Training in progress, step 20

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 30.0,
     "eval_accuracy": 0.592,
-    "eval_f1": 0.43854957441913966,
-    "eval_loss": 0.8978701829910278,
-    "eval_runtime": 131.0498,
-    "eval_samples_per_second": 0.954,
-    "eval_steps_per_second": 0.122,
+    "eval_f1": 0.4602437417654809,
+    "eval_loss": 0.8401041626930237,
+    "eval_runtime": 130.3522,
+    "eval_samples_per_second": 0.959,
+    "eval_steps_per_second": 0.123,
     "total_flos": 2.907095595264e+17,
-    "train_loss": 1.6024109204610189,
-    "train_runtime": 10078.4501,
-    "train_samples_per_second": 0.372,
-    "train_steps_per_second": 0.012
+    "train_loss": 1.6994803905487061,
+    "train_runtime": 10528.1678,
+    "train_samples_per_second": 0.356,
+    "train_steps_per_second": 0.011
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 30.0,
     "eval_accuracy": 0.592,
-    "eval_f1": 0.43854957441913966,
-    "eval_loss": 0.8978701829910278,
-    "eval_runtime": 131.0498,
-    "eval_samples_per_second": 0.954,
-    "eval_steps_per_second": 0.122
+    "eval_f1": 0.4602437417654809,
+    "eval_loss": 0.8401041626930237,
+    "eval_runtime": 130.3522,
+    "eval_samples_per_second": 0.959,
+    "eval_steps_per_second": 0.123
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b5d774cd52b7efdb96d06df5553ae1ce0114e2fbde7330cb2a4b20e7f5a7084
+oid sha256:62557cd7096a9412d55e317cc264879c2bb612afd6036295645eeeb21cd4c111
 size 343359328

runs/Feb09_10-51-58_95d38ead18ce/events.out.tfevents.1707486617.95d38ead18ce.561.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd16c70d4624dfc58a398be0404965c9e43aa9db34cacb027a98891fe7405271
+size 450

runs/Feb12_04-49-49_e7b40a5a562d/events.out.tfevents.1707713396.e7b40a5a562d.565.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf6a1f1b1a1974f1c3b8e6cfb2e7329dd038f71ed574a747d4b814f72491b310
+size 6709

