Finished training

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.15,
+    "train_loss": 2.8869726932965794,
+    "train_runtime": 1925.7546,
+    "train_samples_per_second": 953.779,
+    "train_steps_per_second": 0.117
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a55337cd624737cca9b3cbe986546ff42ab186a113b851fa5460c26cedaf086b
+oid sha256:b8b0db81786ce65a6aa118c68e7152d9951cf5f96890c97ad998cfea4311becf
 size 438128811

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.15,
+    "train_loss": 2.8869726932965794,
+    "train_runtime": 1925.7546,
+    "train_samples_per_second": 953.779,
+    "train_steps_per_second": 0.117
+}

trainer_state.json

@@ -0,0 +1,202 @@
+{
+  "best_metric": 0.3793538836642285,
+  "best_model_checkpoint": "/xdisk/msurdeanu/enoriega/kw_pubmed/kw_pubmed_1000_0.00006/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": 0.3767850923023337,
+      "eval_loss": 3.902531385421753,
+      "eval_runtime": 16.573,
+      "eval_samples_per_second": 603.393,
+      "eval_steps_per_second": 18.886,
+      "step": 4
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 5.8666666666666665e-05,
+      "loss": 4.0323,
+      "step": 5
+    },
+    {
+      "epoch": 0.17,
+      "eval_accuracy": 0.37399860675722746,
+      "eval_loss": 3.8996994495391846,
+      "eval_runtime": 16.5623,
+      "eval_samples_per_second": 603.78,
+      "eval_steps_per_second": 18.898,
+      "step": 8
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 5.7333333333333336e-05,
+      "loss": 3.4655,
+      "step": 10
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 0.3793538836642285,
+      "eval_loss": 3.9113454818725586,
+      "eval_runtime": 16.5561,
+      "eval_samples_per_second": 604.006,
+      "eval_steps_per_second": 18.905,
+      "step": 12
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 5.6e-05,
+      "loss": 3.1532,
+      "step": 15
+    },
+    {
+      "epoch": 0.35,
+      "eval_accuracy": 0.3754353883664229,
+      "eval_loss": 3.9654853343963623,
+      "eval_runtime": 16.5341,
+      "eval_samples_per_second": 604.812,
+      "eval_steps_per_second": 18.931,
+      "step": 16
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 5.466666666666667e-05,
+      "loss": 2.9457,
+      "step": 20
+    },
+    {
+      "epoch": 0.44,
+      "eval_accuracy": 0.3714733542319749,
+      "eval_loss": 4.051833629608154,
+      "eval_runtime": 16.5251,
+      "eval_samples_per_second": 605.14,
+      "eval_steps_per_second": 18.941,
+      "step": 20
+    },
+    {
+      "epoch": 0.52,
+      "eval_accuracy": 0.36964472309299895,
+      "eval_loss": 4.067558765411377,
+      "eval_runtime": 16.4933,
+      "eval_samples_per_second": 606.306,
+      "eval_steps_per_second": 18.977,
+      "step": 24
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 5.36e-05,
+      "loss": 2.7639,
+      "step": 25
+    },
+    {
+      "epoch": 0.61,
+      "eval_accuracy": 0.3722570532915361,
+      "eval_loss": 4.092674255371094,
+      "eval_runtime": 16.5366,
+      "eval_samples_per_second": 604.721,
+      "eval_steps_per_second": 18.928,
+      "step": 28
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.2266666666666665e-05,
+      "loss": 2.6542,
+      "step": 30
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.37169104841518635,
+      "eval_loss": 4.114505290985107,
+      "eval_runtime": 16.541,
+      "eval_samples_per_second": 604.559,
+      "eval_steps_per_second": 18.923,
+      "step": 32
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 5.0933333333333336e-05,
+      "loss": 2.5371,
+      "step": 35
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.3714733542319749,
+      "eval_loss": 4.133761882781982,
+      "eval_runtime": 16.5877,
+      "eval_samples_per_second": 602.858,
+      "eval_steps_per_second": 18.869,
+      "step": 36
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 4.96e-05,
+      "loss": 2.4884,
+      "step": 40
+    },
+    {
+      "epoch": 0.87,
+      "eval_accuracy": 0.3642894461859979,
+      "eval_loss": 4.216277599334717,
+      "eval_runtime": 16.5043,
+      "eval_samples_per_second": 605.903,
+      "eval_steps_per_second": 18.965,
+      "step": 40
+    },
+    {
+      "epoch": 0.96,
+      "eval_accuracy": 0.36920933472657613,
+      "eval_loss": 4.178205490112305,
+      "eval_runtime": 16.5055,
+      "eval_samples_per_second": 605.86,
+      "eval_steps_per_second": 18.963,
+      "step": 44
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 4.826666666666666e-05,
+      "loss": 2.3936,
+      "step": 45
+    },
+    {
+      "epoch": 1.07,
+      "eval_accuracy": 0.3670323928944619,
+      "eval_loss": 4.243963718414307,
+      "eval_runtime": 16.5457,
+      "eval_samples_per_second": 604.386,
+      "eval_steps_per_second": 18.917,
+      "step": 48
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 4.693333333333334e-05,
+      "loss": 2.694,
+      "step": 50
+    },
+    {
+      "epoch": 1.15,
+      "eval_accuracy": 0.36733716475095785,
+      "eval_loss": 4.244164943695068,
+      "eval_runtime": 16.5637,
+      "eval_samples_per_second": 603.731,
+      "eval_steps_per_second": 18.897,
+      "step": 52
+    },
+    {
+      "epoch": 1.15,
+      "step": 52,
+      "total_flos": 3.18987289303776e+16,
+      "train_loss": 2.8869726932965794,
+      "train_runtime": 1925.7546,
+      "train_samples_per_second": 953.779,
+      "train_steps_per_second": 0.117
+    }
+  ],
+  "max_steps": 225,
+  "num_train_epochs": 5,
+  "total_flos": 3.18987289303776e+16,
+  "trial_name": null,
+  "trial_params": null
+}