Upload folder using huggingface_hub

adapter_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4411c80e204fa52239f0e767750debd1cf11225e340233f1709705364827150e
+oid sha256:83e01fc1d25dedc753f4825dabab388ed7180db6815fc7516b723efdbd0fc2c1
 size 160086542

all_results.json

@@ -1,17 +1,17 @@
 {
-    "epoch": 1.0,
-    "eval_accuracy": 0.85,
-    "eval_f1_score": 0.8504053648283457,
-    "eval_gmean": 0.8587214900086042,
-    "eval_loss": 0.44022461771965027,
-    "eval_precision": 0.8646326776395022,
-    "eval_recall": 0.85,
-    "eval_runtime": 281.2283,
-    "eval_samples_per_second": 0.356,
-    "eval_steps_per_second": 0.046,
-    "total_flos": 8.435821078904832e+16,
-    "train_loss": 0.508428317397388,
-    "train_runtime": 14877.7814,
-    "train_samples_per_second": 0.288,
-    "train_steps_per_second": 0.005
+    "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
 }

eval_results.json

@@ -1,12 +1,12 @@
 {
-    "epoch": 1.0,
-    "eval_accuracy": 0.85,
-    "eval_f1_score": 0.8504053648283457,
-    "eval_gmean": 0.8587214900086042,
-    "eval_loss": 0.44022461771965027,
-    "eval_precision": 0.8646326776395022,
-    "eval_recall": 0.85,
-    "eval_runtime": 281.2283,
-    "eval_samples_per_second": 0.356,
-    "eval_steps_per_second": 0.046
+    "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
 }

runs/Mar26_17-17-40_59245c7fbd53/events.out.tfevents.1711473463.59245c7fbd53.35.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78d3d71e8db1d0d700ef4e012d647e61ee029dbbf36c81703e4e8125a1070707
+size 4964

runs/Mar26_18-20-56_8514445b457f/events.out.tfevents.1711477258.8514445b457f.34.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eecbc248a4c8d4479ac388fa729b32724647f89d0da072f0380e10a93e711d69
+size 4964

runs/Mar26_18-21-19_8514445b457f/events.out.tfevents.1711477279.8514445b457f.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfc8b19dcc306bcd08d6fd47061d7b755f2d11995ead5d89b58359b4f2d842
+size 6657

runs/Mar26_18-21-19_8514445b457f/events.out.tfevents.1711490140.8514445b457f.34.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a57f4a061bf5f2b0373447b879ac5ccc98f298a199fde4dc3366e7b4217a2d1
+size 605

train_results.json

@@ -1,8 +1,8 @@
 {
-    "epoch": 1.0,
-    "total_flos": 8.435821078904832e+16,
-    "train_loss": 0.508428317397388,
-    "train_runtime": 14877.7814,
-    "train_samples_per_second": 0.288,
-    "train_steps_per_second": 0.005
+    "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
 }

