Training in progress, step 6500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4035bdc3d60bb99444e112e106791da6c8b539ce2881c991be814a3c71cc4515
+oid sha256:6961f378c80c44992d30e97a2a0b3a0352e5884048167eda192acdeae32f151f
 size 135998360

run-bad69_00000/checkpoint-6500/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-6500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6961f378c80c44992d30e97a2a0b3a0352e5884048167eda192acdeae32f151f
+size 135998360

run-bad69_00000/checkpoint-6500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fae80f9a83f08d4b21d2f84a679b3bf41323bd1650a954f63651836f1629051a
+size 268171578

run-bad69_00000/checkpoint-6500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed92348d85e70d049b7a466a6f858e352fc3be41f2e9ee0582e577a198701baf
+size 14244

run-bad69_00000/checkpoint-6500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f6b14cf57a98d6b6733ebf7c6dbd4c4fce261eef44ed2d3738e8132a9c471c7
+size 1064

run-bad69_00000/checkpoint-6500/trainer_state.json

@@ -0,0 +1,206 @@
+{
+  "best_metric": 0.16458247601985931,
+  "best_model_checkpoint": "mgh6/TCS_Pair/run-bad69_00000/checkpoint-6500",
+  "epoch": 1.7480166733898077,
+  "eval_steps": 500,
+  "global_step": 6500,
+  "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
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.000786228087003387,
+      "loss": 0.1285,
+      "step": 1000
+    },
+    {
+      "epoch": 0.27,
+      "eval_loss": 0.19461262226104736,
+      "eval_runtime": 21.0052,
+      "eval_samples_per_second": 228.086,
+      "eval_steps_per_second": 28.517,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0007808693895728842,
+      "loss": 0.1232,
+      "step": 1500
+    },
+    {
+      "epoch": 0.4,
+      "eval_loss": 0.268852174282074,
+      "eval_runtime": 21.1069,
+      "eval_samples_per_second": 226.988,
+      "eval_steps_per_second": 28.379,
+      "step": 1500
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.0007755106921423813,
+      "loss": 0.1182,
+      "step": 2000
+    },
+    {
+      "epoch": 0.54,
+      "eval_loss": 0.18187156319618225,
+      "eval_runtime": 21.0753,
+      "eval_samples_per_second": 227.328,
+      "eval_steps_per_second": 28.422,
+      "step": 2000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0007701519947118784,
+      "loss": 0.1642,
+      "step": 2500
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 0.25392478704452515,
+      "eval_runtime": 21.48,
+      "eval_samples_per_second": 223.045,
+      "eval_steps_per_second": 27.886,
+      "step": 2500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 0.0007647932972813753,
+      "loss": 0.1779,
+      "step": 3000
+    },
+    {
+      "epoch": 0.81,
+      "eval_loss": 0.2446264624595642,
+      "eval_runtime": 21.3207,
+      "eval_samples_per_second": 224.711,
+      "eval_steps_per_second": 28.095,
+      "step": 3000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 0.0007594345998508726,
+      "loss": 0.1776,
+      "step": 3500
+    },
+    {
+      "epoch": 0.94,
+      "eval_loss": 0.2562008798122406,
+      "eval_runtime": 21.0095,
+      "eval_samples_per_second": 228.039,
+      "eval_steps_per_second": 28.511,
+      "step": 3500
+    },
+    {
+      "epoch": 1.08,
+      "learning_rate": 0.0007540759024203697,
+      "loss": 0.175,
+      "step": 4000
+    },
+    {
+      "epoch": 1.08,
+      "eval_loss": 0.2355659455060959,
+      "eval_runtime": 21.3063,
+      "eval_samples_per_second": 224.863,
+      "eval_steps_per_second": 28.114,
+      "step": 4000
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 0.0007487172049898666,
+      "loss": 0.1362,
+      "step": 4500
+    },
+    {
+      "epoch": 1.21,
+      "eval_loss": 0.21570900082588196,
+      "eval_runtime": 21.316,
+      "eval_samples_per_second": 224.761,
+      "eval_steps_per_second": 28.101,
+      "step": 4500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 0.0007433585075593637,
+      "loss": 0.1122,
+      "step": 5000
+    },
+    {
+      "epoch": 1.34,
+      "eval_loss": 0.1876734346151352,
+      "eval_runtime": 21.4079,
+      "eval_samples_per_second": 223.796,
+      "eval_steps_per_second": 27.98,
+      "step": 5000
+    },
+    {
+      "epoch": 1.48,
+      "learning_rate": 0.0007379998101288608,
+      "loss": 0.101,
+      "step": 5500
+    },
+    {
+      "epoch": 1.48,
+      "eval_loss": 0.18231742084026337,
+      "eval_runtime": 21.3418,
+      "eval_samples_per_second": 224.489,
+      "eval_steps_per_second": 28.067,
+      "step": 5500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.0007326411126983579,
+      "loss": 0.1007,
+      "step": 6000
+    },
+    {
+      "epoch": 1.61,
+      "eval_loss": 0.16691634058952332,
+      "eval_runtime": 21.7262,
+      "eval_samples_per_second": 220.517,
+      "eval_steps_per_second": 27.57,
+      "step": 6000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.000727282415267855,
+      "loss": 0.0956,
+      "step": 6500
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 0.16458247601985931,
+      "eval_runtime": 21.9766,
+      "eval_samples_per_second": 218.005,
+      "eval_steps_per_second": 27.256,
+      "step": 6500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 74360,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 6602651034088368.0,
+  "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-6500/training_args.bin

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