End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.7176,
+    "eval_loss": 0.5037732720375061,
+    "eval_runtime": 411.3387,
+    "eval_samples": 2985,
+    "eval_samples_per_second": 7.257,
+    "eval_steps_per_second": 0.455,
+    "train_loss": 0.3559933085336364,
+    "train_runtime": 23567.5036,
+    "train_samples": 25262,
+    "train_samples_per_second": 3.216,
+    "train_steps_per_second": 0.402
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.7176,
+    "eval_loss": 0.5037732720375061,
+    "eval_runtime": 411.3387,
+    "eval_samples": 2985,
+    "eval_samples_per_second": 7.257,
+    "eval_steps_per_second": 0.455
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a6683fa26306c09f5884cff374e417774782e1fd8755e2ae3e92b40017d9a4
+oid sha256:a7222da7fe8d6ab76854bd0a465fd8119132b6de1f105170b51c30cfb021a2f7
 size 891644863

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.3559933085336364,
+    "train_runtime": 23567.5036,
+    "train_samples": 25262,
+    "train_samples_per_second": 3.216,
+    "train_steps_per_second": 0.402
+}

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9997624891140844,
+  "global_step": 9471,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.573151211183439e-05,
+      "loss": 0.8108,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.039590225162736e-05,
+      "loss": 0.5534,
+      "step": 1000
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 8.506029239142035e-05,
+      "loss": 0.5264,
+      "step": 1500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 7.972468253121332e-05,
+      "loss": 0.4959,
+      "step": 2000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 7.438907267100629e-05,
+      "loss": 0.4691,
+      "step": 2500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 6.905346281079928e-05,
+      "loss": 0.4408,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6315,
+      "eval_loss": 0.4824552536010742,
+      "eval_runtime": 410.0505,
+      "eval_samples_per_second": 7.28,
+      "eval_steps_per_second": 0.456,
+      "step": 3157
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 6.371785295059226e-05,
+      "loss": 0.3701,
+      "step": 3500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.8382243090385235e-05,
+      "loss": 0.3268,
+      "step": 4000
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 5.304663323017821e-05,
+      "loss": 0.3306,
+      "step": 4500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 4.771102336997119e-05,
+      "loss": 0.3089,
+      "step": 5000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 4.237541350976417e-05,
+      "loss": 0.3093,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 3.703980364955715e-05,
+      "loss": 0.3166,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7109,
+      "eval_loss": 0.4108223021030426,
+      "eval_runtime": 410.3466,
+      "eval_samples_per_second": 7.274,
+      "eval_steps_per_second": 0.456,
+      "step": 6314
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 3.170419378935012e-05,
+      "loss": 0.2607,
+      "step": 6500
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 2.6368583929143105e-05,
+      "loss": 0.2,
+      "step": 7000
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 2.103297406893608e-05,
+      "loss": 0.2185,
+      "step": 7500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.569736420872906e-05,
+      "loss": 0.2082,
+      "step": 8000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 1.0361754348522035e-05,
+      "loss": 0.2113,
+      "step": 8500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.026144488315015e-06,
+      "loss": 0.2,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7176,
+      "eval_loss": 0.5037732720375061,
+      "eval_runtime": 410.0834,
+      "eval_samples_per_second": 7.279,
+      "eval_steps_per_second": 0.456,
+      "step": 9471
+    },
+    {
+      "epoch": 3.0,
+      "step": 9471,
+      "total_flos": 4.61468289466368e+16,
+      "train_loss": 0.3559933085336364,
+      "train_runtime": 23567.5036,
+      "train_samples_per_second": 3.216,
+      "train_steps_per_second": 0.402
+    }
+  ],
+  "max_steps": 9471,
+  "num_train_epochs": 3,
+  "total_flos": 4.61468289466368e+16,
+  "trial_name": null,
+  "trial_params": null
+}