Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83e01fc1d25dedc753f4825dabab388ed7180db6815fc7516b723efdbd0fc2c1
+oid sha256:d661b5d8e28c6286c4f688153e59f25326218295967aead1da1fcca840dd8cde
 size 160086542

all_results.json

@@ -1,17 +1,17 @@
 {
-    "epoch": 0.99,
-    "eval_accuracy": 0.78,
-    "eval_f1_score": 0.7760000000000001,
-    "eval_gmean": 0.7929678856251685,
-    "eval_loss": 0.5592187643051147,
-    "eval_precision": 0.82625,
-    "eval_recall": 0.78,
-    "eval_runtime": 111.3804,
-    "eval_samples_per_second": 0.449,
-    "eval_steps_per_second": 0.063,
-    "total_flos": 8.453461911404544e+16,
-    "train_loss": 0.6594164299242424,
-    "train_runtime": 12749.8583,
-    "train_samples_per_second": 0.336,
-    "train_steps_per_second": 0.003
+    "epoch": 1.0,
+    "eval_accuracy": 0.72,
+    "eval_f1_score": 0.7154911433172302,
+    "eval_gmean": 0.7399824497743348,
+    "eval_loss": 0.6498633027076721,
+    "eval_precision": 0.7727777777777777,
+    "eval_recall": 0.72,
+    "eval_runtime": 137.6618,
+    "eval_samples_per_second": 0.363,
+    "eval_steps_per_second": 0.051,
+    "total_flos": 8.468389371174912e+16,
+    "train_loss": 0.9084581972947762,
+    "train_runtime": 14096.0939,
+    "train_samples_per_second": 0.304,
+    "train_steps_per_second": 0.005
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 0.99,
-    "eval_accuracy": 0.78,
-    "eval_f1_score": 0.7760000000000001,
-    "eval_gmean": 0.7929678856251685,
-    "eval_loss": 0.5592187643051147,
-    "eval_precision": 0.82625,
-    "eval_recall": 0.78,
-    "eval_runtime": 111.3804,
-    "eval_samples_per_second": 0.449,
-    "eval_steps_per_second": 0.063
+    "epoch": 1.0,
+    "eval_accuracy": 0.72,
+    "eval_f1_score": 0.7154911433172302,
+    "eval_gmean": 0.7399824497743348,
+    "eval_loss": 0.6498633027076721,
+    "eval_precision": 0.7727777777777777,
+    "eval_recall": 0.72,
+    "eval_runtime": 137.6618,
+    "eval_samples_per_second": 0.363,
+    "eval_steps_per_second": 0.051
 }

runs/Apr01_20-59-31_966bae07cabd/events.out.tfevents.1712005173.966bae07cabd.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2af5e154e7787b72185f5f03a708d8ef21c994033ded01a0f686e55b9b7fad7
+size 7948

runs/Apr01_20-59-31_966bae07cabd/events.out.tfevents.1712019406.966bae07cabd.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b45e57e67436a7e93efa978b3043c3c93592f8f2660f789f90daec17a59b5e40
+size 605

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 0.99,
-    "total_flos": 8.453461911404544e+16,
-    "train_loss": 0.6594164299242424,
-    "train_runtime": 12749.8583,
-    "train_samples_per_second": 0.336,
-    "train_steps_per_second": 0.003
+    "epoch": 1.0,
+    "total_flos": 8.468389371174912e+16,
+    "train_loss": 0.9084581972947762,
+    "train_runtime": 14096.0939,
+    "train_samples_per_second": 0.304,
+    "train_steps_per_second": 0.005
 }

