Training in progress, epoch 2

logs/events.out.tfevents.1710507175.af351b5edcca.3142.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f06198ee44361a23f2d4fd39293a6cc026d37caaed7434826721619e1347790
-size 5178
+oid sha256:c1aa6c609edc24d38dae0e285acfaaaf393dbce51c764813a6cf579d32050175
+size 5712

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76220d7fcfb19b8bac2ae99022cae216a90b830bf00b3012d8b613a63d0bf947
+oid sha256:dcc44da7da9ee7483223f84fc107bea919ad244d54f5eedf49f42aaf1954cee3
 size 17549312

run-3/checkpoint-594/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36b096d092545db3f6929eb2356bdf184c04e49667b8811fe834be8ad526fae3
+oid sha256:dcc44da7da9ee7483223f84fc107bea919ad244d54f5eedf49f42aaf1954cee3
 size 17549312

run-3/checkpoint-594/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75219665ac76bc792388fc4fd95a2d7984f5600f651f2bb63a5d1eb4a184428b
+oid sha256:b00bd81260407d2dcacc2c135676399912a16b5ea23b5442d6377ef454fc7c84
 size 35122746

run-3/checkpoint-594/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ca7ec72111a14ce7876f703e982520232c709c07938716ba856a9bac936336c
+oid sha256:b9d4f642fea8f45d839698b4d161b45cf4f8c426e82e8780e36861baa6efe2aa
 size 1064

run-3/checkpoint-594/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5564356435643565,
+  "best_metric": 0.6,
   "best_model_checkpoint": "tiny-bert-sst2-distilled/run-3/checkpoint-594",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,49 +10,49 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 0.8068264722824097,
-      "learning_rate": 1.8960352341732743e-05,
-      "loss": 0.5426,
+      "grad_norm": 0.9984288811683655,
+      "learning_rate": 9.995670829688553e-05,
+      "loss": 0.5706,
       "step": 297
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.500990099009901,
-      "eval_loss": 0.5363946557044983,
-      "eval_runtime": 55.6857,
-      "eval_samples_per_second": 9.069,
-      "eval_steps_per_second": 0.287,
+      "eval_accuracy": 0.5128712871287129,
+      "eval_loss": 0.5624967217445374,
+      "eval_runtime": 13.6049,
+      "eval_samples_per_second": 37.119,
+      "eval_steps_per_second": 1.176,
       "step": 297
     },
     {
       "epoch": 2.0,
-      "grad_norm": 0.7480373978614807,
-      "learning_rate": 1.580029361811062e-05,
-      "loss": 0.5354,
+      "grad_norm": 0.9848873615264893,
+      "learning_rate": 4.9978354148442764e-05,
+      "loss": 0.5602,
       "step": 594
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5564356435643565,
-      "eval_loss": 0.5311887264251709,
-      "eval_runtime": 55.3283,
-      "eval_samples_per_second": 9.127,
-      "eval_steps_per_second": 0.289,
+      "eval_accuracy": 0.6,
+      "eval_loss": 0.5566068291664124,
+      "eval_runtime": 13.9891,
+      "eval_samples_per_second": 36.099,
+      "eval_steps_per_second": 1.144,
       "step": 594
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2079,
+  "max_steps": 891,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 7,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 1555686566280.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.7228353037734928,
-    "learning_rate": 2.212041106535487e-05,
-    "num_train_epochs": 7,
-    "temperature": 7
+    "alpha": 0.7785816803005383,
+    "learning_rate": 0.0001499350624453283,
+    "num_train_epochs": 3,
+    "temperature": 16
   }
 }

run-3/checkpoint-594/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef26fd1ddbade3db0c49006d3a63755bd6dceb7ec335f1b7b6f7abcb501f62b6
+oid sha256:9decda4f5411e0ed12b24ed68c82ec0237bdb8018a369738f83b0ca5fb77d628
 size 4984