MHGanainy/8-clusters-balanced-lex-best-3

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.54607093334198,
+    "eval_runtime": 30.0856,
+    "eval_samples_per_second": 9.539,
+    "eval_steps_per_second": 1.197,
+    "perplexity": 4.692994821416736,
+    "total_flos": 3.521821556736e+16,
+    "train_loss": 1.7982163059427918,
+    "train_runtime": 803.097,
+    "train_samples_per_second": 4.815,
+    "train_steps_per_second": 2.408
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.54607093334198,
+    "eval_runtime": 30.0856,
+    "eval_samples_per_second": 9.539,
+    "eval_steps_per_second": 1.197,
+    "perplexity": 4.692994821416736
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 3.521821556736e+16,
+    "train_loss": 1.7982163059427918,
+    "train_runtime": 803.097,
+    "train_samples_per_second": 4.815,
+    "train_steps_per_second": 2.408
+}

trainer_state.json

@@ -0,0 +1,183 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1934,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05170630816959669,
+      "grad_norm": 0.39979541301727295,
+      "learning_rate": 1.0362694300518135e-05,
+      "loss": 2.3603,
+      "step": 100
+    },
+    {
+      "epoch": 0.10341261633919338,
+      "grad_norm": 0.3448098599910736,
+      "learning_rate": 1.9999202257897994e-05,
+      "loss": 2.3148,
+      "step": 200
+    },
+    {
+      "epoch": 0.15511892450879008,
+      "grad_norm": 0.5190999507904053,
+      "learning_rate": 1.9814180984676353e-05,
+      "loss": 2.1195,
+      "step": 300
+    },
+    {
+      "epoch": 0.20682523267838676,
+      "grad_norm": 0.7202345132827759,
+      "learning_rate": 1.9310463051595612e-05,
+      "loss": 1.9785,
+      "step": 400
+    },
+    {
+      "epoch": 0.25853154084798347,
+      "grad_norm": 0.9304684996604919,
+      "learning_rate": 1.8504405730142267e-05,
+      "loss": 1.8596,
+      "step": 500
+    },
+    {
+      "epoch": 0.31023784901758017,
+      "grad_norm": 1.1649187803268433,
+      "learning_rate": 1.7422184182197197e-05,
+      "loss": 1.8268,
+      "step": 600
+    },
+    {
+      "epoch": 0.3619441571871768,
+      "grad_norm": 1.3013240098953247,
+      "learning_rate": 1.6098941471974945e-05,
+      "loss": 1.7522,
+      "step": 700
+    },
+    {
+      "epoch": 0.4136504653567735,
+      "grad_norm": 1.0057692527770996,
+      "learning_rate": 1.4577647362575378e-05,
+      "loss": 1.7433,
+      "step": 800
+    },
+    {
+      "epoch": 0.4653567735263702,
+      "grad_norm": 1.1984479427337646,
+      "learning_rate": 1.2907702955535744e-05,
+      "loss": 1.7378,
+      "step": 900
+    },
+    {
+      "epoch": 0.5170630816959669,
+      "grad_norm": 1.20029616355896,
+      "learning_rate": 1.1143336485031156e-05,
+      "loss": 1.7106,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5687693898655636,
+      "grad_norm": 1.1434617042541504,
+      "learning_rate": 9.341842360222717e-06,
+      "loss": 1.6596,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6204756980351603,
+      "grad_norm": 1.2820420265197754,
+      "learning_rate": 7.561720639467684e-06,
+      "loss": 1.6422,
+      "step": 1200
+    },
+    {
+      "epoch": 0.672182006204757,
+      "grad_norm": 1.130136489868164,
+      "learning_rate": 5.860777353389816e-06,
+      "loss": 1.6522,
+      "step": 1300
+    },
+    {
+      "epoch": 0.7238883143743536,
+      "grad_norm": 1.4673417806625366,
+      "learning_rate": 4.294247365166093e-06,
+      "loss": 1.6528,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7755946225439504,
+      "grad_norm": 1.2400269508361816,
+      "learning_rate": 2.913000724533277e-06,
+      "loss": 1.6322,
+      "step": 1500
+    },
+    {
+      "epoch": 0.827300930713547,
+      "grad_norm": 1.1362736225128174,
+      "learning_rate": 1.7618907607196112e-06,
+      "loss": 1.6696,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8790072388831437,
+      "grad_norm": 1.2125930786132812,
+      "learning_rate": 8.782975568080066e-07,
+      "loss": 1.6631,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9307135470527405,
+      "grad_norm": 1.3303070068359375,
+      "learning_rate": 2.909141034005891e-07,
+      "loss": 1.62,
+      "step": 1800
+    },
+    {
+      "epoch": 0.9824198552223371,
+      "grad_norm": 1.3941837549209595,
+      "learning_rate": 1.8814548910730535e-08,
+      "loss": 1.6574,
+      "step": 1900
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.54607093334198,
+      "eval_runtime": 32.6185,
+      "eval_samples_per_second": 8.799,
+      "eval_steps_per_second": 1.104,
+      "step": 1934
+    },
+    {
+      "epoch": 1.0,
+      "step": 1934,
+      "total_flos": 3.521821556736e+16,
+      "train_loss": 1.7982163059427918,
+      "train_runtime": 803.097,
+      "train_samples_per_second": 4.815,
+      "train_steps_per_second": 2.408
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 1934,
+  "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": 3.521821556736e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}