Training in progress, step 500

config.json

@@ -1,10 +1,10 @@
 {
-  "_name_or_path": "facebook/esm2_t12_35M_UR50D",
+  "_name_or_path": "mgh6/esm_cluster_35M_linear",
   "architectures": [
     "EsmForSequenceClassification"
   ],
   "attention_probs_dropout_prob": 0.0,
-  "classifier_dropout": null,
+  "classifier_dropout": 0.18727005942368125,
   "emb_layer_norm_before": false,
   "esmfold_config": null,
   "hidden_act": "gelu",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0a16ea1ab978234692fded08c095e88e6c95d2e3f8d2fb2446ce76f6b93024
+oid sha256:a2d17a5dcc48ed6bac71945622b81fa0af241c8a9e41865e5a7b4e137fe41d97
 size 135998360

run-bad69_00000/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-bad69_00000/checkpoint-500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d17a5dcc48ed6bac71945622b81fa0af241c8a9e41865e5a7b4e137fe41d97
+size 135998360

run-bad69_00000/checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a86edef0bb7fa1cc73fc763387d08eb99eec31dcdd2ce503984ae3d29d82f46
+size 268171578

run-bad69_00000/checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82bf88a64d24f1710990b1b997183a2afa2776859ff863ac96ace4c776f5b99a
+size 14244

run-bad69_00000/checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbcbbfefbb5d00c88e5fa50fd25b0c0e69cd6f9b25c1eefc924adb1431a7921e
+size 1064

run-bad69_00000/checkpoint-500/trainer_state.json

@@ -0,0 +1,38 @@
+{
+  "best_metric": 0.2451040893793106,
+  "best_model_checkpoint": "mgh6/TCS_Pair/run-bad69_00000/checkpoint-500",
+  "epoch": 0.13446282102998522,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.00079158678443389,
+      "loss": 0.1584,
+      "step": 500
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 0.2451040893793106,
+      "eval_runtime": 21.3792,
+      "eval_samples_per_second": 224.096,
+      "eval_steps_per_second": 28.018,
+      "step": 500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 74360,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 507901117056000.0,
+  "trial_name": null,
+  "trial_params": {
+    "classifier_dropout": 0.18727005942368125,
+    "gradient_accumulation_steps": 2,
+    "learning_rate": 0.0007969454818643929,
+    "weight_decay": 0.029106359131330688
+  }
+}

run-bad69_00000/checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6824f9fe4d5530bdfbcda9b94035c681cade4710ef178c7fb69dcfe7e47c4df
+size 4600

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3133fd831cf03d31b2500397c3106e706b572eaffa32f87bd65fd9b936e71d46
+oid sha256:f6824f9fe4d5530bdfbcda9b94035c681cade4710ef178c7fb69dcfe7e47c4df
 size 4600