Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93aa0cf7d99ad26d47d8643e22d1ffc2cdf84ec975fa62bf6a3744af6d78bffa
+oid sha256:b349cc388254688729bb2bee539e11e35048cffe1a215edda714ab0e5e576f87
 size 160086542

all_results.json

@@ -1,17 +1,17 @@
 {
     "epoch": 0.99,
-    "eval_accuracy": 0.84,
-    "eval_f1_score": 0.8423376623376623,
-    "eval_gmean": 0.8605301007689224,
-    "eval_loss": 0.3891015648841858,
-    "eval_precision": 0.8687999999999999,
-    "eval_recall": 0.84,
-    "eval_runtime": 156.3274,
-    "eval_samples_per_second": 0.32,
-    "eval_steps_per_second": 0.045,
-    "total_flos": 1.171238676922368e+17,
-    "train_loss": 0.9641927083333334,
-    "train_runtime": 18930.2986,
-    "train_samples_per_second": 0.317,
+    "eval_accuracy": 0.8,
+    "eval_f1_score": 0.7993558776167471,
+    "eval_gmean": 0.7980746061134115,
+    "eval_loss": 0.5084765553474426,
+    "eval_precision": 0.8012987012987013,
+    "eval_recall": 0.8,
+    "eval_runtime": 158.4717,
+    "eval_samples_per_second": 0.316,
+    "eval_steps_per_second": 0.044,
+    "total_flos": 1.1914693337677824e+17,
+    "train_loss": 0.3557273290490591,
+    "train_runtime": 19662.2913,
+    "train_samples_per_second": 0.305,
     "train_steps_per_second": 0.005
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
     "epoch": 0.99,
-    "eval_accuracy": 0.84,
-    "eval_f1_score": 0.8423376623376623,
-    "eval_gmean": 0.8605301007689224,
-    "eval_loss": 0.3891015648841858,
-    "eval_precision": 0.8687999999999999,
-    "eval_recall": 0.84,
-    "eval_runtime": 156.3274,
-    "eval_samples_per_second": 0.32,
-    "eval_steps_per_second": 0.045
+    "eval_accuracy": 0.8,
+    "eval_f1_score": 0.7993558776167471,
+    "eval_gmean": 0.7980746061134115,
+    "eval_loss": 0.5084765553474426,
+    "eval_precision": 0.8012987012987013,
+    "eval_recall": 0.8,
+    "eval_runtime": 158.4717,
+    "eval_samples_per_second": 0.316,
+    "eval_steps_per_second": 0.044
 }

runs/Mar31_12-39-58_d80bcfba016b/events.out.tfevents.1711888801.d80bcfba016b.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfbe93418dd3800a1f694f88819ccee31229f668fa3f35739f4230494fea5d65
+size 9095

runs/Mar31_12-39-58_d80bcfba016b/events.out.tfevents.1711908621.d80bcfba016b.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a38e13b6604aa68e759fc23bc13c7468123e29500549b8f71f9312b10117fa95
+size 605

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.99,
-    "total_flos": 1.171238676922368e+17,
-    "train_loss": 0.9641927083333334,
-    "train_runtime": 18930.2986,
-    "train_samples_per_second": 0.317,
+    "total_flos": 1.1914693337677824e+17,
+    "train_loss": 0.3557273290490591,
+    "train_runtime": 19662.2913,
+    "train_samples_per_second": 0.305,
     "train_steps_per_second": 0.005
 }

