Training in progress, step 3000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63ed17cd5d69cfd14c439f9208e26666e5049a5f7c6be3ea47b308ff26c93cfa
+oid sha256:0955c1d3b650c9c643c7f2178954f57982b9878d21c7ba1e5fef1f25104b7e68
 size 861965029

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c32fa027261aa6406a0aa449c9993ac247bcab32a17c256ade795f1069197b67
+oid sha256:92b2fea8cd086661eb988c0bea7b142c1c168e6b3db297f20e8b9b74ffd60ccc
 size 431008241

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c0dcd6c769303cf359205c8d5160a859bbff9b742235db157eca3f13a64b6e5
+oid sha256:d51440174fac5a2f22180e2bf7f977b03667d6fdb023d528355e7cdff335590f
 size 17563

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9962220360679d8e10cf7e904b5520efefc5b243afdd605a267181a14c7f58b0
+oid sha256:90caf14b68a6b815c7f5bccb73a9ee2a50f47182fd7f745e59257531952eaeb8
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": 0.771723286444866,
   "best_model_checkpoint": "./tokcl_models/EMBO_bert-base-cased_NER-task/checkpoint-2000",
-  "epoch": 2.621231979030144,
-  "global_step": 2000,
+  "epoch": 3.9318479685452163,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -270,11 +270,143 @@
       "eval_samples_per_second": 123.555,
       "eval_steps_per_second": 0.967,
       "step": 2000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 0.00023132372214941022,
+      "loss": 0.1305,
+      "step": 2050
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 0.00022477064220183487,
+      "loss": 0.1243,
+      "step": 2100
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 0.00021821756225425952,
+      "loss": 0.1265,
+      "step": 2150
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 0.00021166448230668415,
+      "loss": 0.133,
+      "step": 2200
+    },
+    {
+      "epoch": 2.95,
+      "learning_rate": 0.00020511140235910877,
+      "loss": 0.1298,
+      "step": 2250
+    },
+    {
+      "epoch": 3.01,
+      "learning_rate": 0.00019855832241153344,
+      "loss": 0.123,
+      "step": 2300
+    },
+    {
+      "epoch": 3.08,
+      "learning_rate": 0.00019200524246395807,
+      "loss": 0.0871,
+      "step": 2350
+    },
+    {
+      "epoch": 3.15,
+      "learning_rate": 0.0001854521625163827,
+      "loss": 0.086,
+      "step": 2400
+    },
+    {
+      "epoch": 3.21,
+      "learning_rate": 0.00017889908256880736,
+      "loss": 0.0928,
+      "step": 2450
+    },
+    {
+      "epoch": 3.28,
+      "learning_rate": 0.000172346002621232,
+      "loss": 0.083,
+      "step": 2500
+    },
+    {
+      "epoch": 3.34,
+      "learning_rate": 0.0001657929226736566,
+      "loss": 0.0918,
+      "step": 2550
+    },
+    {
+      "epoch": 3.41,
+      "learning_rate": 0.00015923984272608129,
+      "loss": 0.0849,
+      "step": 2600
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 0.0001526867627785059,
+      "loss": 0.0863,
+      "step": 2650
+    },
+    {
+      "epoch": 3.54,
+      "learning_rate": 0.00014613368283093053,
+      "loss": 0.0865,
+      "step": 2700
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 0.00013958060288335518,
+      "loss": 0.0827,
+      "step": 2750
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 0.00013302752293577983,
+      "loss": 0.083,
+      "step": 2800
+    },
+    {
+      "epoch": 3.74,
+      "learning_rate": 0.00012647444298820445,
+      "loss": 0.0849,
+      "step": 2850
+    },
+    {
+      "epoch": 3.8,
+      "learning_rate": 0.0001199213630406291,
+      "loss": 0.0813,
+      "step": 2900
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 0.00011336828309305374,
+      "loss": 0.0873,
+      "step": 2950
+    },
+    {
+      "epoch": 3.93,
+      "learning_rate": 0.00010681520314547838,
+      "loss": 0.0808,
+      "step": 3000
+    },
+    {
+      "epoch": 3.93,
+      "eval_accuracy_score": 0.909553294853392,
+      "eval_f1": 0.7627703980346628,
+      "eval_loss": 0.3164892792701721,
+      "eval_precision": 0.7620479900951458,
+      "eval_recall": 0.7634941769335782,
+      "eval_runtime": 111.6078,
+      "eval_samples_per_second": 123.656,
+      "eval_steps_per_second": 0.968,
+      "step": 3000
     }
   ],
   "max_steps": 3815,
   "num_train_epochs": 5,
-  "total_flos": 2.283293725774362e+16,
+  "total_flos": 3.419886505231602e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c32fa027261aa6406a0aa449c9993ac247bcab32a17c256ade795f1069197b67
+oid sha256:92b2fea8cd086661eb988c0bea7b142c1c168e6b3db297f20e8b9b74ffd60ccc
 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 sha256:63372c2b6f1aa18b43dd0c330803479732d2191a9edc3b644cf43dcc964e1c5a
-size 11403
+oid sha256:e4b13de66060a370e6de71ea674d2e02faa4ec319763ec20f9ff2d1e8b45be73
+size 15021