Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:caeccab941c80b52e5eb757d272efa629bb8a348fb8a4b77625d47bf7acc33ef
+oid sha256:c6b03e6e1e1dd420e540d1d84609aca44d109b1b8e156bc9fec2edb6d1011b84
 size 497805008

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:877a33a6a3a9ad9edc2787a571a4de9508116756609051f92fc72e485aa4eede
+oid sha256:f37fe1cc42498a74c4845b117ce63a81ee22aae316c81d8118898226f297eb6c
 size 995704133

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46dc359b5a55b9b0ddec23dca9a03c15273e7db4bd6b4f7c4f61105c4e72dc70
+oid sha256:08f7c8f2f1f450ef4812e0468b7a029a19d12df470c12014d4db6d65476b4372
 size 14575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc92e8c6ac35d569c4ab17f395a4ac90783d80d786f272b0e4e95e53d403a71e
+oid sha256:2e4d403e393281d76e64949d963b242833c6edfcde8957770a97931714558bf1
 size 627

trainer_state.json

@@ -1,30 +1,62 @@
 {
-  "best_metric": 1.470206379890442,
-  "best_model_checkpoint": "tam_test_out_drug_data/checkpoint-449",
-  "epoch": 1.0,
+  "best_metric": 1.4132897853851318,
+  "best_model_checkpoint": "tam_test_out_drug_data/checkpoint-674",
+  "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 449,
+  "global_step": 1011,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.45968566911559566,
-      "eval_loss": 1.470206379890442,
-      "eval_runtime": 25.6995,
-      "eval_samples_per_second": 418.413,
-      "eval_steps_per_second": 5.837,
-      "step": 449
+      "eval_accuracy": 0.46080163675253416,
+      "eval_loss": 1.4642583131790161,
+      "eval_runtime": 15.3539,
+      "eval_samples_per_second": 700.342,
+      "eval_steps_per_second": 7.36,
+      "step": 337
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 440106.375,
+      "learning_rate": 5.554896142433234e-05,
+      "loss": 1.6371,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.47456523760810937,
+      "eval_loss": 1.4132897853851318,
+      "eval_runtime": 15.004,
+      "eval_samples_per_second": 716.674,
+      "eval_steps_per_second": 7.531,
+      "step": 674
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 298983.0625,
+      "learning_rate": 5.109792284866469e-05,
+      "loss": 1.3737,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.46861341021110386,
+      "eval_loss": 1.4304810762405396,
+      "eval_runtime": 15.0331,
+      "eval_samples_per_second": 715.289,
+      "eval_steps_per_second": 7.517,
+      "step": 1011
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2245,
+  "max_steps": 6740,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 20,
   "save_steps": 500,
-  "total_flos": 4092282306478080.0,
-  "train_batch_size": 72,
+  "total_flos": 1.276707860453376e+16,
+  "train_batch_size": 96,
   "trial_name": null,
   "trial_params": null
 }

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f36df7ffae329fe6576146c0d380adbb4c38dcd792b53f9f2efc689ef84946b
+oid sha256:4d3c8570815cf50a5080ee48052b1e0f25bc57519e96eb840e6d87526b4e2a35
 size 4603