Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "FPTAI/velectra-base-discriminator-cased",
+  "_num_labels": 2,
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 768,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.44.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 32054
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde463bf311ac805eec2150338f697c9940a5c7a200ccc234d37162b4649aed5
+size 442668636

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec1ab9ed8d43fdcf9ecea3365f7eeaacaae0d08b25b5e24189e5e1a81dde674e
+size 885457146

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2477d3715e68f2549c9ecd6a18f4a17a0bfb0a625f50ce4fafa0aa2652affb1c
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b7251b468e4d3cb44eba0757f056754012975e532dc253bb53666972923e5b
+size 1064

last-checkpoint/trainer_state.json

@@ -0,0 +1,108 @@
+{
+  "best_metric": 7.66294542948405,
+  "best_model_checkpoint": "./results/checkpoint-916",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 916,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1091703056768559,
+      "grad_norm": 23.31266975402832,
+      "learning_rate": 2.959061135371179e-05,
+      "loss": 57.4375,
+      "step": 100
+    },
+    {
+      "epoch": 0.2183406113537118,
+      "grad_norm": 36.15751266479492,
+      "learning_rate": 2.918122270742358e-05,
+      "loss": 48.4816,
+      "step": 200
+    },
+    {
+      "epoch": 0.32751091703056767,
+      "grad_norm": 44.80302047729492,
+      "learning_rate": 2.877183406113537e-05,
+      "loss": 37.1763,
+      "step": 300
+    },
+    {
+      "epoch": 0.4366812227074236,
+      "grad_norm": 29.177419662475586,
+      "learning_rate": 2.8362445414847164e-05,
+      "loss": 25.613,
+      "step": 400
+    },
+    {
+      "epoch": 0.5458515283842795,
+      "grad_norm": 42.395999908447266,
+      "learning_rate": 2.7953056768558954e-05,
+      "loss": 16.5535,
+      "step": 500
+    },
+    {
+      "epoch": 0.6550218340611353,
+      "grad_norm": 41.26911926269531,
+      "learning_rate": 2.7543668122270742e-05,
+      "loss": 12.1195,
+      "step": 600
+    },
+    {
+      "epoch": 0.7641921397379913,
+      "grad_norm": 85.68878173828125,
+      "learning_rate": 2.7134279475982533e-05,
+      "loss": 9.5989,
+      "step": 700
+    },
+    {
+      "epoch": 0.8733624454148472,
+      "grad_norm": 29.508316040039062,
+      "learning_rate": 2.6724890829694323e-05,
+      "loss": 8.008,
+      "step": 800
+    },
+    {
+      "epoch": 0.982532751091703,
+      "grad_norm": 47.07627868652344,
+      "learning_rate": 2.6315502183406114e-05,
+      "loss": 7.4156,
+      "step": 900
+    },
+    {
+      "epoch": 1.0,
+      "eval_avg_mae": 7.66294542948405,
+      "eval_loss": 7.66294527053833,
+      "eval_mae_lex": 7.354457378387451,
+      "eval_mae_sem": 5.690549373626709,
+      "eval_mae_syn": 9.943828582763672,
+      "eval_runtime": 26.9061,
+      "eval_samples_per_second": 272.318,
+      "eval_steps_per_second": 8.511,
+      "step": 916
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 7328,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1927766233338624.0,
+  "train_batch_size": 32,
+  "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:aec1e778f9115caa4cace59b9d9ceebc1c6ef6b183b8ddbe4896f4510d7246ed
+size 5176