End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.715090274810791,
+    "eval_runtime": 394.1674,
+    "eval_samples": 10424,
+    "eval_samples_per_second": 26.446,
+    "eval_steps_per_second": 3.306,
+    "perplexity": 5.557177162834785,
+    "train_loss": 2.124942218677418,
+    "train_runtime": 17145.6045,
+    "train_samples": 59224,
+    "train_samples_per_second": 10.363,
+    "train_steps_per_second": 0.324
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.715090274810791,
+    "eval_runtime": 394.1674,
+    "eval_samples": 10424,
+    "eval_samples_per_second": 26.446,
+    "eval_steps_per_second": 3.306,
+    "perplexity": 5.557177162834785
+}

runs/Apr23_21-45-58_2c630289b464/events.out.tfevents.1650768119.2c630289b464.5399.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f8e4bbb51c9b8b5f0627c737ce71a6b100119424a9641c1e250853b2793637
+size 311

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.124942218677418,
+    "train_runtime": 17145.6045,
+    "train_samples": 59224,
+    "train_samples_per_second": 10.363,
+    "train_steps_per_second": 0.324
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": 1.6918816566467285,
+  "best_model_checkpoint": "models/checkpoint-5550",
+  "epoch": 2.9995947588815346,
+  "global_step": 5550,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.54954954954955e-05,
+      "loss": 3.1141,
+      "step": 500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 4.099099099099099e-05,
+      "loss": 2.4833,
+      "step": 1000
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.648648648648649e-05,
+      "loss": 2.2931,
+      "step": 1500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.991529107093811,
+      "eval_runtime": 392.0912,
+      "eval_samples_per_second": 26.586,
+      "eval_steps_per_second": 3.323,
+      "step": 1850
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 3.198198198198199e-05,
+      "loss": 2.1663,
+      "step": 2000
+    },
+    {
+      "epoch": 1.35,
+      "learning_rate": 2.7477477477477483e-05,
+      "loss": 2.0613,
+      "step": 2500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 2.2972972972972976e-05,
+      "loss": 1.9988,
+      "step": 3000
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 1.846846846846847e-05,
+      "loss": 1.9467,
+      "step": 3500
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.786591649055481,
+      "eval_runtime": 395.3774,
+      "eval_samples_per_second": 26.365,
+      "eval_steps_per_second": 3.296,
+      "step": 3700
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 1.3963963963963963e-05,
+      "loss": 1.8878,
+      "step": 4000
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 9.45945945945946e-06,
+      "loss": 1.8407,
+      "step": 4500
+    },
+    {
+      "epoch": 2.7,
+      "learning_rate": 4.954954954954955e-06,
+      "loss": 1.8165,
+      "step": 5000
+    },
+    {
+      "epoch": 2.97,
+      "learning_rate": 4.504504504504505e-07,
+      "loss": 1.7983,
+      "step": 5500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.6918816566467285,
+      "eval_runtime": 392.8778,
+      "eval_samples_per_second": 26.532,
+      "eval_steps_per_second": 3.317,
+      "step": 5550
+    },
+    {
+      "epoch": 3.0,
+      "step": 5550,
+      "total_flos": 1.787459999367168e+17,
+      "train_loss": 2.124942218677418,
+      "train_runtime": 17145.6045,
+      "train_samples_per_second": 10.363,
+      "train_steps_per_second": 0.324
+    }
+  ],
+  "max_steps": 5550,
+  "num_train_epochs": 3,
+  "total_flos": 1.787459999367168e+17,
+  "trial_name": null,
+  "trial_params": null
+}