End of training

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.012880325317383,
+    "eval_runtime": 198.2994,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 10.086,
+    "eval_steps_per_second": 0.63,
+    "train_loss": 1.619314953175289,
+    "train_runtime": 7201.217,
+    "train_samples": 20000,
+    "train_samples_per_second": 8.332,
+    "train_steps_per_second": 0.694
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 2.012880325317383,
+    "eval_runtime": 198.2994,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 10.086,
+    "eval_steps_per_second": 0.63
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.619314953175289,
+    "train_runtime": 7201.217,
+    "train_samples": 20000,
+    "train_samples_per_second": 8.332,
+    "train_steps_per_second": 0.694
+}

trainer_state.json

@@ -0,0 +1,109 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 5001,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.3,
+      "learning_rate": 4.99001996007984e-05,
+      "loss": 3.6478,
+      "step": 500
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 4.445555555555555e-05,
+      "loss": 2.7964,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.8900000000000004e-05,
+      "loss": 2.66,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.064293622970581,
+      "eval_runtime": 200.8568,
+      "eval_samples_per_second": 9.957,
+      "eval_steps_per_second": 0.622,
+      "step": 1667
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.334444444444445e-05,
+      "loss": 2.5197,
+      "step": 2000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.7788888888888892e-05,
+      "loss": 2.4882,
+      "step": 2500
+    },
+    {
+      "epoch": 1.8,
+      "learning_rate": 2.2233333333333333e-05,
+      "loss": 2.472,
+      "step": 3000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.0240793228149414,
+      "eval_runtime": 212.8772,
+      "eval_samples_per_second": 9.395,
+      "eval_steps_per_second": 0.587,
+      "step": 3334
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 1.6677777777777777e-05,
+      "loss": 2.4282,
+      "step": 3500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.1122222222222223e-05,
+      "loss": 2.3806,
+      "step": 4000
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 5.566666666666667e-06,
+      "loss": 2.3865,
+      "step": 4500
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.1111111111111112e-08,
+      "loss": 2.3574,
+      "step": 5000
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.012880325317383,
+      "eval_runtime": 199.4135,
+      "eval_samples_per_second": 10.029,
+      "eval_steps_per_second": 0.627,
+      "step": 5001
+    },
+    {
+      "epoch": 3.0,
+      "step": 5001,
+      "total_flos": 1.8376153805625754e+17,
+      "train_loss": 1.619314953175289,
+      "train_runtime": 7201.217,
+      "train_samples_per_second": 8.332,
+      "train_steps_per_second": 0.694
+    }
+  ],
+  "max_steps": 5001,
+  "num_train_epochs": 3,
+  "total_flos": 1.8376153805625754e+17,
+  "trial_name": null,
+  "trial_params": null
+}