Training in progress, epoch 1

logs/events.out.tfevents.1711296799.8cc2eef2edb7.2942.1

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ed6243de1b4126f38bda31247c0cdb569e0d85fd2368ac42cc28ee9b6056e27
-size 6136
+oid sha256:1f1a5654e3d6fba66852b0b3fdbbe538b4d682b3fd4796ddd8536724429535cd
+size 7220

logs/events.out.tfevents.1711296858.8cc2eef2edb7.2942.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9474f9bb69d62b8f8bbe6dd7caf55abc5b4f0dc9fc15dfe2101e9aa6fdd738c
+size 5407

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4e4ed65de241fa382d9773b2e0209cc2134af774c4ee35f8d263835c2997d29
+oid sha256:fcd6611d9aeb31d0657795a4eaca47f364cd69272d929d8b6df5c3bda9e50e99
 size 17549312

run-1/checkpoint-891/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-1/checkpoint-891/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dad2c00079bf827d9e719db18d4c86aa796e128a9e02878962ed25adb3bcd1b
+oid sha256:9040181db8d76005f676d97b5534a17a4eb2972656beafd2186dc0a419359f6a
 size 17549312

run-1/checkpoint-891/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f743eb06051cc7a52c530b8568ca77b298b705e7ad276b49dc748f0572f28ee2
-size 35122746
+oid sha256:5e2af4c26f15a15ff765a52e923766a4900ce6828c6c1331d3fd8bfb0624998a
+size 35123898

run-1/checkpoint-891/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8825af3ee3a915f6774d349057db9cb8bcc74ea981ae299e1cb35993773495a5
-size 14054
+oid sha256:45b689ca5add5bd2b3024a96e15979227e5788dfce70568554fb1702c585abab
+size 14308

run-1/checkpoint-891/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48269bd025e4a2a9251c6dba3b071353cc95ee138f476ea609464c3d7a8e9248
+oid sha256:291008d3b6238846646f9b85fa92243b0cc21db6c35ba667d2fe4cc4e955c671
 size 1064

run-1/checkpoint-891/tokenizer.json

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

run-1/checkpoint-891/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.6495049504950495,
-  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-891",
+  "best_metric": 0.5425742574257426,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-1/checkpoint-594",
   "epoch": 3.0,
   "eval_steps": 500,
   "global_step": 891,
@@ -10,65 +10,77 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 1.3426679372787476,
-      "learning_rate": 0.0003560526201910554,
-      "loss": 0.6371,
+      "grad_norm": 0.9758312702178955,
+      "learning_rate": 2.4789676674761582e-05,
+      "loss": 0.4903,
       "step": 297
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5841584158415841,
-      "eval_loss": 0.637409508228302,
-      "eval_runtime": 56.7978,
-      "eval_samples_per_second": 8.891,
-      "eval_steps_per_second": 0.282,
+      "eval_accuracy": 0.502970297029703,
+      "eval_f1": 0.08058608058608059,
+      "eval_loss": 0.48342981934547424,
+      "eval_mcc": 0.010331488326433175,
+      "eval_precision": 0.5238095238095238,
+      "eval_recall": 0.04365079365079365,
+      "eval_runtime": 0.9315,
+      "eval_samples_per_second": 542.124,
+      "eval_steps_per_second": 17.176,
       "step": 297
     },
     {
       "epoch": 2.0,
-      "grad_norm": 1.018396258354187,
-      "learning_rate": 0.0002373684134607036,
-      "loss": 0.603,
+      "grad_norm": 0.7211948037147522,
+      "learning_rate": 1.2394838337380791e-05,
+      "loss": 0.4812,
       "step": 594
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6277227722772277,
-      "eval_loss": 0.6017976403236389,
-      "eval_runtime": 55.6441,
-      "eval_samples_per_second": 9.076,
-      "eval_steps_per_second": 0.288,
+      "eval_accuracy": 0.5425742574257426,
+      "eval_f1": 0.3773584905660377,
+      "eval_loss": 0.4795511066913605,
+      "eval_mcc": 0.09908299956847767,
+      "eval_precision": 0.5882352941176471,
+      "eval_recall": 0.2777777777777778,
+      "eval_runtime": 0.9303,
+      "eval_samples_per_second": 542.812,
+      "eval_steps_per_second": 17.198,
       "step": 594
     },
     {
       "epoch": 3.0,
-      "grad_norm": 1.4982593059539795,
-      "learning_rate": 0.0001186842067303518,
-      "loss": 0.588,
+      "grad_norm": 0.8099855184555054,
+      "learning_rate": 0.0,
+      "loss": 0.4778,
       "step": 891
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6495049504950495,
-      "eval_loss": 0.5974766612052917,
-      "eval_runtime": 55.1255,
-      "eval_samples_per_second": 9.161,
-      "eval_steps_per_second": 0.29,
+      "eval_accuracy": 0.5326732673267327,
+      "eval_f1": 0.32954545454545453,
+      "eval_loss": 0.47736045718193054,
+      "eval_mcc": 0.08048876531271514,
+      "eval_precision": 0.58,
+      "eval_recall": 0.23015873015873015,
+      "eval_runtime": 0.9394,
+      "eval_samples_per_second": 537.574,
+      "eval_steps_per_second": 17.032,
       "step": 891
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1188,
+  "max_steps": 891,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 4,
+  "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 2333529849420.0,
+  "total_flos": 2192103797940.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.900582717199523,
-    "learning_rate": 0.0004747368269214072,
-    "num_train_epochs": 4,
-    "temperature": 18
+    "alpha": 0.6389006598546823,
+    "learning_rate": 3.718451501214238e-05,
+    "num_train_epochs": 3,
+    "temperature": 17
   }
 }

