MHGanainy/gpt2-xl-lora-ecthr-tf-idf-kmeans-imbalanced-uniform-cluster-8-id-8

README.md

@@ -15,6 +15,8 @@ should probably proofread and complete it, then remove this comment. -->
 # gpt2-xl-lora-ecthr-tf-idf-kmeans-imbalanced-uniform-cluster-8-id-8
 
 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: 2.2193
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.2192912101745605,
+    "eval_runtime": 15.6464,
+    "eval_samples_per_second": 22.369,
+    "eval_steps_per_second": 2.812,
+    "perplexity": 9.200807115702053,
+    "total_flos": 3.088310550528e+16,
+    "train_loss": 2.3357728562265074,
+    "train_runtime": 448.4214,
+    "train_samples_per_second": 7.562,
+    "train_steps_per_second": 3.782
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.2192912101745605,
+    "eval_runtime": 15.6464,
+    "eval_samples_per_second": 22.369,
+    "eval_steps_per_second": 2.812,
+    "perplexity": 9.200807115702053
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 3.088310550528e+16,
+    "train_loss": 2.3357728562265074,
+    "train_runtime": 448.4214,
+    "train_samples_per_second": 7.562,
+    "train_steps_per_second": 3.782
+}

trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1696,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0589622641509434,
+      "grad_norm": 0.11502372473478317,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.5402,
+      "step": 100
+    },
+    {
+      "epoch": 0.1179245283018868,
+      "grad_norm": 0.21899548172950745,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.5382,
+      "step": 200
+    },
+    {
+      "epoch": 0.17688679245283018,
+      "grad_norm": 0.2467164397239685,
+      "learning_rate": 6e-06,
+      "loss": 2.5015,
+      "step": 300
+    },
+    {
+      "epoch": 0.2358490566037736,
+      "grad_norm": 0.3598988354206085,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.4872,
+      "step": 400
+    },
+    {
+      "epoch": 0.294811320754717,
+      "grad_norm": 0.42844414710998535,
+      "learning_rate": 1e-05,
+      "loss": 2.4242,
+      "step": 500
+    },
+    {
+      "epoch": 0.35377358490566035,
+      "grad_norm": 0.5226746797561646,
+      "learning_rate": 1.2e-05,
+      "loss": 2.3893,
+      "step": 600
+    },
+    {
+      "epoch": 0.41273584905660377,
+      "grad_norm": 0.5295324325561523,
+      "learning_rate": 1.4e-05,
+      "loss": 2.3536,
+      "step": 700
+    },
+    {
+      "epoch": 0.4716981132075472,
+      "grad_norm": 0.5710903406143188,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 2.323,
+      "step": 800
+    },
+    {
+      "epoch": 0.5306603773584906,
+      "grad_norm": 0.5894581079483032,
+      "learning_rate": 1.8e-05,
+      "loss": 2.2702,
+      "step": 900
+    },
+    {
+      "epoch": 0.589622641509434,
+      "grad_norm": 0.6792523860931396,
+      "learning_rate": 2e-05,
+      "loss": 2.2962,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6485849056603774,
+      "grad_norm": 0.7023124694824219,
+      "learning_rate": 1.899846753957507e-05,
+      "loss": 2.2594,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7075471698113207,
+      "grad_norm": 0.7881377339363098,
+      "learning_rate": 1.6194483612157232e-05,
+      "loss": 2.2429,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7665094339622641,
+      "grad_norm": 0.7712042331695557,
+      "learning_rate": 1.2149704402110243e-05,
+      "loss": 2.2229,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8254716981132075,
+      "grad_norm": 0.7452691793441772,
+      "learning_rate": 7.674325444256899e-06,
+      "loss": 2.2289,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8844339622641509,
+      "grad_norm": 0.7722818851470947,
+      "learning_rate": 3.6647941983957647e-06,
+      "loss": 2.1969,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9433962264150944,
+      "grad_norm": 0.858065128326416,
+      "learning_rate": 9.242458032904311e-07,
+      "loss": 2.2172,
+      "step": 1600
+    },
+    {
+      "epoch": 1.0,
+      "step": 1696,
+      "total_flos": 3.088310550528e+16,
+      "train_loss": 2.3357728562265074,
+      "train_runtime": 448.4214,
+      "train_samples_per_second": 7.562,
+      "train_steps_per_second": 3.782
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1696,
+  "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": 3.088310550528e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}