Training in progress, epoch 2

logs/events.out.tfevents.1711297090.8cc2eef2edb7.2942.4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:feaf25b48afd5cec13c72a7309deddfd25015ebc1d48e8d78c23c22c7d99e770
-size 5406
+oid sha256:890180357e2c6c1e9c781ffc2dd5737c5625af93c3736ae37f5f754885bf507d
+size 6136

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3efb3ab4c0e91a15fd6119f8b7e090eafed10aac6dc177239fc7ebfc74974753
+oid sha256:a1373d9a02412908ee3ce5bab868f7cbec3faa136e3d1694a1fe4ce56b314f5d
 size 17549312

run-4/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-4/checkpoint-594/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a9f5899de3a13fc33628c62536f81bcc454491bdf7c8dff370e0c1f67285da1
+oid sha256:a1373d9a02412908ee3ce5bab868f7cbec3faa136e3d1694a1fe4ce56b314f5d
 size 17549312

run-4/checkpoint-594/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4f225cbcf4be011db2b36b3c5f7f4a441e936b4532a87e4873bb53ef3102373
-size 35122746
+oid sha256:67818f3594ea0ca3785f4f2954eef44ae6d2d2c5fa96513a50b43a27c67a8d7d
+size 35123898

run-4/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-4/checkpoint-594/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65d2dccd940bec011857c38259860d9eb722df804caef6710c785d20e0ebb647
+oid sha256:938ae2beae3d140aca43811cc80ada974d817af03ca88b16ecb307a2a47a970e
 size 1064

run-4/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-4/checkpoint-594/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.500990099009901,
-  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-297",
+  "best_metric": 0.594059405940594,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-4/checkpoint-594",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 594,
@@ -10,49 +10,57 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 1.3486188650131226,
-      "learning_rate": 0.0008534021470265506,
-      "loss": 0.5548,
+      "grad_norm": 1.202705979347229,
+      "learning_rate": 6.504485936113838e-05,
+      "loss": 0.5495,
       "step": 297
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.500990099009901,
-      "eval_loss": 0.5633774399757385,
-      "eval_runtime": 55.4108,
-      "eval_samples_per_second": 9.114,
-      "eval_steps_per_second": 0.289,
+      "eval_accuracy": 0.5069306930693069,
+      "eval_f1": 0.10108303249097472,
+      "eval_loss": 0.5468167662620544,
+      "eval_mcc": 0.027838098756040194,
+      "eval_precision": 0.56,
+      "eval_recall": 0.05555555555555555,
+      "eval_runtime": 0.9316,
+      "eval_samples_per_second": 542.063,
+      "eval_steps_per_second": 17.174,
       "step": 297
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.8194136023521423,
-      "learning_rate": 0.0007467268786482318,
-      "loss": 0.5553,
+      "grad_norm": 0.8953370451927185,
+      "learning_rate": 5.4204049467615325e-05,
+      "loss": 0.54,
       "step": 594
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.500990099009901,
-      "eval_loss": 0.5545336604118347,
-      "eval_runtime": 54.9924,
-      "eval_samples_per_second": 9.183,
-      "eval_steps_per_second": 0.291,
+      "eval_accuracy": 0.594059405940594,
+      "eval_f1": 0.5858585858585857,
+      "eval_loss": 0.5394836068153381,
+      "eval_mcc": 0.18817791261380143,
+      "eval_precision": 0.5967078189300411,
+      "eval_recall": 0.5753968253968254,
+      "eval_runtime": 0.9335,
+      "eval_samples_per_second": 540.967,
+      "eval_steps_per_second": 17.14,
       "step": 594
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2673,
+  "max_steps": 2079,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 9,
+  "num_train_epochs": 7,
   "save_steps": 500,
-  "total_flos": 1555686566280.0,
+  "total_flos": 1461402531960.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.7480049651920854,
-    "learning_rate": 0.0009600774154048695,
-    "num_train_epochs": 9,
-    "temperature": 2
+    "alpha": 0.7404813991868276,
+    "learning_rate": 7.588566925466145e-05,
+    "num_train_epochs": 7,
+    "temperature": 47
   }
 }

run-4/checkpoint-594/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9362332d8be73fdeb508a202d9b7c32cc7427a6a4b9b0d6128331394ce376267
-size 4984
+oid sha256:0b89f4b12e9eb0ed1644da45c1653800b9447c89374868af92258b08fc1b6045
+size 4920