Training in progress, step 500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:232e27d498310e239f29ab4dc4a6b88a7df4a45389d801179bef55d23878c4da
+oid sha256:6bc037964fb4532c3fbe0661daa2cb24c635f5c5b14122d19bb3e974f11695cf
 size 135998360

run-faa58daf/checkpoint-500/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "mgh6/esm_cluster_35M_linear",
+  "architectures": [
+    "EsmForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "classifier_dropout": 0.18727005942368125,
+  "emb_layer_norm_before": false,
+  "esmfold_config": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "hidden_size": 480,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1920,
+  "is_folding_model": false,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "mask_token_id": 32,
+  "max_position_embeddings": 1026,
+  "model_type": "esm",
+  "num_attention_heads": 20,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "rotary",
+  "problem_type": "regression",
+  "token_dropout": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_list": null,
+  "vocab_size": 33
+}

run-faa58daf/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc037964fb4532c3fbe0661daa2cb24c635f5c5b14122d19bb3e974f11695cf
+size 135998360

run-faa58daf/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5324f3a40e0c2e21375d4b256ac801816dc2c71f3a3d840e4d80bb2a71b1983
+size 268171578

run-faa58daf/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f077b2f5a1c369ee4a3f74c2424dab29dce328d101e98bc5ebef831752ab14bd
+size 14244

run-faa58daf/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0c6c31d10af81783a887ad48ca5702e81bc44128e52a29e866b3fa94d439cc1
+size 1064

run-faa58daf/checkpoint-500/trainer_state.json

@@ -0,0 +1,38 @@
+{
+  "best_metric": 0.15397430956363678,
+  "best_model_checkpoint": "mgh6/TCS_Pair/run-faa58daf/checkpoint-500",
+  "epoch": 1.0057663939922221,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.01,
+      "learning_rate": 0.0006977185696773308,
+      "loss": 0.0932,
+      "step": 500
+    },
+    {
+      "epoch": 1.01,
+      "eval_loss": 0.15397430956363678,
+      "eval_runtime": 21.4027,
+      "eval_samples_per_second": 223.85,
+      "eval_steps_per_second": 27.987,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9940,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 3808940939721840.0,
+  "trial_name": null,
+  "trial_params": {
+    "classifier_dropout": 0.18727005942368125,
+    "gradient_accumulation_steps": 15.310000289738827,
+    "learning_rate": 0.000734674002393291,
+    "weight_decay": 0.06026718993550663
+  }
+}

run-faa58daf/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d46e74d245c1bc18e06275b4a98e13d9ed4372c7020352518f1ee46e02e7c9
+size 4600

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6824f9fe4d5530bdfbcda9b94035c681cade4710ef178c7fb69dcfe7e47c4df
+oid sha256:59d46e74d245c1bc18e06275b4a98e13d9ed4372c7020352518f1ee46e02e7c9
 size 4600