fcsebuetnlp/banglabert-new

csebuetnlp/banglabert/checkpoint-8000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8792961eca66fa8a7c4737a4729c26d0571a50454572700fee429c4ab7df6e44
+size 880341733

csebuetnlp/banglabert/checkpoint-8000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f47bc3afb33671f5faf7de692d66c6ae19549cfb4369a8222f82449471467663
+size 440196977

csebuetnlp/banglabert/checkpoint-8000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6f666cb80b0a3ba24cd6a58768a539f6f1559d121adb3752b78526a3d4eb34b
+size 14503

csebuetnlp/banglabert/checkpoint-8000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45803f109d11da67ac8663f411272883599d138daeffce48a734439256fded2c
+size 623

csebuetnlp/banglabert/runs2/Jan14_13-43-45_4ac0fd88951a/1642167963.155689/events.out.tfevents.1642167963.4ac0fd88951a.2300.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab225fb619e8b9ed30643885a396aa30b2864739c32cfd954878601e4502a8af
+size 4924

csebuetnlp/banglabert/runs2/Jan14_13-43-45_4ac0fd88951a/events.out.tfevents.1642167963.4ac0fd88951a.2300.16

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:350237b7870d4ca868a8f144b665b1bc927a0fc8de8910b288fdb736c7d81f91
+size 5928

csebuetnlp/banglabert/trainer_state.json

@@ -0,0 +1,181 @@
+{
+  "best_metric": 0.7209533267130088,
+  "best_model_checkpoint": "./clickbait_identification/neuralspace-reverie/indic-transformers-bn-xlmroberta/checkpoint-8000",
+  "epoch": 3.635161929940516,
+  "global_step": 11000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.33,
+      "eval_accuracy": 0.7013372956909361,
+      "eval_f1": 0.32094594594594594,
+      "eval_loss": 0.5926413536071777,
+      "eval_precision": 0.7480314960629921,
+      "eval_recall": 0.20430107526881722,
+      "eval_runtime": 25.7194,
+      "eval_samples_per_second": 52.334,
+      "eval_steps_per_second": 13.103,
+      "step": 1000
+    },
+    {
+      "epoch": 0.66,
+      "eval_accuracy": 0.7332838038632986,
+      "eval_f1": 0.4665676077265974,
+      "eval_loss": 0.514832079410553,
+      "eval_precision": 0.7548076923076923,
+      "eval_recall": 0.33763440860215055,
+      "eval_runtime": 25.719,
+      "eval_samples_per_second": 52.335,
+      "eval_steps_per_second": 13.103,
+      "step": 2000
+    },
+    {
+      "epoch": 0.99,
+      "eval_accuracy": 0.7540861812778603,
+      "eval_f1": 0.6814244465832531,
+      "eval_loss": 0.49710002541542053,
+      "eval_precision": 0.6167247386759582,
+      "eval_recall": 0.7612903225806451,
+      "eval_runtime": 25.7279,
+      "eval_samples_per_second": 52.317,
+      "eval_steps_per_second": 13.099,
+      "step": 3000
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 1.9e-05,
+      "loss": 0.58,
+      "step": 3026
+    },
+    {
+      "epoch": 1.32,
+      "eval_accuracy": 0.7674591381872214,
+      "eval_f1": 0.6916256157635469,
+      "eval_loss": 0.628989577293396,
+      "eval_precision": 0.6381818181818182,
+      "eval_recall": 0.7548387096774194,
+      "eval_runtime": 25.7155,
+      "eval_samples_per_second": 52.342,
+      "eval_steps_per_second": 13.105,
+      "step": 4000
+    },
+    {
+      "epoch": 1.65,
+      "eval_accuracy": 0.7867756315007429,
+      "eval_f1": 0.6849615806805708,
+      "eval_loss": 0.6614874005317688,
+      "eval_precision": 0.6995515695067265,
+      "eval_recall": 0.6709677419354839,
+      "eval_runtime": 26.0668,
+      "eval_samples_per_second": 51.636,
+      "eval_steps_per_second": 12.928,
+      "step": 5000
+    },
+    {
+      "epoch": 1.98,
+      "eval_accuracy": 0.7838038632986627,
+      "eval_f1": 0.7063572149344096,
+      "eval_loss": 0.6481547951698303,
+      "eval_precision": 0.6653992395437263,
+      "eval_recall": 0.7526881720430108,
+      "eval_runtime": 25.9916,
+      "eval_samples_per_second": 51.786,
+      "eval_steps_per_second": 12.966,
+      "step": 6000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.8e-05,
+      "loss": 0.4892,
+      "step": 6052
+    },
+    {
+      "epoch": 2.31,
+      "eval_accuracy": 0.7800891530460624,
+      "eval_f1": 0.6613272311212814,
+      "eval_loss": 0.7997592687606812,
+      "eval_precision": 0.706601466992665,
+      "eval_recall": 0.621505376344086,
+      "eval_runtime": 14.3538,
+      "eval_samples_per_second": 93.773,
+      "eval_steps_per_second": 23.478,
+      "step": 7000
+    },
+    {
+      "epoch": 2.64,
+      "eval_accuracy": 0.7912332838038633,
+      "eval_f1": 0.7209533267130088,
+      "eval_loss": 0.7411750555038452,
+      "eval_precision": 0.6697416974169742,
+      "eval_recall": 0.7806451612903226,
+      "eval_runtime": 14.126,
+      "eval_samples_per_second": 95.285,
+      "eval_steps_per_second": 23.857,
+      "step": 8000
+    },
+    {
+      "epoch": 2.97,
+      "eval_accuracy": 0.7912332838038633,
+      "eval_f1": 0.6839145106861643,
+      "eval_loss": 0.730811595916748,
+      "eval_precision": 0.7169811320754716,
+      "eval_recall": 0.6537634408602151,
+      "eval_runtime": 14.1172,
+      "eval_samples_per_second": 95.345,
+      "eval_steps_per_second": 23.872,
+      "step": 9000
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.7e-05,
+      "loss": 0.5359,
+      "step": 9078
+    },
+    {
+      "epoch": 3.3,
+      "eval_accuracy": 0.7897473997028231,
+      "eval_f1": 0.7049009384775808,
+      "eval_loss": 0.8810334801673889,
+      "eval_precision": 0.6842105263157895,
+      "eval_recall": 0.7268817204301076,
+      "eval_runtime": 14.149,
+      "eval_samples_per_second": 95.13,
+      "eval_steps_per_second": 23.818,
+      "step": 10000
+    },
+    {
+      "epoch": 3.64,
+      "eval_accuracy": 0.787518573551263,
+      "eval_f1": 0.7008368200836819,
+      "eval_loss": 0.755975067615509,
+      "eval_precision": 0.6822810590631364,
+      "eval_recall": 0.7204301075268817,
+      "eval_runtime": 14.1239,
+      "eval_samples_per_second": 95.3,
+      "eval_steps_per_second": 23.86,
+      "step": 11000
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 1.6364838070059484e-05,
+      "loss": 0.5023,
+      "step": 11000
+    },
+    {
+      "epoch": 3.64,
+      "step": 11000,
+      "total_flos": 0.0,
+      "train_loss": 0.23749410299821333,
+      "train_runtime": 750.0737,
+      "train_samples_per_second": 322.688,
+      "train_steps_per_second": 80.685
+    }
+  ],
+  "max_steps": 60520,
+  "num_train_epochs": 20,
+  "total_flos": 0.0,
+  "trial_name": null,
+  "trial_params": null
+}