Training in progress, step 2000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8e0e79a7a83f8d6c5da3c1219d679a9f73e1a64f33535e1427c8b07d4efdcdd
+oid sha256:63ed17cd5d69cfd14c439f9208e26666e5049a5f7c6be3ea47b308ff26c93cfa
 size 861965029

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b54d1db48c390e2aa766827b4b778f34a81d18da384628bd6055b79f0089620
+oid sha256:c32fa027261aa6406a0aa449c9993ac247bcab32a17c256ade795f1069197b67
 size 431008241

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fa55671a3580107240d729cd7668202e19cfe9ced85cf63192c87c239366db8
+oid sha256:4c0dcd6c769303cf359205c8d5160a859bbff9b742235db157eca3f13a64b6e5
 size 17563

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcddb40dc24b0f5884040379936f3e8e69d7789af11443275c0d7c46029c5402
+oid sha256:9962220360679d8e10cf7e904b5520efefc5b243afdd605a267181a14c7f58b0
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.7458701475198578,
-  "best_model_checkpoint": "./tokcl_models/EMBO_bert-base-cased_NER-task/checkpoint-1000",
-  "epoch": 1.310615989515072,
-  "global_step": 1000,
+  "best_metric": 0.771723286444866,
+  "best_model_checkpoint": "./tokcl_models/EMBO_bert-base-cased_NER-task/checkpoint-2000",
+  "epoch": 2.621231979030144,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -138,11 +138,143 @@
       "eval_samples_per_second": 123.99,
       "eval_steps_per_second": 0.97,
       "step": 1000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.00036238532110091746,
+      "loss": 0.1825,
+      "step": 1050
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 0.0003558322411533421,
+      "loss": 0.1898,
+      "step": 1100
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 0.0003492791612057667,
+      "loss": 0.1858,
+      "step": 1150
+    },
+    {
+      "epoch": 1.57,
+      "learning_rate": 0.0003427260812581914,
+      "loss": 0.182,
+      "step": 1200
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 0.000336173001310616,
+      "loss": 0.1853,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 0.0003296199213630406,
+      "loss": 0.1869,
+      "step": 1300
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 0.0003230668414154653,
+      "loss": 0.1771,
+      "step": 1350
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 0.0003165137614678899,
+      "loss": 0.1759,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 0.00030996068152031454,
+      "loss": 0.1705,
+      "step": 1450
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 0.00030340760157273916,
+      "loss": 0.1786,
+      "step": 1500
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 0.00029685452162516384,
+      "loss": 0.1589,
+      "step": 1550
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 0.00029030144167758846,
+      "loss": 0.1364,
+      "step": 1600
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 0.00028374836173001314,
+      "loss": 0.1319,
+      "step": 1650
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 0.00027719528178243776,
+      "loss": 0.1283,
+      "step": 1700
+    },
+    {
+      "epoch": 2.29,
+      "learning_rate": 0.0002706422018348624,
+      "loss": 0.1266,
+      "step": 1750
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 0.000264089121887287,
+      "loss": 0.1359,
+      "step": 1800
+    },
+    {
+      "epoch": 2.42,
+      "learning_rate": 0.0002575360419397117,
+      "loss": 0.1271,
+      "step": 1850
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 0.0002509829619921363,
+      "loss": 0.1328,
+      "step": 1900
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 0.000244429882044561,
+      "loss": 0.1328,
+      "step": 1950
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 0.0002378768020969856,
+      "loss": 0.138,
+      "step": 2000
+    },
+    {
+      "epoch": 2.62,
+      "eval_accuracy_score": 0.9121489075478695,
+      "eval_f1": 0.771723286444866,
+      "eval_loss": 0.2743813991546631,
+      "eval_precision": 0.751326535173136,
+      "eval_recall": 0.7932583890920736,
+      "eval_runtime": 111.6996,
+      "eval_samples_per_second": 123.555,
+      "eval_steps_per_second": 0.967,
+      "step": 2000
     }
   ],
   "max_steps": 3815,
   "num_train_epochs": 5,
-  "total_flos": 1.139953338400401e+16,
+  "total_flos": 2.283293725774362e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b54d1db48c390e2aa766827b4b778f34a81d18da384628bd6055b79f0089620
+oid sha256:c32fa027261aa6406a0aa449c9993ac247bcab32a17c256ade795f1069197b67
 size 431008241

runs/May20_12-43-43_9288e76c4417/events.out.tfevents.1653050648.9288e76c4417.830.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83cbcf1822635c478dede77180c40bf9aa26892caa42abaf69351c9324581801
-size 7785
+oid sha256:63372c2b6f1aa18b43dd0c330803479732d2191a9edc3b644cf43dcc964e1c5a
+size 11403