End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.6067,
+    "eval_loss": 0.5614107251167297,
+    "eval_runtime": 114.688,
+    "eval_samples": 2985,
+    "eval_samples_per_second": 26.027,
+    "eval_steps_per_second": 1.631,
+    "train_loss": 0.441310719092838,
+    "train_runtime": 6663.2861,
+    "train_samples": 25262,
+    "train_samples_per_second": 11.374,
+    "train_steps_per_second": 1.422
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.6067,
+    "eval_loss": 0.5614107251167297,
+    "eval_runtime": 114.688,
+    "eval_samples": 2985,
+    "eval_samples_per_second": 26.027,
+    "eval_steps_per_second": 1.631
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7040b642bf4412d24fa8e9861745b8a57c2f54f0686e6ccfe4f73a605801147a
+oid sha256:0d56bd48676449309e8563dc79664e3fe113a3519bebc0bbbc5e2046c6720c4e
 size 242028283

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.441310719092838,
+    "train_runtime": 6663.2861,
+    "train_samples": 25262,
+    "train_samples_per_second": 11.374,
+    "train_steps_per_second": 1.422
+}

trainer_state.json

@@ -0,0 +1,160 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 9474,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "learning_rate": 5e-05,
+      "loss": 0.4827,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 0.0001,
+      "loss": 0.4887,
+      "step": 1000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 9.409959877271654e-05,
+      "loss": 0.5093,
+      "step": 1500
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 8.81991975454331e-05,
+      "loss": 0.4984,
+      "step": 2000
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 8.229879631814964e-05,
+      "loss": 0.4914,
+      "step": 2500
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 7.639839509086619e-05,
+      "loss": 0.4811,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5548,
+      "eval_loss": 0.5445399284362793,
+      "eval_runtime": 114.7335,
+      "eval_samples_per_second": 26.017,
+      "eval_steps_per_second": 1.63,
+      "step": 3158
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 7.049799386358273e-05,
+      "loss": 0.4623,
+      "step": 3500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 6.459759263629928e-05,
+      "loss": 0.4404,
+      "step": 4000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 5.869719140901582e-05,
+      "loss": 0.4558,
+      "step": 4500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 5.279679018173236e-05,
+      "loss": 0.4336,
+      "step": 5000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 4.68963889544489e-05,
+      "loss": 0.4375,
+      "step": 5500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 4.099598772716545e-05,
+      "loss": 0.4428,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5836,
+      "eval_loss": 0.5302113890647888,
+      "eval_runtime": 114.4324,
+      "eval_samples_per_second": 26.085,
+      "eval_steps_per_second": 1.634,
+      "step": 6316
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 3.5095586499881994e-05,
+      "loss": 0.4197,
+      "step": 6500
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 2.919518527259854e-05,
+      "loss": 0.3906,
+      "step": 7000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 2.3294784045315082e-05,
+      "loss": 0.3951,
+      "step": 7500
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.7394382818031625e-05,
+      "loss": 0.3966,
+      "step": 8000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 1.1493981590748172e-05,
+      "loss": 0.3946,
+      "step": 8500
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 5.5935803634647154e-06,
+      "loss": 0.3805,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6067,
+      "eval_loss": 0.5614107251167297,
+      "eval_runtime": 114.4577,
+      "eval_samples_per_second": 26.079,
+      "eval_steps_per_second": 1.634,
+      "step": 9474
+    },
+    {
+      "epoch": 3.0,
+      "step": 9474,
+      "total_flos": 1.0257013766356992e+16,
+      "train_loss": 0.441310719092838,
+      "train_runtime": 6663.2861,
+      "train_samples_per_second": 11.374,
+      "train_steps_per_second": 1.422
+    }
+  ],
+  "max_steps": 9474,
+  "num_train_epochs": 3,
+  "total_flos": 1.0257013766356992e+16,
+  "trial_name": null,
+  "trial_params": null
+}