Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81019171f57fe06b9e19da488e023dce2bf580b121d2173e2e6f9577d599d4a7
+oid sha256:9f6186de49c4c240964ef641c4a8c3b95eb2d548423986eca54d36e1d5a13957
 size 497805008

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6cd5380c1d872971324c4b89e2670e9f71d76bba24c6c403e946b0762f77f3b
+oid sha256:6de11ddd7c3f391710615cb5968e72b75b0441fbfad712a6c1d794c1dc6937b1
 size 995704133

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802fce84ad05868499d41c3b4634506178ec2c020c0346ca354a18a41f72992e
+oid sha256:5c2f9bc2a3ad46f8f150379e5de8b3fe4f2d36b39fcb9132074d3b699746dc83
 size 14575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc92e8c6ac35d569c4ab17f395a4ac90783d80d786f272b0e4e95e53d403a71e
+oid sha256:11b85be459119ef17ec22d37d7186483189b4d638b69028a782c1261d8d5a4f1
 size 627

trainer_state.json

@@ -1,30 +1,112 @@
 {
-  "best_metric": 1.4867627620697021,
-  "best_model_checkpoint": "tam_test_out_drug_data/checkpoint-449",
-  "epoch": 1.0,
+  "best_metric": 1.4213874340057373,
+  "best_model_checkpoint": "tam_test_out_drug_data/checkpoint-1011",
+  "epoch": 7.0,
   "eval_steps": 500,
-  "global_step": 449,
+  "global_step": 2359,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
+      "eval_accuracy": 0.46219659629870735,
+      "eval_loss": 1.4630001783370972,
+      "eval_runtime": 15.2997,
+      "eval_samples_per_second": 702.823,
+      "eval_steps_per_second": 7.386,
+      "step": 337
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 283691.34375,
+      "learning_rate": 5.554896142433234e-05,
+      "loss": 1.599,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.4721473077280759,
+      "eval_loss": 1.443649411201477,
+      "eval_runtime": 15.1007,
+      "eval_samples_per_second": 712.086,
+      "eval_steps_per_second": 7.483,
+      "step": 674
+    },
+    {
+      "epoch": 2.97,
+      "grad_norm": 246200.171875,
+      "learning_rate": 5.109792284866469e-05,
+      "loss": 1.3511,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.471310332000372,
+      "eval_loss": 1.4213874340057373,
+      "eval_runtime": 14.9491,
+      "eval_samples_per_second": 719.309,
+      "eval_steps_per_second": 7.559,
+      "step": 1011
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.45615177159862363,
+      "eval_loss": 1.5083941221237183,
+      "eval_runtime": 15.0793,
+      "eval_samples_per_second": 713.097,
+      "eval_steps_per_second": 7.494,
+      "step": 1348
+    },
+    {
+      "epoch": 4.45,
+      "grad_norm": 280970.59375,
+      "learning_rate": 4.664688427299703e-05,
+      "loss": 1.1818,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.461173625964847,
+      "eval_loss": 1.5575577020645142,
+      "eval_runtime": 15.1913,
+      "eval_samples_per_second": 707.84,
+      "eval_steps_per_second": 7.438,
+      "step": 1685
+    },
+    {
+      "epoch": 5.93,
+      "grad_norm": 403212.34375,
+      "learning_rate": 4.219584569732938e-05,
+      "loss": 1.0233,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.46907839672649493,
+      "eval_loss": 1.6354960203170776,
+      "eval_runtime": 15.1613,
+      "eval_samples_per_second": 709.238,
+      "eval_steps_per_second": 7.453,
+      "step": 2022
+    },
+    {
+      "epoch": 7.0,
       "eval_accuracy": 0.4567097554170929,
-      "eval_loss": 1.4867627620697021,
-      "eval_runtime": 17.716,
-      "eval_samples_per_second": 606.966,
-      "eval_steps_per_second": 8.467,
-      "step": 449
+      "eval_loss": 1.7575633525848389,
+      "eval_runtime": 15.399,
+      "eval_samples_per_second": 698.293,
+      "eval_steps_per_second": 7.338,
+      "step": 2359
     }
   ],
   "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": 4063042006732800.0,
-  "train_batch_size": 72,
+  "total_flos": 3.08983856643072e+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 sha256:26a5c5deac729d817653111c7b0ce9686e1d385aab557c504d6e32dcc63509b4
+oid sha256:031e77c7775f2760360cdc9ed1a2d9e618d47728f22b58e85ee32d4d55d0ce3d
 size 4603