos": 7.557299011584e+16,
+    "train_loss": 2.1402389717607737,
+    "train_runtime": 1100.7663,
+    "train_samples_per_second": 7.538,
+    "train_steps_per_second": 3.769
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.954843282699585,
+    "eval_runtime": 30.2843,
+    "eval_samples_per_second": 22.025,
+    "eval_steps_per_second": 2.774,
+    "perplexity": 7.062812072122963
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 7.557299011584e+16,
+    "train_loss": 2.1402389717607737,
+    "train_runtime": 1100.7663,
+    "train_samples_per_second": 7.538,
+    "train_steps_per_second": 3.769
+}

trainer_state.json

@@ -0,0 +1,329 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 4149,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.024102193299590263,
+      "grad_norm": 0.12129273265600204,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.4343,
+      "step": 100
+    },
+    {
+      "epoch": 0.048204386599180526,
+      "grad_norm": 0.14322014153003693,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.432,
+      "step": 200
+    },
+    {
+      "epoch": 0.07230657989877079,
+      "grad_norm": 0.1989438235759735,
+      "learning_rate": 6e-06,
+      "loss": 2.4093,
+      "step": 300
+    },
+    {
+      "epoch": 0.09640877319836105,
+      "grad_norm": 0.29073336720466614,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.4068,
+      "step": 400
+    },
+    {
+      "epoch": 0.12051096649795132,
+      "grad_norm": 0.3857264518737793,
+      "learning_rate": 1e-05,
+      "loss": 2.3247,
+      "step": 500
+    },
+    {
+      "epoch": 0.14461315979754158,
+      "grad_norm": 0.4371218979358673,
+      "learning_rate": 1.2e-05,
+      "loss": 2.2812,
+      "step": 600
+    },
+    {
+      "epoch": 0.16871535309713184,
+      "grad_norm": 0.4732334613800049,
+      "learning_rate": 1.4e-05,
+      "loss": 2.3052,
+      "step": 700
+    },
+    {
+      "epoch": 0.1928175463967221,
+      "grad_norm": 0.5335157513618469,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.3033,
+      "step": 800
+    },
+    {
+      "epoch": 0.21691973969631237,
+      "grad_norm": 0.5665431022644043,
+      "learning_rate": 1.8e-05,
+      "loss": 2.2356,
+      "step": 900
+    },
+    {
+      "epoch": 0.24102193299590263,
+      "grad_norm": 0.6024836301803589,
+      "learning_rate": 2e-05,
+      "loss": 2.2147,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26512412629549287,
+      "grad_norm": 0.6340093612670898,
+      "learning_rate": 1.9950276214176393e-05,
+      "loss": 2.1827,
+      "step": 1100
+    },
+    {
+      "epoch": 0.28922631959508316,
+      "grad_norm": 0.7230168581008911,
+      "learning_rate": 1.9801599347680883e-05,
+      "loss": 2.1725,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3133285128946734,
+      "grad_norm": 0.6333301067352295,
+      "learning_rate": 1.9555447955846792e-05,
+      "loss": 2.1721,
+      "step": 1300
+    },
+    {
+      "epoch": 0.3374307061942637,
+      "grad_norm": 0.7931402325630188,
+      "learning_rate": 1.921426995449166e-05,
+      "loss": 2.1553,
+      "step": 1400
+    },
+    {
+      "epoch": 0.3615328994938539,
+      "grad_norm": 0.8418000340461731,
+      "learning_rate": 1.8781458275988913e-05,
+      "loss": 2.1593,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3856350927934442,
+      "grad_norm": 0.7354087233543396,
+      "learning_rate": 1.826131712737932e-05,
+      "loss": 2.1141,
+      "step": 1600
+    },
+    {
+      "epoch": 0.40973728609303445,
+      "grad_norm": 0.7928228974342346,
+      "learning_rate": 1.7659019186077174e-05,
+      "loss": 2.106,
+      "step": 1700
+    },
+    {
+      "epoch": 0.43383947939262474,
+      "grad_norm": 0.8684613704681396,
+      "learning_rate": 1.6980554158849546e-05,
+      "loss": 2.1097,
+      "step": 1800
+    },
+    {
+      "epoch": 0.457941672692215,
+      "grad_norm": 0.8732122778892517,
+      "learning_rate": 1.6232669215636963e-05,
+      "loss": 2.0938,
+      "step": 1900
+    },
+    {
+      "epoch": 0.48204386599180526,
+      "grad_norm": 0.7818373441696167,
+      "learning_rate": 1.5422801890586833e-05,
+      "loss": 2.0519,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5061460592913956,