trainer_state.json

@@ -10,127 +10,127 @@
   "log_history": [
     {
       "epoch": 0.09,
-      "grad_norm": 35.25,
+      "grad_norm": 6.0,
       "learning_rate": 1.8681318681318682e-05,
-      "loss": 1.1454,
+      "loss": 0.266,
       "step": 8
     },
     {
       "epoch": 0.17,
-      "grad_norm": 36.5,
+      "grad_norm": 8.75,
       "learning_rate": 1.6923076923076924e-05,
-      "loss": 1.1827,
+      "loss": 0.404,
       "step": 16
     },
     {
       "epoch": 0.26,
-      "grad_norm": 34.0,
+      "grad_norm": 7.90625,
       "learning_rate": 1.5164835164835166e-05,
-      "loss": 1.1057,
+      "loss": 0.4084,
       "step": 24
     },
     {
       "epoch": 0.3,
-      "eval_accuracy": 0.82,
-      "eval_f1_score": 0.8225454545454545,
-      "eval_gmean": 0.844292130744656,
-      "eval_loss": 0.4087499976158142,
-      "eval_precision": 0.8572435897435898,
-      "eval_recall": 0.82,
-      "eval_runtime": 156.306,
-      "eval_samples_per_second": 0.32,
-      "eval_steps_per_second": 0.045,
+      "eval_accuracy": 0.8,
+      "eval_f1_score": 0.7993558776167471,
+      "eval_gmean": 0.7980746061134115,
+      "eval_loss": 0.5118359327316284,
+      "eval_precision": 0.8012987012987013,
+      "eval_recall": 0.8,
+      "eval_runtime": 158.1221,
+      "eval_samples_per_second": 0.316,
+      "eval_steps_per_second": 0.044,
       "step": 28
     },
     {
       "epoch": 0.34,
-      "grad_norm": 30.75,
+      "grad_norm": 6.84375,
       "learning_rate": 1.3406593406593406e-05,
-      "loss": 0.9439,
+      "loss": 0.3697,
       "step": 32
     },
     {
       "epoch": 0.43,
-      "grad_norm": 35.25,
+      "grad_norm": 5.9375,
       "learning_rate": 1.164835164835165e-05,
-      "loss": 0.9382,
+      "loss": 0.3647,
       "step": 40
     },
     {
       "epoch": 0.51,
-      "grad_norm": 35.25,
+      "grad_norm": 7.1875,
       "learning_rate": 9.890109890109892e-06,
-      "loss": 0.9136,
+      "loss": 0.3738,
       "step": 48
     },
     {
       "epoch": 0.6,
-      "grad_norm": 35.75,
+      "grad_norm": 6.46875,
       "learning_rate": 8.131868131868132e-06,
-      "loss": 0.8892,
+      "loss": 0.3298,
       "step": 56
     },
     {
       "epoch": 0.6,
-      "eval_accuracy": 0.84,
-      "eval_f1_score": 0.8423376623376623,
-      "eval_gmean": 0.8605301007689224,
-      "eval_loss": 0.39445313811302185,
-      "eval_precision": 0.8687999999999999,
-      "eval_recall": 0.84,
-      "eval_runtime": 156.2149,
-      "eval_samples_per_second": 0.32,
-      "eval_steps_per_second": 0.045,
+      "eval_accuracy": 0.8,
+      "eval_f1_score": 0.7993558776167471,
+      "eval_gmean": 0.7980746061134115,
+      "eval_loss": 0.5087890625,
+      "eval_precision": 0.8012987012987013,
+      "eval_recall": 0.8,
+      "eval_runtime": 158.641,
+      "eval_samples_per_second": 0.315,
+      "eval_steps_per_second": 0.044,
       "step": 56
     },
     {
       "epoch": 0.68,
-      "grad_norm": 25.0,
+      "grad_norm": 6.75,
       "learning_rate": 6.373626373626373e-06,
-      "loss": 0.9037,
+      "loss": 0.333,
       "step": 64
     },
     {
       "epoch": 0.77,
-      "grad_norm": 19.25,
+      "grad_norm": 7.3125,
       "learning_rate": 4.615384615384616e-06,
-      "loss": 0.8933,
+      "loss": 0.3813,
       "step": 72
     },
     {
       "epoch": 0.85,
-      "grad_norm": 21.0,
+      "grad_norm": 6.5,
       "learning_rate": 2.8571428571428573e-06,
-      "loss": 0.8473,
+      "loss": 0.3403,
       "step": 80
     },
     {
       "epoch": 0.9,
-      "eval_accuracy": 0.84,
-      "eval_f1_score": 0.8423376623376623,
-      "eval_gmean": 0.8605301007689224,
-      "eval_loss": 0.3901953101158142,
-      "eval_precision": 0.8687999999999999,
-      "eval_recall": 0.84,
-      "eval_runtime": 155.9323,
-      "eval_samples_per_second": 0.321,
-      "eval_steps_per_second": 0.045,
+      "eval_accuracy": 0.8,
+      "eval_f1_score": 0.7993558776167471,
+      "eval_gmean": 0.7980746061134115,
+      "eval_loss": 0.5084765553474426,
+      "eval_precision": 0.8012987012987013,
+      "eval_recall": 0.8,
+      "eval_runtime": 158.2765,
+      "eval_samples_per_second": 0.316,
+      "eval_steps_per_second": 0.044,
       "step": 84
     },
     {
       "epoch": 0.94,
-      "grad_norm": 32.5,
+      "grad_norm": 6.84375,
       "learning_rate": 1.098901098901099e-06,
-      "loss": 0.8776,
+      "loss": 0.3473,
       "step": 88
     },
     {
       "epoch": 0.99,
       "step": 93,
-      "total_flos": 1.171238676922368e+17,
-      "train_loss": 0.9641927083333334,
-      "train_runtime": 18930.2986,
-      "train_samples_per_second": 0.317,
+      "total_flos": 1.1914693337677824e+17,
+      "train_loss": 0.3557273290490591,
+      "train_runtime": 19662.2913,
+      "train_samples_per_second": 0.305,
       "train_steps_per_second": 0.005
     }
   ],
@@ -139,7 +139,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 1.171238676922368e+17,
+  "total_flos": 1.1914693337677824e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null