Finished training

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.15,
+    "train_loss": 2.93648067345986,
+    "train_runtime": 1938.9621,
+    "train_samples_per_second": 947.283,
+    "train_steps_per_second": 0.116
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:781b6898c3f35643638edb54bac15599c8f1fb9e9b9bf4cad96eaf65973b473b
+oid sha256:962769cb81d8c4950d11ada96f668a837d241f7ae01cf8e34047ca631da7b979
 size 438128811

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.15,
+    "train_loss": 2.93648067345986,
+    "train_runtime": 1938.9621,
+    "train_samples_per_second": 947.283,
+    "train_steps_per_second": 0.116
+}

trainer_state.json

@@ -0,0 +1,202 @@
+{
+  "best_metric": 0.3634186694531522,
+  "best_model_checkpoint": "/xdisk/msurdeanu/enoriega/kw_pubmed/kw_pubmed_1000_0.0003/checkpoint-12",
+  "epoch": 1.1524390243902438,
+  "global_step": 52,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "eval_accuracy": 0.3436084987809126,
+      "eval_loss": 4.372271537780762,
+      "eval_runtime": 16.6642,
+      "eval_samples_per_second": 600.088,
+      "eval_steps_per_second": 18.783,
+      "step": 4
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 0.00029466666666666666,
+      "loss": 6.0386,
+      "step": 5
+    },
+    {
+      "epoch": 0.17,
+      "eval_accuracy": 0.34417450365726227,
+      "eval_loss": 4.2112579345703125,
+      "eval_runtime": 16.5968,
+      "eval_samples_per_second": 602.524,
+      "eval_steps_per_second": 18.859,
+      "step": 8
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002893333333333333,
+      "loss": 3.7573,
+      "step": 10
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 0.3634186694531522,
+      "eval_loss": 4.2079362869262695,
+      "eval_runtime": 16.5847,
+      "eval_samples_per_second": 602.965,
+      "eval_steps_per_second": 18.873,
+      "step": 12
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.00028266666666666663,
+      "loss": 2.9944,
+      "step": 15
+    },
+    {
+      "epoch": 0.35,
+      "eval_accuracy": 0.3512713340299547,
+      "eval_loss": 4.3369622230529785,
+      "eval_runtime": 16.6084,
+      "eval_samples_per_second": 602.106,
+      "eval_steps_per_second": 18.846,
+      "step": 16
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 0.000276,
+      "loss": 2.7048,
+      "step": 20
+    },
+    {
+      "epoch": 0.44,
+      "eval_accuracy": 0.30673110414489724,
+      "eval_loss": 4.859361171722412,
+      "eval_runtime": 16.6048,
+      "eval_samples_per_second": 602.234,
+      "eval_steps_per_second": 18.85,
+      "step": 20
+    },
+    {
+      "epoch": 0.52,
+      "eval_accuracy": 0.3382967607105538,
+      "eval_loss": 4.492859840393066,
+      "eval_runtime": 16.5439,
+      "eval_samples_per_second": 604.454,
+      "eval_steps_per_second": 18.919,
+      "step": 24
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00027066666666666667,
+      "loss": 2.9458,
+      "step": 25
+    },
+    {
+      "epoch": 0.61,
+      "eval_accuracy": 0.34077847439916403,
+      "eval_loss": 4.514556884765625,
+      "eval_runtime": 16.5866,
+      "eval_samples_per_second": 602.897,
+      "eval_steps_per_second": 18.871,
+      "step": 28
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 0.00026399999999999997,
+      "loss": 2.3783,
+      "step": 30
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.3429989550679206,
+      "eval_loss": 4.5680060386657715,
+      "eval_runtime": 16.5703,
+      "eval_samples_per_second": 603.491,
+      "eval_steps_per_second": 18.889,
+      "step": 32
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 0.0002573333333333333,
+      "loss": 2.2485,
+      "step": 35
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.34770114942528735,
+      "eval_loss": 4.509522914886475,
+      "eval_runtime": 16.5871,
+      "eval_samples_per_second": 602.877,
+      "eval_steps_per_second": 18.87,
+      "step": 36
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 0.00025066666666666667,
+      "loss": 2.1701,
+      "step": 40
+    },
+    {
+      "epoch": 0.87,
+      "eval_accuracy": 0.3449146638801811,
+      "eval_loss": 4.4971489906311035,
+      "eval_runtime": 16.5577,
+      "eval_samples_per_second": 603.949,
+      "eval_steps_per_second": 18.904,
+      "step": 40
+    },
+    {
+      "epoch": 0.96,
+      "eval_accuracy": 0.33207070707070707,
+      "eval_loss": 4.7050604820251465,
+      "eval_runtime": 16.5693,
+      "eval_samples_per_second": 603.527,
+      "eval_steps_per_second": 18.89,
+      "step": 44
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 0.000244,
+      "loss": 2.0861,
+      "step": 45
+    },
+    {
+      "epoch": 1.07,
+      "eval_accuracy": 0.3310257749912922,
+      "eval_loss": 4.761545658111572,
+      "eval_runtime": 16.5548,
+      "eval_samples_per_second": 604.054,
+      "eval_steps_per_second": 18.907,
+      "step": 48
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 0.00023733333333333332,
+      "loss": 2.4168,
+      "step": 50
+    },
+    {
+      "epoch": 1.15,
+      "eval_accuracy": 0.33938523162661094,
+      "eval_loss": 4.7085795402526855,
+      "eval_runtime": 16.5811,
+      "eval_samples_per_second": 603.096,
+      "eval_steps_per_second": 18.877,
+      "step": 52
+    },
+    {
+      "epoch": 1.15,
+      "step": 52,
+      "total_flos": 3.18987289303776e+16,
+      "train_loss": 2.93648067345986,
+      "train_runtime": 1938.9621,
+      "train_samples_per_second": 947.283,
+      "train_steps_per_second": 0.116
+    }
+  ],
+  "max_steps": 225,
+  "num_train_epochs": 5,
+  "total_flos": 3.18987289303776e+16,
+  "trial_name": null,
+  "trial_params": null
+}