End of training

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.5908326759211433,
+    "eval_loss": 2.1676268577575684,
+    "eval_runtime": 588.5812,
+    "eval_samples": 154178,
+    "eval_samples_per_second": 261.949,
+    "eval_steps_per_second": 2.047,
+    "perplexity": 8.73752402988492,
+    "train_loss": 3.446043330256489,
+    "train_runtime": 56381.9546,
+    "train_samples": 2929379,
+    "train_samples_per_second": 259.78,
+    "train_steps_per_second": 2.03
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.5908326759211433,
+    "eval_loss": 2.1676268577575684,
+    "eval_runtime": 588.5812,
+    "eval_samples": 154178,
+    "eval_samples_per_second": 261.949,
+    "eval_steps_per_second": 2.047,
+    "perplexity": 8.73752402988492
+}

logs/events.out.tfevents.1677560444.serv-3331.970357.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adde922881a20088bfe46556d86c00311c16e0794fd4a202bfff9534eabbdee9
+size 369

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 3.446043330256489,
+    "train_runtime": 56381.9546,
+    "train_samples": 2929379,
+    "train_samples_per_second": 259.78,
+    "train_steps_per_second": 2.03
+}

trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 2.1713204383850098,
+  "best_model_checkpoint": "bert_12_layer_model_v1/checkpoint-114430",
+  "epoch": 5.0,
+  "global_step": 114430,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.383366848606723e-05,
+      "loss": 6.293,
+      "step": 22886
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.17226526540143652,
+      "eval_loss": 5.639528274536133,
+      "eval_runtime": 477.3383,
+      "eval_samples_per_second": 322.995,
+      "eval_steps_per_second": 2.524,
+      "step": 22886
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.288087714258355e-05,
+      "loss": 3.7477,
+      "step": 45772
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5251830425896279,
+      "eval_loss": 2.662482738494873,
+      "eval_runtime": 581.5496,
+      "eval_samples_per_second": 265.116,
+      "eval_steps_per_second": 2.072,
+      "step": 45772
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 2.1927607009480036e-05,
+      "loss": 2.5641,
+      "step": 68658
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5673138370361093,
+      "eval_loss": 2.343093156814575,
+      "eval_runtime": 575.4194,
+      "eval_samples_per_second": 267.94,
+      "eval_steps_per_second": 2.094,
+      "step": 68658
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.0974336876376521e-05,
+      "loss": 2.3563,
+      "step": 91544
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.5838652826139948,
+      "eval_loss": 2.2187583446502686,
+      "eval_runtime": 579.1978,
+      "eval_samples_per_second": 266.192,
+      "eval_steps_per_second": 2.08,
+      "step": 91544
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.05879536531648e-08,
+      "loss": 2.2692,
+      "step": 114430
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5905086901184071,
+      "eval_loss": 2.1713204383850098,
+      "eval_runtime": 579.6724,
+      "eval_samples_per_second": 265.974,
+      "eval_steps_per_second": 2.079,
+      "step": 114430
+    },
+    {
+      "epoch": 5.0,
+      "step": 114430,
+      "total_flos": 3.701503489726218e+18,
+      "train_loss": 3.446043330256489,
+      "train_runtime": 56381.9546,
+      "train_samples_per_second": 259.78,
+      "train_steps_per_second": 2.03
+    }
+  ],
+  "max_steps": 114430,
+  "num_train_epochs": 5,
+  "total_flos": 3.701503489726218e+18,
+  "trial_name": null,
+  "trial_params": null
+}