Training in progress, step 20

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 30.0,
-    "eval_accuracy": 0.592,
-    "eval_f1": 0.4602437417654809,
-    "eval_loss": 0.8401041626930237,
-    "eval_runtime": 130.3522,
-    "eval_samples_per_second": 0.959,
-    "eval_steps_per_second": 0.123,
+    "eval_accuracy": 0.608,
+    "eval_f1": 0.5096170704866357,
+    "eval_loss": 0.736162006855011,
+    "eval_runtime": 44.8107,
+    "eval_samples_per_second": 2.79,
+    "eval_steps_per_second": 0.357,
     "total_flos": 2.907095595264e+17,
-    "train_loss": 1.6994803905487061,
-    "train_runtime": 10528.1678,
-    "train_samples_per_second": 0.356,
-    "train_steps_per_second": 0.011
+    "train_loss": 1.321283253033956,
+    "train_runtime": 2416.2795,
+    "train_samples_per_second": 1.552,
+    "train_steps_per_second": 0.05
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 30.0,
-    "eval_accuracy": 0.592,
-    "eval_f1": 0.4602437417654809,
-    "eval_loss": 0.8401041626930237,
-    "eval_runtime": 130.3522,
-    "eval_samples_per_second": 0.959,
-    "eval_steps_per_second": 0.123
+    "eval_accuracy": 0.608,
+    "eval_f1": 0.5096170704866357,
+    "eval_loss": 0.736162006855011,
+    "eval_runtime": 44.8107,
+    "eval_samples_per_second": 2.79,
+    "eval_steps_per_second": 0.357
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e03496b8aa90189bc23efd44b1041370b4122b82f242ce16acd5fdb67f18732c
+oid sha256:93d51a216f8b7baad87599fc55a5a954339890cf705dbc6e4abbda8ba83f4590
 size 343359328

runs/Feb12_04-49-49_e7b40a5a562d/events.out.tfevents.1707715881.e7b40a5a562d.565.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d6a65b12f329a510afed2e849ef189c8708c5636f48ca03d1bdf8950f3c784f
+size 450

runs/Feb12_10-05-02_8d0c95f0ef0d/events.out.tfevents.1707732306.8d0c95f0ef0d.266.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fec226b902e6b7c51d60c0fa98c7f81307c112eda25f5ea94e6c3b5162b6511
+size 6710

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 30.0,
     "total_flos": 2.907095595264e+17,
-    "train_loss": 1.6994803905487061,
-    "train_runtime": 10528.1678,
-    "train_samples_per_second": 0.356,
-    "train_steps_per_second": 0.011
+    "train_loss": 1.321283253033956,
+    "train_runtime": 2416.2795,
+    "train_samples_per_second": 1.552,
+    "train_steps_per_second": 0.05
 }

trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.8401041626930237,
+  "best_metric": 0.736162006855011,
   "best_model_checkpoint": "/content/drive/MyDrive/Fine-Tuned_Model3/checkpoint-120",
   "epoch": 30.0,
   "eval_steps": 20,
@@ -10,108 +10,108 @@
   "log_history": [
     {
       "epoch": 5.0,
-      "learning_rate": 2.9488887394336025e-05,
-      "loss": 3.5336,
+      "learning_rate": 6.25e-05,
+      "loss": 3.2255,
       "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,
+      "eval_accuracy": 0.512,
+      "eval_f1": 0.30833289169267614,
+      "eval_loss": 1.9573944807052612,
+      "eval_runtime": 43.495,
+      "eval_samples_per_second": 2.874,
+      "eval_steps_per_second": 0.368,
       "step": 20
     },
     {
       "epoch": 10.0,
-      "learning_rate": 1.5e-05,
-      "loss": 1.952,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.3773,
       "step": 40
     },
     {
       "epoch": 10.0,
-      "eval_accuracy": 0.576,
-      "eval_f1": 0.369042862070919,
-      "eval_loss": 1.468719482421875,
-      "eval_runtime": 131.8983,
-      "eval_samples_per_second": 0.948,
-      "eval_steps_per_second": 0.121,
+      "eval_accuracy": 0.584,
+      "eval_f1": 0.46169772256728775,
+      "eval_loss": 0.8853923678398132,
+      "eval_runtime": 43.5002,
+      "eval_samples_per_second": 2.874,
+      "eval_steps_per_second": 0.368,
       "step": 40
     },
     {
       "epoch": 15.0,
-      "learning_rate": 5.11112605663977e-07,
-      "loss": 1.3471,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.869,
       "step": 60
     },
     {
       "epoch": 15.0,
-      "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,
+      "eval_accuracy": 0.608,
+      "eval_f1": 0.4795432331237958,
+      "eval_loss": 0.7879514098167419,
+      "eval_runtime": 43.7619,
+      "eval_samples_per_second": 2.856,
+      "eval_steps_per_second": 0.366,
       "step": 60
     },
     {
       "epoch": 20.0,
-      "learning_rate": 7.499999999999993e-06,
-      "loss": 1.2688,
+      "learning_rate": 4.999999999999999e-05,
+      "loss": 0.7966,
       "step": 80
     },
     {
       "epoch": 20.0,
-      "eval_accuracy": 0.576,
-      "eval_f1": 0.3823282044677926,
-      "eval_loss": 1.2294681072235107,
-      "eval_runtime": 131.4905,
-      "eval_samples_per_second": 0.951,
-      "eval_steps_per_second": 0.122,
+      "eval_accuracy": 0.6,
+      "eval_f1": 0.4846140574401444,
+      "eval_loss": 0.7732068300247192,
+      "eval_runtime": 43.5459,
+      "eval_samples_per_second": 2.871,
+      "eval_steps_per_second": 0.367,
       "step": 80
     },
     {
       "epoch": 25.0,
-      "learning_rate": 2.5606601717798212e-05,
-      "loss": 1.1444,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.8458,
       "step": 100
     },
     {
       "epoch": 25.0,
-      "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,
+      "eval_accuracy": 0.576,
+      "eval_f1": 0.4111637823594345,
+      "eval_loss": 0.7794835567474365,
+      "eval_runtime": 43.6082,
+      "eval_samples_per_second": 2.866,
+      "eval_steps_per_second": 0.367,
       "step": 100
     },
     {
       "epoch": 30.0,
-      "learning_rate": 2.7990381056766586e-05,
-      "loss": 0.9511,
+      "learning_rate": 1.4644660940672666e-05,
+      "loss": 0.8135,
       "step": 120
     },
     {
       "epoch": 30.0,
-      "eval_accuracy": 0.592,
-      "eval_f1": 0.4602437417654809,
-      "eval_loss": 0.8401041626930237,
-      "eval_runtime": 130.7723,
-      "eval_samples_per_second": 0.956,
-      "eval_steps_per_second": 0.122,
+      "eval_accuracy": 0.608,
+      "eval_f1": 0.5096170704866357,
+      "eval_loss": 0.736162006855011,
+      "eval_runtime": 43.4882,
+      "eval_samples_per_second": 2.874,
+      "eval_steps_per_second": 0.368,
       "step": 120
     },
     {
       "epoch": 30.0,
       "step": 120,
       "total_flos": 2.907095595264e+17,
-      "train_loss": 1.6994803905487061,
-      "train_runtime": 10528.1678,
-      "train_samples_per_second": 0.356,
-      "train_steps_per_second": 0.011
+      "train_loss": 1.321283253033956,
+      "train_runtime": 2416.2795,
+      "train_samples_per_second": 1.552,
+      "train_steps_per_second": 0.05
     }
   ],
   "logging_steps": 20,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81a55a26d6ce36bd2cb1c3749ad8b71ae387f415df79ce84248209b54e4b4b4
+oid sha256:fc61c928db9a41caeebca7f4059dc89cc650436397dc5bae656b56cbbcd0f2c0
 size 4728