Training in progress, step 10, 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": 0.1,
+  "emb_layer_norm_before": false,
+  "esmfold_config": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "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": "4.45.2",
+  "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 sha256:6fad645606f766214a513d9abb3702cf400c1430b3b13570ca42f83211e78def
+size 136989964

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:20d8bbbd03574954ac0026ba23687f2aecc2cdb07d19ca3d94ebe2c1ae59fac2
+size 270158266

last-checkpoint/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e9a96b6c55c20afe790a8cb205455bae2a418c09960c194e65eddb9785262d7
+size 15024

last-checkpoint/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd4d69880c1b60618f72780d51d2d76cb0b198b111993bd92a128c3ed93a64aa
+size 15024

last-checkpoint/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e7865bbaacc07e097c0c8122b00cb8d8a73668ff7b1e8113b0cf2ed098e0807
+size 15024

last-checkpoint/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e944f069d6dc1604a8bb0c976abc85c20d8cac4ec389e120fe342888d1f04c4
+size 15024

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c977fb38c051b92c0da24652d501a434592fa15ac6055c06154f25847bf8d87
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,57 @@
+{
+  "best_metric": 1.2486435174942017,
+  "best_model_checkpoint": "mgh6/TCS_Pair_base/checkpoint-10",
+  "epoch": 0.06514657980456026,
+  "eval_steps": 10,
+  "global_step": 10,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06514657980456026,
+      "grad_norm": 2.7395334243774414,
+      "learning_rate": 0.0009934640522875817,
+      "loss": 7.51,
+      "step": 10
+    },
+    {
+      "epoch": 0.06514657980456026,
+      "eval_loss": 1.2486435174942017,
+      "eval_runtime": 0.2205,
+      "eval_samples_per_second": 181.375,
+      "eval_steps_per_second": 4.534,
+      "step": 10
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1530,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 10,
+  "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": 0.0,
+  "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:d29db146f9eb0a1a33d2b16499a21e602f1b99053241fe8a767d24522d0e3cb2
+size 5240