Training in progress, step 1500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17791bc22c6f05b36b99409e29274db5eb1df6ef000e66bbadaf86373089dc53
+oid sha256:2ddcdabb355032ab95f0a91327cfea6d659383376a69ee82ecbe9ad20ecd4726
 size 135998360

run-faa58daf/checkpoint-1500/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-1500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ddcdabb355032ab95f0a91327cfea6d659383376a69ee82ecbe9ad20ecd4726
+size 135998360

run-faa58daf/checkpoint-1500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea15bd39cc346e891c3270b16d720f0edaa7ddfbf13c3f4bcef053fcbff01a7d
+size 268171578

run-faa58daf/checkpoint-1500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2acb815b799e8cba0b70a8d0da1883b1e7c91225cd427c4bf2c2c16eb2c55b12
+size 14244

run-faa58daf/checkpoint-1500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40ee36d28051608bd421f8249115cecd4856fa0fb491c191462c9cf6fc37f3a5
+size 1064

run-faa58daf/checkpoint-1500/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": 0.13721677660942078,
+  "best_model_checkpoint": "mgh6/TCS_Pair/run-faa58daf/checkpoint-1000",
+  "epoch": 3.017299181976666,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "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
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 0.0006607631369613704,
+      "loss": 0.0411,
+      "step": 1000
+    },
+    {
+      "epoch": 2.01,
+      "eval_loss": 0.13721677660942078,
+      "eval_runtime": 20.95,
+      "eval_samples_per_second": 228.687,
+      "eval_steps_per_second": 28.592,
+      "step": 1000
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 0.0006238077042454101,
+      "loss": 0.0246,
+      "step": 1500
+    },
+    {
+      "epoch": 3.02,
+      "eval_loss": 0.17266754806041718,
+      "eval_runtime": 21.3503,
+      "eval_samples_per_second": 224.4,
+      "eval_steps_per_second": 28.056,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 9940,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 1.142682281916552e+16,
+  "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-1500/training_args.bin

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