Training in progress, epoch 2

config.json

@@ -15,8 +15,8 @@
   "initializer_range": 0.02,
   "intermediate_size": 512,
   "label2id": {
-    "negative": 0,
-    "positive": 1
+    "negative": "0",
+    "positive": "1"
   },
   "layer_norm_eps": 1e-12,
   "max_position_embeddings": 512,

logs/events.out.tfevents.1711296625.8cc2eef2edb7.2942.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0804651d934794d2f3432a085dac20bc07dbbf8d7a146946e40d42fab3e0e3d4
-size 5407
+oid sha256:6973212017b131d5027bfcd6fcf4c66a78bf985373f44472fa43302be836d429
+size 6137

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b786e1f0895234ea7a9fe0442335d74cac1176b9afdc2ded1c8ce0a27a538ce
+oid sha256:50dab4f218aa2736e49b3bc03c2401c3aa2cf3b09c88a31bf8f9e66c330ffaa4
 size 17549312

run-0/checkpoint-594/config.json

@@ -27,7 +27,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.38.2",
+  "transformers_version": "4.39.1",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

run-0/checkpoint-594/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:088e63b4c3a6c6cb565263cdb3909e74387b189e23b1faa39d6a055b6133c1f9
+oid sha256:50dab4f218aa2736e49b3bc03c2401c3aa2cf3b09c88a31bf8f9e66c330ffaa4
 size 17549312

run-0/checkpoint-594/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4690b24bf955cfbadddccdf8a2c13e2d999a82da5edd867355b1fdac79cac6c
-size 35122746
+oid sha256:66c3551ef9e34057e3a1dbfeaa7124f909a144226c4eb4d6abc830b896fde4a5
+size 35123898

run-0/checkpoint-594/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df6866d0dff400085edf68783c4718d94e08dcfa8f0d23f9d94ad3e230de2def
-size 14054
+oid sha256:07703232e8862ddf942921f960a4672ac4604f89da896da8b4bab92d3ecc94f2
+size 14308

run-0/checkpoint-594/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feb7146c9a68524856f100f015c06d1f6b4ff2e6bce26d842523fdd6ad8ddfd8
+oid sha256:4ad7545db207e67d6bb4e489b30269759aa0b2b49a31d2b14a3df648e2abdc7f
 size 1064

run-0/checkpoint-594/tokenizer.json

@@ -2,7 +2,7 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 33,
+    "max_length": 31,
     "strategy": "LongestFirst",
     "stride": 0
   },

run-0/checkpoint-594/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.5227722772277228,
-  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-594",
+  "best_metric": 0.5108910891089109,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-0/checkpoint-297",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 594,
@@ -10,49 +10,57 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.48113372921943665,
-      "learning_rate": 1.1539601014308473e-05,
-      "loss": 0.265,
+      "grad_norm": 0.3744499087333679,
+      "learning_rate": 1.7212091585793122e-05,
+      "loss": 0.1576,
       "step": 297
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.502970297029703,
-      "eval_loss": 0.24101482331752777,
-      "eval_runtime": 14.0847,
-      "eval_samples_per_second": 35.854,
-      "eval_steps_per_second": 1.136,
+      "eval_accuracy": 0.5108910891089109,
+      "eval_f1": 0.127208480565371,
+      "eval_loss": 0.13107798993587494,
+      "eval_mcc": 0.04175421326407947,
+      "eval_precision": 0.5806451612903226,
+      "eval_recall": 0.07142857142857142,
+      "eval_runtime": 0.9746,
+      "eval_samples_per_second": 518.155,
+      "eval_steps_per_second": 16.417,
       "step": 297
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.3685588538646698,
-      "learning_rate": 8.654700760731354e-06,
-      "loss": 0.2411,
+      "grad_norm": 0.2569155693054199,
+      "learning_rate": 1.5060580137568982e-05,
+      "loss": 0.1312,
       "step": 594
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5227722772277228,
-      "eval_loss": 0.23663455247879028,
-      "eval_runtime": 15.2033,
-      "eval_samples_per_second": 33.216,
-      "eval_steps_per_second": 1.052,
+      "eval_accuracy": 0.5089108910891089,
+      "eval_f1": 0.1205673758865248,
+      "eval_loss": 0.12648388743400574,
+      "eval_mcc": 0.03400602754322123,
+      "eval_precision": 0.5666666666666667,
+      "eval_recall": 0.06746031746031746,
+      "eval_runtime": 0.9581,
+      "eval_samples_per_second": 527.09,
+      "eval_steps_per_second": 16.7,
       "step": 594
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1485,
+  "max_steps": 2673,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 9,
   "save_steps": 500,
-  "total_flos": 1555686566280.0,
+  "total_flos": 1461402531960.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.28450461852175,
-    "learning_rate": 1.4424501267885591e-05,
-    "num_train_epochs": 5,
-    "temperature": 8
+    "alpha": 0.14400624333141754,
+    "learning_rate": 1.9363603034017264e-05,
+    "num_train_epochs": 9,
+    "temperature": 24
   }
 }

run-0/checkpoint-594/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:077f4108dc0cc2deb6d8b370dcd0cd733cd0d0661416c4baa607e842107e384b
-size 4984
+oid sha256:c912bc6fd00d5204347fd43667538d9d5c27c5837fabea72f3fbe2b6f790708e
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f62d580257060cdaf08ca2f6bebff447fe36fd6a4ed09c360f3a936d71824ec
+oid sha256:c912bc6fd00d5204347fd43667538d9d5c27c5837fabea72f3fbe2b6f790708e
 size 4920