Training in progress, step 1000, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "mgh6/TCS_MLM",
+  "architectures": [
+    "EsmForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.01,
+  "classifier_dropout": 0.0,
+  "emb_layer_norm_before": false,
+  "esmfold_config": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.01,
+  "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": "4.36.2",
+  "use_cache": true,
+  "vocab_list": null,
+  "vocab_size": 33
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a022506ca120afd8353e4b96f1b5eb7fd3aa6b824cdc3c89fbb3bfd87337f763
+size 135998360

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d03aa6d85948cd08c54580de89678fd914bfa13425102626365c66caff47179d
+size 268169559

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:504e9619c88e849667bbc202f485d53738df6d90104f87ff3dff23d30bf6e19b
+size 14503

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:636cb99335b952eb5bdca42ca2b7676456a7a1a5cae0b252e306f477ad62c8ea
+size 623

last-checkpoint/trainer_state.json

@@ -0,0 +1,35 @@
+{
+  "best_metric": 0.07249107211828232,
+  "best_model_checkpoint": "mgh6/TCS_Pairing/checkpoint-1000",
+  "epoch": 0.11934598400763814,
+  "eval_steps": 1000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.40327007996181e-05,
+      "loss": 0.0928,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12,
+      "eval_loss": 0.07249107211828232,
+      "eval_runtime": 165.3451,
+      "eval_samples_per_second": 153.63,
+      "eval_steps_per_second": 19.208,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 1000,
+  "max_steps": 16758,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 1000,
+  "total_flos": 2500930816896000.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f57e735ecdbd36abe84f100f9b2112de636300c625aacf811cfd6ae6323ce117
+size 4271