Training in progress, epoch 1, checkpoint

last-checkpoint/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "xaviergillard/brabant-xvii-from-scratch",
+  "architectures": [
+    "BertForPreTraining"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 24263
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd7034cffc604ac0bb2306480dbd29c66375ed1064aa84284e7f9ddc5c3bcbe7
+size 421197092

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53d48becb56e44a7fc75d4c3a8ac3dc0cb43d2dab2dc8ffd27ff953361cc8f0f
+size 842518266

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ecca4db0136c3537e24ce4cda906d3f7fa36bb872dba4dcf69667680d9abcd4
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f18e355220f7be0d28cf9768c1a2a0defa7052b6bf58d9c12772f32b11318f9
+size 1064

last-checkpoint/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,64 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 128,
+  "model_max_length": 1000000000000000019884624838656,
+  "never_split": null,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 3.539703845977783,
+  "best_model_checkpoint": "/content/drive/MyDrive/brabant-from-scratch/bi-objective/checkpoint-5687",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 5687,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "grad_norm": 7.530444622039795,
+      "learning_rate": 4.978020045718305e-05,
+      "loss": 0.3375,
+      "step": 500
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 8.392064094543457,
+      "learning_rate": 4.9560400914366104e-05,
+      "loss": 0.3686,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 8.53122615814209,
+      "learning_rate": 4.934060137154915e-05,
+      "loss": 0.361,
+      "step": 1500
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 7.576234340667725,
+      "learning_rate": 4.91208018287322e-05,
+      "loss": 0.3669,
+      "step": 2000
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 7.397663593292236,
+      "learning_rate": 4.890100228591525e-05,
+      "loss": 0.3608,
+      "step": 2500
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 8.71353530883789,
+      "learning_rate": 4.86812027430983e-05,
+      "loss": 0.3463,
+      "step": 3000
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 8.535433769226074,
+      "learning_rate": 4.8461403200281345e-05,
+      "loss": 0.3457,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 12.396780014038086,
+      "learning_rate": 4.8241603657464396e-05,
+      "loss": 0.3392,
+      "step": 4000
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 9.127644538879395,
+      "learning_rate": 4.802180411464745e-05,
+      "loss": 0.3473,
+      "step": 4500
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 8.218430519104004,
+      "learning_rate": 4.78020045718305e-05,
+      "loss": 0.323,
+      "step": 5000
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 12.705328941345215,
+      "learning_rate": 4.758220502901354e-05,
+      "loss": 0.3242,
+      "step": 5500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.539703845977783,
+      "eval_runtime": 41.371,
+      "eval_samples_per_second": 1648.256,
+      "eval_steps_per_second": 54.942,
+      "step": 5687
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 113740,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 500,
+  "total_flos": 2750382937430730.0,
+  "train_batch_size": 30,
+  "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:bd08e41a68165f6cf24ae1556c58069966a65178ea677129a240716e3fc7fd3d
+size 5048