run-1/checkpoint-891/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f636dbab8b5e516bcd85051f9f0732a28727ed1675f1d1f3076c7baf2be402
-size 4984
+oid sha256:b6731b358035f4120a393e277eadf83407dfaf70785f0599f775fe36a1054fb1
+size 4920

run-2/checkpoint-297/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-2/checkpoint-297/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae39d29dd9e95b52e3db360285f2fd6ef5b67eb60eaf84ca0b63e30e0a570a1b
+oid sha256:fcd6611d9aeb31d0657795a4eaca47f364cd69272d929d8b6df5c3bda9e50e99
 size 17549312

run-2/checkpoint-297/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:106f6d7312d0b8cbbb01e4e6f8733e13f510903a2af457faaaa23790cbf88dc6
-size 35122746
+oid sha256:2b5715f10ee578dc0e25cbb1e64595d2d14801c8fac136a5b282b868d389c6ae
+size 35123898

run-2/checkpoint-297/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f414017d19e8a66d09e6a16c0bca909eff6c9e5541f54da3f0dba2607378e04d
-size 14054
+oid sha256:a5f5e396c574b9b2ecc40d3f9e87d628a8f4be69caef81905a47fcf8895067e6
+size 14308

run-2/checkpoint-297/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e29f4582b08e2f0e75667a827e9b21c66b9a7caa9edd4095c8bbdf663e5ee13f
+oid sha256:eec7f7712dcbdabc9e134706fd1460f920b47b7ffce0b705c1cbe548ebce60db
 size 1064

run-2/checkpoint-297/tokenizer.json

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

run-2/checkpoint-297/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.497029702970297,
+  "best_metric": 0.4910891089108911,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-2/checkpoint-297",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,18 +10,22 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.46941760182380676,
-      "learning_rate": 1.0066413527942762e-05,
-      "loss": 0.2155,
+      "grad_norm": 0.6258772015571594,
+      "learning_rate": 1.171336966673164e-05,
+      "loss": 0.303,
       "step": 297
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.497029702970297,
-      "eval_loss": 0.18417517840862274,
-      "eval_runtime": 14.6034,
-      "eval_samples_per_second": 34.581,
-      "eval_steps_per_second": 1.096,
+      "eval_accuracy": 0.4910891089108911,
+      "eval_f1": 0.0,
+      "eval_loss": 0.28316354751586914,
+      "eval_mcc": -0.09980217586956908,
+      "eval_precision": 0.0,
+      "eval_recall": 0.0,
+      "eval_runtime": 0.9281,
+      "eval_samples_per_second": 544.113,
+      "eval_steps_per_second": 17.239,
       "step": 297
     }
   ],
@@ -30,13 +34,13 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 9,
   "save_steps": 500,
-  "total_flos": 777843283140.0,
+  "total_flos": 730701265980.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.20650329892275032,
-    "learning_rate": 1.1324715218935609e-05,
+    "alpha": 0.33782488262757904,
+    "learning_rate": 1.3177540875073095e-05,
     "num_train_epochs": 9,
-    "temperature": 10
+    "temperature": 26
   }
 }

run-2/checkpoint-297/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53af5913dd7a7ac18c4af82b6aa52534a7091d8ef8c41f1056aa7fa989430b5d
-size 4984
+oid sha256:28b3023982056159c033a3a1a25c2d159010d9ff247770a44c7d7d6d0e3bba5b
+size 4920

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0df23de5f2d7c569f8878223b016d804cf54077b0824a5d63ecc274595ea3eea
-size 4984
+oid sha256:28b3023982056159c033a3a1a25c2d159010d9ff247770a44c7d7d6d0e3bba5b
+size 4920