End of training

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.5982814143913313,
+    "eval_loss": 2.1100358963012695,
+    "eval_runtime": 502.4632,
+    "eval_samples": 154178,
+    "eval_samples_per_second": 306.844,
+    "eval_steps_per_second": 4.796,
+    "perplexity": 8.248537371294933,
+    "train_loss": 3.027850917318448,
+    "train_runtime": 97726.2074,
+    "train_samples": 2929379,
+    "train_samples_per_second": 149.877,
+    "train_steps_per_second": 2.342
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.5982814143913313,
+    "eval_loss": 2.1100358963012695,
+    "eval_runtime": 502.4632,
+    "eval_samples": 154178,
+    "eval_samples_per_second": 306.844,
+    "eval_steps_per_second": 4.796,
+    "perplexity": 8.248537371294933
+}

logs/events.out.tfevents.1677602843.serv-3330.4081018.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f093d3556f00727ecf052fb0eb2fe018d5fa8867cf1c4922aaf2ba13816be7d2
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 3.027850917318448,
+    "train_runtime": 97726.2074,
+    "train_samples": 2929379,
+    "train_samples_per_second": 149.877,
+    "train_steps_per_second": 2.342
+}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 2.1091487407684326,
+  "best_model_checkpoint": "bert_12_layer_model_v2/checkpoint-228860",
+  "epoch": 5.0,
+  "global_step": 228860,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.183130768527826e-05,
+      "loss": 5.4137,
+      "step": 45772
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.46051966179528414,
+      "eval_loss": 3.1519112586975098,
+      "eval_runtime": 507.7189,
+      "eval_samples_per_second": 303.668,
+      "eval_steps_per_second": 4.747,
+      "step": 45772
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.137896372110025e-05,
+      "loss": 2.7951,
+      "step": 91544
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5519476580194423,
+      "eval_loss": 2.4478278160095215,
+      "eval_runtime": 505.2058,
+      "eval_samples_per_second": 305.179,
+      "eval_steps_per_second": 4.77,
+      "step": 91544
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.0926162843827106e-05,
+      "loss": 2.4298,
+      "step": 137316
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5783926471903155,
+      "eval_loss": 2.252242088317871,
+      "eval_runtime": 507.6768,
+      "eval_samples_per_second": 303.693,
+      "eval_steps_per_second": 4.747,
+      "step": 137316
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.0473590423101528e-05,
+      "loss": 2.2864,
+      "step": 183088
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.592032966422163,
+      "eval_loss": 2.1547858715057373,
+      "eval_runtime": 505.0498,
+      "eval_samples_per_second": 305.273,
+      "eval_steps_per_second": 4.772,
+      "step": 183088
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.0789545828383442e-08,
+      "loss": 2.2142,
+      "step": 228860
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5983179869567139,
+      "eval_loss": 2.1091487407684326,
+      "eval_runtime": 502.6673,
+      "eval_samples_per_second": 306.72,
+      "eval_steps_per_second": 4.794,
+      "step": 228860
+    },
+    {
+      "epoch": 5.0,
+      "step": 228860,
+      "total_flos": 3.65001542178177e+18,
+      "train_loss": 3.027850917318448,
+      "train_runtime": 97726.2074,
+      "train_samples_per_second": 149.877,
+      "train_steps_per_second": 2.342
+    }
+  ],
+  "max_steps": 228860,
+  "num_train_epochs": 5,
+  "total_flos": 3.65001542178177e+18,
+  "trial_name": null,
+  "trial_params": null
+}