Training in progress, epoch 2

logs/events.out.tfevents.1711297031.8cc2eef2edb7.2942.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5671c871dec21b814e238027bc460e37eeca98777d4d78926a461e91685a1999
-size 5406
+oid sha256:9aec06acf2a8e079593f9eca3449c4e387e8466ce8e96255fe32bec5c97c28ff
+size 6136

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8535679c03461b298018d74a95c8d714c32a4f38defdc9aadd1837a148497803
+oid sha256:d8787c73455dbc98abc8d9e870c41942e3996f1081a3f3c5cd872817f27a3b53
 size 17549312

run-3/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-3/checkpoint-594/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc44da7da9ee7483223f84fc107bea919ad244d54f5eedf49f42aaf1954cee3
+oid sha256:d8787c73455dbc98abc8d9e870c41942e3996f1081a3f3c5cd872817f27a3b53
 size 17549312

run-3/checkpoint-594/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b00bd81260407d2dcacc2c135676399912a16b5ea23b5442d6377ef454fc7c84
-size 35122746
+oid sha256:4b467e85815ba0af002cb553cec311e49a0f572a70fb2690ad6d7728980c1fd8
+size 35123898

run-3/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-3/checkpoint-594/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9d4f642fea8f45d839698b4d161b45cf4f8c426e82e8780e36861baa6efe2aa
+oid sha256:ba183537a264f124c1c17977272b5c3edb6a640be7f75fd73ba9c48332f9477e
 size 1064

run-3/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-3/checkpoint-594/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.6,
-  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-594",
+  "best_metric": 0.5168316831683168,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-297",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 594,
@@ -10,34 +10,42 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.9984288811683655,
-      "learning_rate": 9.995670829688553e-05,
-      "loss": 0.5706,
+      "grad_norm": 0.8371890187263489,
+      "learning_rate": 0.000508582557644255,
+      "loss": 0.309,
       "step": 297
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5128712871287129,
-      "eval_loss": 0.5624967217445374,
-      "eval_runtime": 13.6049,
-      "eval_samples_per_second": 37.119,
-      "eval_steps_per_second": 1.176,
+      "eval_accuracy": 0.5168316831683168,
+      "eval_f1": 0.1643835616438356,
+      "eval_loss": 0.30045250058174133,
+      "eval_mcc": 0.059239742807176775,
+      "eval_precision": 0.6,
+      "eval_recall": 0.09523809523809523,
+      "eval_runtime": 0.9336,
+      "eval_samples_per_second": 540.929,
+      "eval_steps_per_second": 17.138,
       "step": 297
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.9848873615264893,
-      "learning_rate": 4.9978354148442764e-05,
-      "loss": 0.5602,
+      "grad_norm": 0.21939373016357422,
+      "learning_rate": 0.0002542912788221275,
+      "loss": 0.3016,
       "step": 594
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6,
-      "eval_loss": 0.5566068291664124,
-      "eval_runtime": 13.9891,
-      "eval_samples_per_second": 36.099,
-      "eval_steps_per_second": 1.144,
+      "eval_accuracy": 0.5128712871287129,
+      "eval_f1": 0.14583333333333331,
+      "eval_loss": 0.29779767990112305,
+      "eval_mcc": 0.046724423554504804,
+      "eval_precision": 0.5833333333333334,
+      "eval_recall": 0.08333333333333333,
+      "eval_runtime": 0.9339,
+      "eval_samples_per_second": 540.765,
+      "eval_steps_per_second": 17.133,
       "step": 594
     }
   ],
@@ -46,13 +54,13 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 1555686566280.0,
+  "total_flos": 1461402531960.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.7785816803005383,
-    "learning_rate": 0.0001499350624453283,
+    "alpha": 0.37059488996882817,
+    "learning_rate": 0.0007628738364663827,
     "num_train_epochs": 3,
-    "temperature": 16
+    "temperature": 5
   }
 }

run-3/checkpoint-594/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9decda4f5411e0ed12b24ed68c82ec0237bdb8018a369738f83b0ca5fb77d628
-size 4984
+oid sha256:c77ece67af99569b700b80b7c3d227a73e33d56768e0354e21fbf558f6ec676a
+size 4920