MHGanainy/gpt2-xl-lora-multi-7

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # gpt2-xl-lora-multi-7
 
 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: 2.5501
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.5500738620758057,
+    "eval_runtime": 333.0501,
+    "eval_samples_per_second": 7.786,
+    "eval_steps_per_second": 0.489,
+    "perplexity": 12.808049776869597,
+    "total_flos": 3.940214344788214e+17,
+    "train_loss": 2.675769654604105,
+    "train_runtime": 864.3634,
+    "train_samples_per_second": 50.048,
+    "train_steps_per_second": 3.128
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.5500738620758057,
+    "eval_runtime": 333.0501,
+    "eval_samples_per_second": 7.786,
+    "eval_steps_per_second": 0.489,
+    "perplexity": 12.808049776869597
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 3.940214344788214e+17,
+    "train_loss": 2.675769654604105,
+    "train_runtime": 864.3634,
+    "train_samples_per_second": 50.048,
+    "train_steps_per_second": 3.128
+}

trainer_state.json

@@ -0,0 +1,231 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2704,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03698224852071006,
+      "grad_norm": 0.14849229156970978,
+      "learning_rate": 9.06148867313916e-07,
+      "loss": 2.9299,
+      "step": 100
+    },
+    {
+      "epoch": 0.07396449704142012,
+      "grad_norm": 0.18462003767490387,
+      "learning_rate": 1.8307905686546466e-06,
+      "loss": 2.9277,
+      "step": 200
+    },
+    {
+      "epoch": 0.11094674556213018,
+      "grad_norm": 0.2244928628206253,
+      "learning_rate": 2.7461858529819695e-06,
+      "loss": 2.9367,
+      "step": 300
+    },
+    {
+      "epoch": 0.14792899408284024,
+      "grad_norm": 0.11301285773515701,
+      "learning_rate": 3.6708275543227e-06,
+      "loss": 2.865,
+      "step": 400
+    },
+    {
+      "epoch": 0.1849112426035503,
+      "grad_norm": 0.16168534755706787,
+      "learning_rate": 4.59546925566343e-06,
+      "loss": 2.834,
+      "step": 500
+    },
+    {
+      "epoch": 0.22189349112426035,
+      "grad_norm": 0.23730890452861786,
+      "learning_rate": 5.520110957004161e-06,
+      "loss": 2.8,
+      "step": 600
+    },
+    {
+      "epoch": 0.2588757396449704,
+      "grad_norm": 0.150528684258461,
+      "learning_rate": 6.444752658344892e-06,
+      "loss": 2.7822,
+      "step": 700
+    },
+    {
+      "epoch": 0.2958579881656805,
+      "grad_norm": 0.1429228037595749,
+      "learning_rate": 7.369394359685622e-06,
+      "loss": 2.7178,
+      "step": 800
+    },
+    {
+      "epoch": 0.3328402366863905,
+      "grad_norm": 0.30748799443244934,
+      "learning_rate": 8.294036061026353e-06,
+      "loss": 2.7005,
+      "step": 900
+    },
+    {
+      "epoch": 0.3698224852071006,
+      "grad_norm": 0.163905069231987,
+      "learning_rate": 9.218677762367084e-06,
+      "loss": 2.6718,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4068047337278107,
+      "grad_norm": 0.2939082384109497,
+      "learning_rate": 1.0143319463707815e-05,
+      "loss": 2.6669,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4437869822485207,
+      "grad_norm": 0.22948721051216125,
+      "learning_rate": 1.1067961165048544e-05,
+      "loss": 2.6516,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4807692307692308,
+      "grad_norm": 0.19319839775562286,
+      "learning_rate": 1.1992602866389276e-05,
+      "loss": 2.647,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5177514792899408,
+      "grad_norm": 0.21269312500953674,
+      "learning_rate": 1.2917244567730005e-05,
+      "loss": 2.6304,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5547337278106509,
+      "grad_norm": 0.2854045331478119,
+      "learning_rate": 1.3841886269070736e-05,
+      "loss": 2.6148,
+      "step": 1500
+    },
+    {
+      "epoch": 0.591715976331361,
+      "grad_norm": 0.21025152504444122,
+      "learning_rate": 1.4766527970411465e-05,
+      "loss": 2.6068,
+      "step": 1600
+    },
+    {
+      "epoch": 0.628698224852071,
+      "grad_norm": 0.2919473350048065,
+      "learning_rate": 1.5691169671752196e-05,
+      "loss": 2.6001,
+      "step": 1700
+    },
+    {
+      "epoch": 0.665680473372781,
+      "grad_norm": 0.21243709325790405,
+      "learning_rate": 1.661581137309293e-05,
+      "loss": 2.5868,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7026627218934911,
+      "grad_norm": 0.2556278109550476,
+      "learning_rate": 1.7540453074433658e-05,
+      "loss": 2.5812,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7396449704142012,
+      "grad_norm": 0.2942062318325043,
+      "learning_rate": 1.8465094775774387e-05,
+      "loss": 2.5816,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7766272189349113,
+      "grad_norm": 0.23691928386688232,
+      "learning_rate": 1.938973647711512e-05,
+      "loss": 2.5727,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8136094674556213,
+      "grad_norm": 0.2230062484741211,
+      "learning_rate": 1.980572281912978e-05,
+      "loss": 2.5698,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8505917159763313,
+      "grad_norm": 0.23846900463104248,
+      "learning_rate": 1.7122208281783788e-05,
+      "loss": 2.552,
+      "step": 2300
+    },
+    {
+      "epoch": 0.8875739644970414,
+      "grad_norm": 0.24352632462978363,
+      "learning_rate": 1.2103724124062295e-05,
+      "loss": 2.565,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9245562130177515,
+      "grad_norm": 0.2532407343387604,
+      "learning_rate": 6.395547707284e-06,
+      "loss": 2.5503,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9615384615384616,
+      "grad_norm": 0.2501896619796753,
+      "learning_rate": 1.869067510077197e-06,
+      "loss": 2.5497,
+      "step": 2600
+    },
+    {
+      "epoch": 0.9985207100591716,
+      "grad_norm": 0.21952682733535767,
+      "learning_rate": 8.260598198537306e-09,
+      "loss": 2.5555,
+      "step": 2700
+    },
+    {
+      "epoch": 1.0,
+      "step": 2704,
+      "total_flos": 3.940214344788214e+17,
+      "train_loss": 2.675769654604105,
+      "train_runtime": 864.3634,
+      "train_samples_per_second": 50.048,
+      "train_steps_per_second": 3.128
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 2704,
+  "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": 3.940214344788214e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}