trainer_state.json

@@ -1,71 +1,112 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9850746268656716,
+  "epoch": 1.0,
   "eval_steps": 28,
-  "global_step": 33,
+  "global_step": 67,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.24,
-      "grad_norm": 19.75,
-      "learning_rate": 1.6129032258064517e-05,
-      "loss": 0.7026,
+      "epoch": 0.12,
+      "grad_norm": 47.25,
+      "learning_rate": 1.8153846153846155e-05,
+      "loss": 1.1395,
       "step": 8
     },
     {
-      "epoch": 0.48,
-      "grad_norm": 14.875,
-      "learning_rate": 1.096774193548387e-05,
-      "loss": 0.6661,
+      "epoch": 0.24,
+      "grad_norm": 39.75,
+      "learning_rate": 1.5692307692307693e-05,
+      "loss": 1.0434,
       "step": 16
     },
     {
-      "epoch": 0.72,
-      "grad_norm": 18.375,
-      "learning_rate": 5.806451612903226e-06,
-      "loss": 0.6407,
+      "epoch": 0.36,
+      "grad_norm": 42.0,
+      "learning_rate": 1.3230769230769231e-05,
+      "loss": 0.8923,
       "step": 24
     },
     {
-      "epoch": 0.84,
-      "eval_accuracy": 0.78,
-      "eval_f1_score": 0.7760000000000001,
-      "eval_gmean": 0.7929678856251685,
-      "eval_loss": 0.5600000023841858,
-      "eval_precision": 0.82625,
-      "eval_recall": 0.78,
-      "eval_runtime": 108.8057,
-      "eval_samples_per_second": 0.46,
-      "eval_steps_per_second": 0.064,
+      "epoch": 0.42,
+      "eval_accuracy": 0.66,
+      "eval_f1_score": 0.6473765809873521,
+      "eval_gmean": 0.6861694917646597,
+      "eval_loss": 0.692578136920929,
+      "eval_precision": 0.7367619047619047,
+      "eval_recall": 0.66,
+      "eval_runtime": 137.4001,
+      "eval_samples_per_second": 0.364,
+      "eval_steps_per_second": 0.051,
       "step": 28
     },
     {
-      "epoch": 0.96,
-      "grad_norm": 16.25,
-      "learning_rate": 6.451612903225807e-07,
-      "loss": 0.6313,
+      "epoch": 0.48,
+      "grad_norm": 41.5,
+      "learning_rate": 1.076923076923077e-05,
+      "loss": 0.8968,
       "step": 32
     },
     {
-      "epoch": 0.99,
-      "step": 33,
-      "total_flos": 8.453461911404544e+16,
-      "train_loss": 0.6594164299242424,
-      "train_runtime": 12749.8583,
-      "train_samples_per_second": 0.336,
-      "train_steps_per_second": 0.003
+      "epoch": 0.6,
+      "grad_norm": 40.75,
+      "learning_rate": 8.307692307692309e-06,
+      "loss": 0.8597,
+      "step": 40
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 29.0,
+      "learning_rate": 5.846153846153847e-06,
+      "loss": 0.8077,
+      "step": 48
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 37.75,
+      "learning_rate": 3.384615384615385e-06,
+      "loss": 0.8601,
+      "step": 56
+    },
+    {
+      "epoch": 0.84,
+      "eval_accuracy": 0.72,
+      "eval_f1_score": 0.7154911433172302,
+      "eval_gmean": 0.7399824497743348,
+      "eval_loss": 0.6498633027076721,
+      "eval_precision": 0.7727777777777777,
+      "eval_recall": 0.72,
+      "eval_runtime": 137.4306,
+      "eval_samples_per_second": 0.364,
+      "eval_steps_per_second": 0.051,
+      "step": 56
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 39.25,
+      "learning_rate": 9.230769230769232e-07,
+      "loss": 0.8283,
+      "step": 64
+    },
+    {
+      "epoch": 1.0,
+      "step": 67,
+      "total_flos": 8.468389371174912e+16,
+      "train_loss": 0.9084581972947762,
+      "train_runtime": 14096.0939,
+      "train_samples_per_second": 0.304,
+      "train_steps_per_second": 0.005
     }
   ],
   "logging_steps": 8,
-  "max_steps": 33,
+  "max_steps": 67,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 8.453461911404544e+16,
-  "train_batch_size": 32,
+  "total_flos": 8.468389371174912e+16,
+  "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null
 }