Training in progress, step 500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e43d07ec730b99e0609243499fb9c9b7352d7b71f553eb3fe05bd7fe4ea734b
+oid sha256:a4b66b232cfe3c35cb59eec17d1bba9acc297396e1fa7c762e72c2bc83bccdf5
 size 88883845

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1db26081e2516f0f4541a4522cf5d3bd971de1eeb1d269d3e125373b01fed9
+oid sha256:a306f199dadca9c29199af89ce20e3d3329aa60985a7198283967f1ce71766e2
 size 44449417

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2215bd178ed740561f409d05123e5162c0e443007652bd536af7586e4a47f9bd
+oid sha256:1509ee85fa64f545e114cdaeb719c65524c2eabebb894701e5ac95a4915d5a78
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21ae5a62833995c1563a784b5f1cdc45460f2d612f79638c1eb8e763367a349e
+oid sha256:3a7964cc59dbcd4cafe1ff58736b1a37cf044babc53007397f39ade5c8183aa6
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
-  "best_metric": 0.43918731808662415,
-  "best_model_checkpoint": "./test-small-bert-with-loss-weight/checkpoint-1500",
-  "epoch": 1.4763779527559056,
-  "global_step": 1500,
+  "best_metric": 0.14738939702510834,
+  "best_model_checkpoint": "./test-small-bert-with-loss-weight/checkpoint-500",
+  "epoch": 0.4921259842519685,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -10,61 +10,25 @@
     {
       "epoch": 0.49,
       "learning_rate": 4.1797900262467194e-05,
-      "loss": 0.5221,
+      "loss": 0.1546,
       "step": 500
     },
     {
       "epoch": 0.49,
-      "eval_accuracy": 0.7981369412985216,
-      "eval_f1": 0.559788090457472,
-      "eval_loss": 0.47408804297447205,
-      "eval_precision": 0.4648381238649884,
-      "eval_recall": 0.7034852038761343,
-      "eval_runtime": 9.072,
-      "eval_samples_per_second": 1084.879,
-      "eval_steps_per_second": 4.299,
+      "eval_accuracy": 0.8429757067519668,
+      "eval_f1": 0.27041574613376174,
+      "eval_loss": 0.14738939702510834,
+      "eval_precision": 0.8877752868257945,
+      "eval_recall": 0.1594996090695856,
+      "eval_runtime": 8.7195,
+      "eval_samples_per_second": 1128.732,
+      "eval_steps_per_second": 4.473,
       "step": 500
-    },
-    {
-      "epoch": 0.98,
-      "learning_rate": 3.3595800524934386e-05,
-      "loss": 0.4802,
-      "step": 1000
-    },
-    {
-      "epoch": 0.98,
-      "eval_accuracy": 0.7898547592288406,
-      "eval_f1": 0.5730545285288977,
-      "eval_loss": 0.4475861191749573,
-      "eval_precision": 0.45528886408037955,
-      "eval_recall": 0.7729997393797238,
-      "eval_runtime": 8.8778,
-      "eval_samples_per_second": 1108.611,
-      "eval_steps_per_second": 4.393,
-      "step": 1000
-    },
-    {
-      "epoch": 1.48,
-      "learning_rate": 2.5393700787401574e-05,
-      "loss": 0.4616,
-      "step": 1500
-    },
-    {
-      "epoch": 1.48,
-      "eval_accuracy": 0.7831719546987118,
-      "eval_f1": 0.5731305687223958,
-      "eval_loss": 0.43918731808662415,
-      "eval_precision": 0.44718599771586415,
-      "eval_recall": 0.7978297438813466,
-      "eval_runtime": 9.3248,
-      "eval_samples_per_second": 1055.461,
-      "eval_steps_per_second": 4.182,
-      "step": 1500
     }
   ],
   "max_steps": 3048,
   "num_train_epochs": 3,
-  "total_flos": 465852985957632.0,
+  "total_flos": 155323564032000.0,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f78e51cdb55988f80e94c328e516b8025aedbf34269355824347fae368c890
+oid sha256:81d4ac1d3962683c36259631224ee7f99693fc3b5040a7f8d80a608346ac1fe7
 size 3515

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa1db26081e2516f0f4541a4522cf5d3bd971de1eeb1d269d3e125373b01fed9
+oid sha256:a306f199dadca9c29199af89ce20e3d3329aa60985a7198283967f1ce71766e2
 size 44449417

runs/Feb06_09-48-46_fadceb92582a/1675676932.2926033/events.out.tfevents.1675676932.fadceb92582a.597.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a600cba203b83f2ca7fd92079b6a0336ff447984624c16291af0cacf54cb57
+size 5734

runs/Feb06_09-48-46_fadceb92582a/events.out.tfevents.1675676932.fadceb92582a.597.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86c35be03a9b692dccc65911003be02ceee2a68056609db7171900bcc8e9308
+size 4595

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7f78e51cdb55988f80e94c328e516b8025aedbf34269355824347fae368c890
+oid sha256:81d4ac1d3962683c36259631224ee7f99693fc3b5040a7f8d80a608346ac1fe7
 size 3515