Training in progress, step 100, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "facebook/esm2_t12_35M_UR50D",
+  "architectures": [
+    "EsmForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.01,
+  "classifier_dropout": null,
+  "emb_layer_norm_before": false,
+  "esmfold_config": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.01,
+  "hidden_size": 480,
+  "initializer_range": 0.02,
+  "intermediate_size": 1920,
+  "is_folding_model": false,
+  "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",
+  "token_dropout": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.1",
+  "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:eefda298f75891da5b3b7123f655f917920cb3deba4b8b2c7dd47558aa20dafb
+size 136000488

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0c3f8d6724cc803d2a68c8b8964379f0d89a73a38d3dc1c032cf748e90b484a4
+size 268176506

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bf3f3c24bb80a8453d4f69a54971bc84e22f4d6c02bfcca11e053397356566a
+size 15006

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4a92e9ad8019c6268839642eaf93ddfbc87d95771e6168ef7c982099d3cceca
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 1.3059791326522827,
+  "best_model_checkpoint": "mgh6/TCS_MLM_50/checkpoint-100",
+  "epoch": 0.02902757619738752,
+  "eval_steps": 100,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02902757619738752,
+      "grad_norm": 0.5972162485122681,
+      "learning_rate": 0.0009970972423802612,
+      "loss": 3.1833,
+      "step": 100
+    },
+    {
+      "epoch": 0.02902757619738752,
+      "eval_loss": 1.3059791326522827,
+      "eval_runtime": 213.3119,
+      "eval_samples_per_second": 213.298,
+      "eval_steps_per_second": 3.333,
+      "step": 100
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 34450,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1000387607789568.0,
+  "train_batch_size": 64,
+  "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:ee0ef74173b2c9a49dca197269030629fd4de03cd43419ed74c4742b9a5dba90
+size 5368