trainer_state.json

@@ -1,138 +1,71 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
-  "eval_steps": 16,
-  "global_step": 67,
+  "epoch": 0.9850746268656716,
+  "eval_steps": 28,
+  "global_step": 33,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
-    {
-      "epoch": 0.12,
-      "grad_norm": 22.625,
-      "learning_rate": 1.8153846153846155e-05,
-      "loss": 0.6146,
-      "step": 8
-    },
-    {
-      "epoch": 0.24,
-      "grad_norm": 23.375,
-      "learning_rate": 1.5692307692307693e-05,
-      "loss": 0.5536,
-      "step": 16
-    },
     {
       "epoch": 0.24,
-      "eval_accuracy": 0.84,
-      "eval_f1_score": 0.8403201280512205,
-      "eval_gmean": 0.849780720378659,
-      "eval_loss": 0.4766210913658142,
-      "eval_precision": 0.8575523349436394,
-      "eval_recall": 0.84,
-      "eval_runtime": 281.1532,
-      "eval_samples_per_second": 0.356,
-      "eval_steps_per_second": 0.046,
-      "step": 16
-    },
-    {
-      "epoch": 0.36,
-      "grad_norm": 12.5,
-      "learning_rate": 1.3230769230769231e-05,
-      "loss": 0.5034,
-      "step": 24
-    },
-    {
-      "epoch": 0.48,
-      "grad_norm": 9.0625,
-      "learning_rate": 1.076923076923077e-05,
-      "loss": 0.4886,
-      "step": 32
+      "grad_norm": 19.75,
+      "learning_rate": 1.6129032258064517e-05,
+      "loss": 0.7026,
+      "step": 8
     },
     {
       "epoch": 0.48,
-      "eval_accuracy": 0.85,
-      "eval_f1_score": 0.8504053648283457,
-      "eval_gmean": 0.8587214900086042,
-      "eval_loss": 0.4527539014816284,
-      "eval_precision": 0.8646326776395022,
-      "eval_recall": 0.85,
-      "eval_runtime": 280.8117,
-      "eval_samples_per_second": 0.356,
-      "eval_steps_per_second": 0.046,
-      "step": 32
-    },
-    {
-      "epoch": 0.6,
-      "grad_norm": 14.0,
-      "learning_rate": 8.307692307692309e-06,
-      "loss": 0.4542,
-      "step": 40
-    },
-    {
-      "epoch": 0.72,
-      "grad_norm": 21.625,
-      "learning_rate": 5.846153846153847e-06,
-      "loss": 0.4781,
-      "step": 48
+      "grad_norm": 14.875,
+      "learning_rate": 1.096774193548387e-05,
+      "loss": 0.6661,
+      "step": 16
     },
     {
       "epoch": 0.72,
-      "eval_accuracy": 0.85,
-      "eval_f1_score": 0.8504053648283457,
-      "eval_gmean": 0.8587214900086042,
-      "eval_loss": 0.44312500953674316,
-      "eval_precision": 0.8646326776395022,
-      "eval_recall": 0.85,
-      "eval_runtime": 280.8661,
-      "eval_samples_per_second": 0.356,
-      "eval_steps_per_second": 0.046,
-      "step": 48
+      "grad_norm": 18.375,
+      "learning_rate": 5.806451612903226e-06,
+      "loss": 0.6407,
+      "step": 24
     },
     {
       "epoch": 0.84,
-      "grad_norm": 16.5,
-      "learning_rate": 3.384615384615385e-06,
-      "loss": 0.4712,
-      "step": 56
+      "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,
+      "step": 28
     },
     {
       "epoch": 0.96,
-      "grad_norm": 11.9375,
-      "learning_rate": 9.230769230769232e-07,
-      "loss": 0.4697,
-      "step": 64
-    },
-    {
-      "epoch": 0.96,
-      "eval_accuracy": 0.85,
-      "eval_f1_score": 0.8504053648283457,
-      "eval_gmean": 0.8587214900086042,
-      "eval_loss": 0.44022461771965027,
-      "eval_precision": 0.8646326776395022,
-      "eval_recall": 0.85,
-      "eval_runtime": 281.3025,
-      "eval_samples_per_second": 0.355,
-      "eval_steps_per_second": 0.046,
-      "step": 64
+      "grad_norm": 16.25,
+      "learning_rate": 6.451612903225807e-07,
+      "loss": 0.6313,
+      "step": 32
     },
     {
-      "epoch": 1.0,
-      "step": 67,
-      "total_flos": 8.435821078904832e+16,
-      "train_loss": 0.508428317397388,
-      "train_runtime": 14877.7814,
-      "train_samples_per_second": 0.288,
-      "train_steps_per_second": 0.005
+      "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
     }
   ],
   "logging_steps": 8,
-  "max_steps": 67,
+  "max_steps": 33,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 500,
-  "total_flos": 8.435821078904832e+16,
-  "train_batch_size": 16,
+  "total_flos": 8.453461911404544e+16,
+  "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null
 }