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 30.0,
     "total_flos": 2.907095595264e+17,
-    "train_loss": 1.6024109204610189,
-    "train_runtime": 10078.4501,
-    "train_samples_per_second": 0.372,
-    "train_steps_per_second": 0.012
+    "train_loss": 1.6994803905487061,
+    "train_runtime": 10528.1678,
+    "train_samples_per_second": 0.356,
+    "train_steps_per_second": 0.011
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8978701829910278,
+  "best_metric": 0.8401041626930237,
   "best_model_checkpoint": "/content/drive/MyDrive/Fine-Tuned_Model3/checkpoint-120",
   "epoch": 30.0,
   "eval_steps": 20,
@@ -10,72 +10,96 @@
   "log_history": [
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.512,
-      "eval_f1": 0.2812087537790227,
-      "eval_loss": 2.0562753677368164,
-      "eval_runtime": 131.4968,
-      "eval_samples_per_second": 0.951,
+      "learning_rate": 2.9488887394336025e-05,
+      "loss": 3.5336,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.472,
+      "eval_f1": 0.2688021058225662,
+      "eval_loss": 2.5429601669311523,
+      "eval_runtime": 130.7136,
+      "eval_samples_per_second": 0.956,
       "eval_steps_per_second": 0.122,
       "step": 20
     },
+    {
+      "epoch": 10.0,
+      "learning_rate": 1.5e-05,
+      "loss": 1.952,
+      "step": 40
+    },
     {
       "epoch": 10.0,
       "eval_accuracy": 0.576,
-      "eval_f1": 0.375200783721446,
-      "eval_loss": 1.4345649480819702,
-      "eval_runtime": 132.0355,
-      "eval_samples_per_second": 0.947,
+      "eval_f1": 0.369042862070919,
+      "eval_loss": 1.468719482421875,
+      "eval_runtime": 131.8983,
+      "eval_samples_per_second": 0.948,
       "eval_steps_per_second": 0.121,
       "step": 40
     },
     {
-      "epoch": 12.5,
-      "learning_rate": 3.4048431995589453e-06,
-      "loss": 2.1474,
-      "step": 50
+      "epoch": 15.0,
+      "learning_rate": 5.11112605663977e-07,
+      "loss": 1.3471,
+      "step": 60
     },
     {
       "epoch": 15.0,
-      "eval_accuracy": 0.576,
-      "eval_f1": 0.3873325405294715,
-      "eval_loss": 1.3222265243530273,
-      "eval_runtime": 132.1891,
-      "eval_samples_per_second": 0.946,
-      "eval_steps_per_second": 0.121,
+      "eval_accuracy": 0.584,
+      "eval_f1": 0.38577990574558085,
+      "eval_loss": 1.274966835975647,
+      "eval_runtime": 139.0851,
+      "eval_samples_per_second": 0.899,
+      "eval_steps_per_second": 0.115,
       "step": 60
     },
+    {
+      "epoch": 20.0,
+      "learning_rate": 7.499999999999993e-06,
+      "loss": 1.2688,
+      "step": 80
+    },
     {
       "epoch": 20.0,
       "eval_accuracy": 0.576,
-      "eval_f1": 0.3879913020577983,
-      "eval_loss": 1.2946172952651978,
-      "eval_runtime": 131.2242,
-      "eval_samples_per_second": 0.953,
+      "eval_f1": 0.3823282044677926,
+      "eval_loss": 1.2294681072235107,
+      "eval_runtime": 131.4905,
+      "eval_samples_per_second": 0.951,
       "eval_steps_per_second": 0.122,
       "step": 80
     },
     {
       "epoch": 25.0,
-      "learning_rate": 1.7926354830241928e-05,
-      "loss": 1.2873,
+      "learning_rate": 2.5606601717798212e-05,
+      "loss": 1.1444,
       "step": 100
     },
     {
       "epoch": 25.0,
-      "eval_accuracy": 0.6,
-      "eval_f1": 0.40130894254935173,
-      "eval_loss": 1.0957316160202026,
-      "eval_runtime": 130.6383,
-      "eval_samples_per_second": 0.957,
-      "eval_steps_per_second": 0.122,
+      "eval_accuracy": 0.592,
+      "eval_f1": 0.38488272384052435,
+      "eval_loss": 0.9876356720924377,
+      "eval_runtime": 130.1608,
+      "eval_samples_per_second": 0.96,
+      "eval_steps_per_second": 0.123,
       "step": 100
     },
+    {
+      "epoch": 30.0,
+      "learning_rate": 2.7990381056766586e-05,
+      "loss": 0.9511,
+      "step": 120
+    },
     {
       "epoch": 30.0,
       "eval_accuracy": 0.592,
-      "eval_f1": 0.43854957441913966,
-      "eval_loss": 0.8978701829910278,
-      "eval_runtime": 130.7817,
+      "eval_f1": 0.4602437417654809,
+      "eval_loss": 0.8401041626930237,
+      "eval_runtime": 130.7723,
       "eval_samples_per_second": 0.956,
       "eval_steps_per_second": 0.122,
       "step": 120
@@ -84,13 +108,13 @@
       "epoch": 30.0,
       "step": 120,
       "total_flos": 2.907095595264e+17,
-      "train_loss": 1.6024109204610189,
-      "train_runtime": 10078.4501,
-      "train_samples_per_second": 0.372,
-      "train_steps_per_second": 0.012
+      "train_loss": 1.6994803905487061,
+      "train_runtime": 10528.1678,
+      "train_samples_per_second": 0.356,
+      "train_steps_per_second": 0.011
     }
   ],
-  "logging_steps": 50,
+  "logging_steps": 20,
   "max_steps": 120,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:524ac55fe2d55f48c14744604e89ac38f57b6b1a0be144350a0aa965c80cbf5f
+oid sha256:d81a55a26d6ce36bd2cb1c3749ad8b71ae387f415df79ce84248209b54e4b4b4
 size 4728