model files

Best Bert classifier on the test set multilingual multilabel.

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.45.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fe2584345efefbe0ed11d793b9a048a48353467db57004928a34d9e699335e2
+size 711455760

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba214be2aca20edcaf99f7706629906c7a567f59aa322036c759b5c5d8a29a0e
+size 1423026938

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3811946552ce17d3fa03f5826a4f156bcd637257da3358fc87fc9daf59f51c3
+size 13990

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43948305d4de5007d74a0019041f1ef275584623c07425bc2e0271ce75238a8f
+size 1064

trainer_state.json

@@ -0,0 +1,169 @@
+{
+  "best_metric": 0.8333333333333334,
+  "best_model_checkpoint": "./models/roberta/checkpoint-56",
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 56,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.6466717720031738,
+      "learning_rate": 9.666666666666667e-05,
+      "loss": 0.1697,
+      "step": 7
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1_macro": 0.35912698412698413,
+      "eval_f1_micro": 0.45,
+      "eval_loss": 0.1369188129901886,
+      "eval_runtime": 7.5543,
+      "eval_samples_per_second": 1.589,
+      "eval_steps_per_second": 0.132,
+      "step": 7
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.6866563558578491,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 0.1247,
+      "step": 14
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1_macro": 0.49907407407407406,
+      "eval_f1_micro": 0.5641025641025641,
+      "eval_loss": 0.09602320194244385,
+      "eval_runtime": 6.4291,
+      "eval_samples_per_second": 1.867,
+      "eval_steps_per_second": 0.156,
+      "step": 14
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.0547248125076294,
+      "learning_rate": 9e-05,
+      "loss": 0.0901,
+      "step": 21
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1_macro": 0.7619047619047619,
+      "eval_f1_micro": 0.75,
+      "eval_loss": 0.07866408675909042,
+      "eval_runtime": 5.9612,
+      "eval_samples_per_second": 2.013,
+      "eval_steps_per_second": 0.168,
+      "step": 21
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 1.8302876949310303,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 0.0673,
+      "step": 28
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1_macro": 0.7431818181818182,
+      "eval_f1_micro": 0.8333333333333334,
+      "eval_loss": 0.0431751012802124,
+      "eval_runtime": 6.5441,
+      "eval_samples_per_second": 1.834,
+      "eval_steps_per_second": 0.153,
+      "step": 28
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 1.7726091146469116,
+      "learning_rate": 8.333333333333334e-05,
+      "loss": 0.0564,
+      "step": 35
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1_macro": 0.8095238095238096,
+      "eval_f1_micro": 0.8333333333333334,
+      "eval_loss": 0.04845364764332771,
+      "eval_runtime": 6.4361,
+      "eval_samples_per_second": 1.864,
+      "eval_steps_per_second": 0.155,
+      "step": 35
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.5374885201454163,
+      "learning_rate": 8e-05,
+      "loss": 0.0326,
+      "step": 42
+    },
+    {
+      "epoch": 6.0,
+      "eval_f1_macro": 0.8095238095238096,
+      "eval_f1_micro": 0.967741935483871,
+      "eval_loss": 0.024476679041981697,
+      "eval_runtime": 5.7698,
+      "eval_samples_per_second": 2.08,
+      "eval_steps_per_second": 0.173,
+      "step": 42
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.8273659348487854,
+      "learning_rate": 7.666666666666667e-05,
+      "loss": 0.0282,
+      "step": 49
+    },
+    {
+      "epoch": 7.0,
+      "eval_f1_macro": 0.8148148148148149,
+      "eval_f1_micro": 0.9333333333333333,
+      "eval_loss": 0.027787813916802406,
+      "eval_runtime": 5.897,
+      "eval_samples_per_second": 2.035,
+      "eval_steps_per_second": 0.17,
+      "step": 49
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 1.7157799005508423,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 0.0243,
+      "step": 56
+    },
+    {
+      "epoch": 8.0,
+      "eval_f1_macro": 0.8333333333333334,
+      "eval_f1_micro": 1.0,
+      "eval_loss": 0.010664558969438076,
+      "eval_runtime": 5.9437,
+      "eval_samples_per_second": 2.019,
+      "eval_steps_per_second": 0.168,
+      "step": 56
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 210,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "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": 225231152136192.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51a52c331810743912dd0843537f66cfc7d314fdd0da2da43ff1eb78ea789aa4
+size 5176