Gaussian 512 fine-tuned CoNLL 2002 es with f1/acc 0.8707/0.981

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9810101468170739,
+    "eval_f1": 0.8706660583941607,
+    "eval_loss": 0.092462919652462,
+    "eval_precision": 0.8643568840579711,
+    "eval_recall": 0.8770680147058824,
+    "eval_runtime": 19.171,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 99.942,
+    "eval_steps_per_second": 6.259,
+    "train_loss": 0.04096609338002562,
+    "train_runtime": 1383.1538,
+    "train_samples": 8324,
+    "train_samples_per_second": 30.091,
+    "train_steps_per_second": 1.883
+}

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "bertin-project/bertin-base-gaussian-exp-512seqlen",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "finetuning_task": "ner",
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "7": 7,
+    "8": 8
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "0": 0,
+    "1": 1,
+    "2": 2,
+    "3": 3,
+    "4": 4,
+    "5": 5,
+    "6": 6,
+    "7": 7,
+    "8": 8
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 5.0,
+    "eval_accuracy": 0.9810101468170739,
+    "eval_f1": 0.8706660583941607,
+    "eval_loss": 0.092462919652462,
+    "eval_precision": 0.8643568840579711,
+    "eval_recall": 0.8770680147058824,
+    "eval_runtime": 19.171,
+    "eval_samples": 1916,
+    "eval_samples_per_second": 99.942,
+    "eval_steps_per_second": 6.259
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8f56f5ad449dbd57ab38dae534ec652d4217cdb901ae56646a8c37352b48d5
+size 496332529

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": true, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "special_tokens_map_file": null, "name_or_path": "bertin-project/bertin-base-gaussian-exp-512seqlen", "tokenizer_class": "RobertaTokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 0.04096609338002562,
+    "train_runtime": 1383.1538,
+    "train_samples": 8324,
+    "train_samples_per_second": 30.091,
+    "train_steps_per_second": 1.883
+}

trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 2605,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.96,
+      "learning_rate": 4.040307101727447e-05,
+      "loss": 0.1122,
+      "step": 500
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 3.080614203454895e-05,
+      "loss": 0.0432,
+      "step": 1000
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 2.1209213051823416e-05,
+      "loss": 0.0261,
+      "step": 1500
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 1.161228406909789e-05,
+      "loss": 0.0177,
+      "step": 2000
+    },
+    {
+      "epoch": 4.8,
+      "learning_rate": 2.015355086372361e-06,
+      "loss": 0.0121,
+      "step": 2500
+    },
+    {
+      "epoch": 5.0,
+      "step": 2605,
+      "total_flos": 1.087585926764544e+16,
+      "train_loss": 0.04096609338002562,
+      "train_runtime": 1383.1538,
+      "train_samples_per_second": 30.091,
+      "train_steps_per_second": 1.883
+    }
+  ],
+  "max_steps": 2605,
+  "num_train_epochs": 5,
+  "total_flos": 1.087585926764544e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38809d0551f7e7d28187722f88870e0f68e199a69d8cbb477c71a26acf59dec6
+size 2735