Upload folder using huggingface_hub

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:32b849e2c9e0f1841adf44361e3908ae7371734c2c0e074b1f92bdb06b88769a
+oid sha256:e4da67f62237b3bb0c425f93bedf5464e7ae9507a6affb62c37112d795be69f5
 size 497805008

optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68246cc9169ce766b856705da31adaba45e4032fd00ac87653ea3ccf8ed46397
+oid sha256:63e54c8c4efb35059a75ba77fb769670f234d1cd5f600d814a097f2d33613da0
 size 995704133

rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc22a7f4646136ee686f8ffffc4c17960827b8d0690d08f1faedc80a3e6f6ef4
+oid sha256:eb4dd9d1e2a50bc3d07cac2022a784819448dd290d65076fdfe62b5aa6c41def
 size 14575

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc92e8c6ac35d569c4ab17f395a4ac90783d80d786f272b0e4e95e53d403a71e
+oid sha256:ac7407a0c8d2fe4371dadfa59d9dddefa668d77469707548ef1435b98fa09050
 size 627

trainer_state.json

@@ -1,30 +1,185 @@
 {
-  "best_metric": 1.4763978719711304,
-  "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": 12.0,
   "eval_steps": 500,
-  "global_step": 449,
+  "global_step": 4044,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.44926997117083606,
-      "eval_loss": 1.4763978719711304,
-      "eval_runtime": 17.5163,
-      "eval_samples_per_second": 613.884,
-      "eval_steps_per_second": 8.563,
-      "step": 449
+      "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": 1.7575633525848389,
+      "eval_runtime": 15.399,
+      "eval_samples_per_second": 698.293,
+      "eval_steps_per_second": 7.338,
+      "step": 2359
+    },
+    {
+      "epoch": 7.42,
+      "grad_norm": 479722.78125,
+      "learning_rate": 3.774480712166172e-05,
+      "loss": 0.8189,
+      "step": 2500
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.4754022133358133,
+      "eval_loss": 1.8389304876327515,
+      "eval_runtime": 15.2863,
+      "eval_samples_per_second": 703.44,
+      "eval_steps_per_second": 7.392,
+      "step": 2696
+    },
+    {
+      "epoch": 8.9,
+      "grad_norm": 851824.9375,
+      "learning_rate": 3.3293768545994065e-05,
+      "loss": 0.6647,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.48228401376360086,
+      "eval_loss": 1.9549497365951538,
+      "eval_runtime": 14.9633,
+      "eval_samples_per_second": 718.624,
+      "eval_steps_per_second": 7.552,
+      "step": 3033
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.4780991351250814,
+      "eval_loss": 2.1215293407440186,
+      "eval_runtime": 15.2366,
+      "eval_samples_per_second": 705.736,
+      "eval_steps_per_second": 7.416,
+      "step": 3370
+    },
+    {
+      "epoch": 10.39,
+      "grad_norm": 430901.96875,
+      "learning_rate": 2.884272997032641e-05,
+      "loss": 0.5063,
+      "step": 3500
+    },
+    {
+      "epoch": 11.0,
+      "eval_accuracy": 0.4572677392355622,
+      "eval_loss": 2.341653823852539,
+      "eval_runtime": 15.1545,
+      "eval_samples_per_second": 709.56,
+      "eval_steps_per_second": 7.457,
+      "step": 3707
+    },
+    {
+      "epoch": 11.87,
+      "grad_norm": 649377.0625,
+      "learning_rate": 2.4391691394658753e-05,
+      "loss": 0.3982,
+      "step": 4000
+    },
+    {
+      "epoch": 12.0,
+      "eval_accuracy": 0.47633218636659536,
+      "eval_loss": 2.4381961822509766,
+      "eval_runtime": 15.2391,
+      "eval_samples_per_second": 705.618,
+      "eval_steps_per_second": 7.415,
+      "step": 4044
     }
   ],
   "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": 4158825922068480.0,
-  "train_batch_size": 72,
+  "total_flos": 5.300994106017792e+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:db003e0b8701e6480fec83890e167f87831cc64f9bd6f4f25b408c4d452e291b
+oid sha256:031e77c7775f2760360cdc9ed1a2d9e618d47728f22b58e85ee32d4d55d0ce3d
 size 4603