End of training

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8170995182696579,
+    "eval_loss": 1.0433119535446167,
+    "eval_runtime": 49.5731,
+    "eval_samples": 2251,
+    "eval_samples_per_second": 45.408,
+    "eval_steps_per_second": 1.432,
+    "perplexity": 2.838602783707372,
+    "train_loss": 1.2553224705938082,
+    "train_runtime": 11299.6989,
+    "train_samples": 42861,
+    "train_samples_per_second": 37.931,
+    "train_steps_per_second": 1.186
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 10.0,
+    "eval_accuracy": 0.8170995182696579,
+    "eval_loss": 1.0433119535446167,
+    "eval_runtime": 49.5731,
+    "eval_samples": 2251,
+    "eval_samples_per_second": 45.408,
+    "eval_steps_per_second": 1.432,
+    "perplexity": 2.838602783707372
+}

runs/Nov13_14-20-09_hkmustamd-Super-Server/events.out.tfevents.1731490308.hkmustamd-Super-Server.2240873.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9caa3c414705ccaa7838d2b2793fb8607eefa0a0e950546ce5ecefbc2486a4ae
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 10.0,
+    "train_loss": 1.2553224705938082,
+    "train_runtime": 11299.6989,
+    "train_samples": 42861,
+    "train_samples_per_second": 37.931,
+    "train_steps_per_second": 1.186
+}

trainer_state.json

@@ -0,0 +1,181 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "global_step": 13400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.7313432835820895e-07,
+      "loss": 2.3966,
+      "step": 500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 7.462686567164179e-07,
+      "loss": 1.5891,
+      "step": 1000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 9.867330016583748e-07,
+      "loss": 1.401,
+      "step": 1500
+    },
+    {
+      "epoch": 1.49,
+      "learning_rate": 9.45273631840796e-07,
+      "loss": 1.325,
+      "step": 2000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 9.038142620232172e-07,
+      "loss": 1.2832,
+      "step": 2500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 8.623548922056384e-07,
+      "loss": 1.256,
+      "step": 3000
+    },
+    {
+      "epoch": 2.61,
+      "learning_rate": 8.208955223880597e-07,
+      "loss": 1.2343,
+      "step": 3500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 7.794361525704809e-07,
+      "loss": 1.223,
+      "step": 4000
+    },
+    {
+      "epoch": 3.36,
+      "learning_rate": 7.379767827529021e-07,
+      "loss": 1.2113,
+      "step": 4500
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 6.965174129353234e-07,
+      "loss": 1.2001,
+      "step": 5000
+    },
+    {
+      "epoch": 4.1,
+      "learning_rate": 6.550580431177446e-07,
+      "loss": 1.1904,
+      "step": 5500
+    },
+    {
+      "epoch": 4.48,
+      "learning_rate": 6.135986733001658e-07,
+      "loss": 1.1879,
+      "step": 6000
+    },
+    {
+      "epoch": 4.85,
+      "learning_rate": 5.72139303482587e-07,
+      "loss": 1.1812,
+      "step": 6500
+    },
+    {
+      "epoch": 5.22,
+      "learning_rate": 5.306799336650083e-07,
+      "loss": 1.1746,
+      "step": 7000
+    },
+    {
+      "epoch": 5.6,
+      "learning_rate": 4.892205638474295e-07,
+      "loss": 1.1716,
+      "step": 7500
+    },
+    {
+      "epoch": 5.97,
+      "learning_rate": 4.4776119402985074e-07,
+      "loss": 1.1661,
+      "step": 8000
+    },
+    {
+      "epoch": 6.34,
+      "learning_rate": 4.0630182421227194e-07,
+      "loss": 1.1627,
+      "step": 8500
+    },
+    {
+      "epoch": 6.72,
+      "learning_rate": 3.648424543946932e-07,
+      "loss": 1.1596,
+      "step": 9000
+    },
+    {
+      "epoch": 7.09,
+      "learning_rate": 3.2338308457711446e-07,
+      "loss": 1.1563,
+      "step": 9500
+    },
+    {
+      "epoch": 7.46,
+      "learning_rate": 2.8192371475953566e-07,
+      "loss": 1.1552,
+      "step": 10000
+    },
+    {
+      "epoch": 7.84,
+      "learning_rate": 2.4046434494195686e-07,
+      "loss": 1.1539,
+      "step": 10500
+    },
+    {
+      "epoch": 8.21,
+      "learning_rate": 1.9900497512437812e-07,
+      "loss": 1.1505,
+      "step": 11000
+    },
+    {
+      "epoch": 8.58,
+      "learning_rate": 1.5754560530679933e-07,
+      "loss": 1.1494,
+      "step": 11500
+    },
+    {
+      "epoch": 8.96,
+      "learning_rate": 1.1608623548922056e-07,
+      "loss": 1.1501,
+      "step": 12000
+    },
+    {
+      "epoch": 9.33,
+      "learning_rate": 7.462686567164178e-08,
+      "loss": 1.1478,
+      "step": 12500
+    },
+    {
+      "epoch": 9.7,
+      "learning_rate": 3.316749585406302e-08,
+      "loss": 1.147,
+      "step": 13000
+    },
+    {
+      "epoch": 10.0,
+      "step": 13400,
+      "total_flos": 1.306695716831232e+17,
+      "train_loss": 1.2553224705938082,
+      "train_runtime": 11299.6989,
+      "train_samples_per_second": 37.931,
+      "train_steps_per_second": 1.186
+    }
+  ],
+  "max_steps": 13400,
+  "num_train_epochs": 10,
+  "total_flos": 1.306695716831232e+17,
+  "trial_name": null,
+  "trial_params": null
+}