+      "grad_norm": 1.1101610660552979,
+      "learning_rate": 1.4559006117582424e-05,
+      "loss": 2.1027,
+      "step": 2100
+    },
+    {
+      "epoch": 0.5302482525909857,
+      "grad_norm": 1.3163758516311646,
+      "learning_rate": 1.3649872135826173e-05,
+      "loss": 2.0895,
+      "step": 2200
+    },
+    {
+      "epoch": 0.554350445890576,
+      "grad_norm": 0.9687483906745911,
+      "learning_rate": 1.2704441061996842e-05,
+      "loss": 2.0358,
+      "step": 2300
+    },
+    {
+      "epoch": 0.5784526391901663,
+      "grad_norm": 0.8182618618011475,
+      "learning_rate": 1.1732114978539648e-05,
+      "loss": 2.0623,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6025548324897566,
+      "grad_norm": 0.8492296934127808,
+      "learning_rate": 1.0742563432239503e-05,
+      "loss": 2.0807,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6266570257893468,
+      "grad_norm": 0.9861396551132202,
+      "learning_rate": 9.745627272926332e-06,
+      "loss": 2.0644,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6507592190889371,
+      "grad_norm": 0.8451273441314697,
+      "learning_rate": 8.751220788613237e-06,
+      "loss": 2.053,
+      "step": 2700
+    },
+    {
+      "epoch": 0.6748614123885274,
+      "grad_norm": 0.850528359413147,
+      "learning_rate": 7.769233110309735e-06,
+      "loss": 2.052,
+      "step": 2800
+    },
+    {
+      "epoch": 0.6989636056881177,
+      "grad_norm": 0.8158134818077087,
+      "learning_rate": 6.809429867015307e-06,
+      "loss": 2.1133,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7230657989877078,
+      "grad_norm": 0.9995165467262268,
+      "learning_rate": 5.881356068910429e-06,
+      "loss": 2.0591,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7471679922872981,
+      "grad_norm": 1.094310998916626,
+      "learning_rate": 4.994241184548192e-06,
+      "loss": 1.9957,
+      "step": 3100
+    },
+    {
+      "epoch": 0.7712701855868884,
+      "grad_norm": 1.0143593549728394,
+      "learning_rate": 4.1569073560307905e-06,
+      "loss": 2.0432,
+      "step": 3200
+    },
+    {
+      "epoch": 0.7953723788864787,
+      "grad_norm": 0.9745491743087769,
+      "learning_rate": 3.3776816649486378e-06,
+      "loss": 2.0405,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8194745721860689,
+      "grad_norm": 0.9726706147193909,
+      "learning_rate": 2.6643133215760586e-06,
+      "loss": 2.0432,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8435767654856592,
+      "grad_norm": 0.9675843715667725,
+      "learning_rate": 2.0238966008568905e-06,
+      "loss": 2.012,
+      "step": 3500
+    },
+    {
+      "epoch": 0.8676789587852495,
+      "grad_norm": 0.9434055685997009,
+      "learning_rate": 1.4628002915629202e-06,
+      "loss": 2.0621,
+      "step": 3600
+    },
+    {
+      "epoch": 0.8917811520848398,
+      "grad_norm": 0.9228490591049194,
+      "learning_rate": 9.866043602360909e-07,
+      "loss": 2.0445,
+      "step": 3700
+    },
+    {
+      "epoch": 0.91588334538443,
+      "grad_norm": 0.7192670702934265,
+      "learning_rate": 6.000444597762811e-07,
+      "loss": 2.0472,
+      "step": 3800
+    },
+    {
+      "epoch": 0.9399855386840202,
+      "grad_norm": 1.0140488147735596,
+      "learning_rate": 3.069648345231813e-07,
+      "loss": 2.0127,
+      "step": 3900
+    },
+    {
+      "epoch": 0.9640877319836105,
+      "grad_norm": 0.9785950183868408,
+      "learning_rate": 1.1028009017986174e-07,
+      "loss": 2.0638,
+      "step": 4000
+    },
+    {
+      "epoch": 0.9881899252832008,
+      "grad_norm": 1.1137417554855347,
+      "learning_rate": 1.1946208766822066e-08,
+      "loss": 2.0633,
+      "step": 4100
+    },
+    {
+      "epoch": 1.0,
+      "step": 4149,
+      "total_flos": 7.557299011584e+16,
+      "train_loss": 2.1402389717607737,
+      "train_runtime": 1100.7663,
+      "train_samples_per_second": 7.538,
+      "train_steps_per_second": 3.769
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4149,
+  "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": 7.557299011584e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}