Upload 11 files

.gitattributes

@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,132 @@
+{
+  "_name_or_path": "mbruton/spa_XLM-R",
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "O",
+    "1": "r0:arg0",
+    "2": "r0:arg1",
+    "3": "r0:arg2",
+    "4": "r0:root",
+    "5": "r10:arg0",
+    "6": "r10:arg1",
+    "7": "r10:root",
+    "8": "r11:arg0",
+    "9": "r11:root",
+    "10": "r12:arg1",
+    "11": "r12:root",
+    "12": "r13:arg1",
+    "13": "r13:root",
+    "14": "r1:arg0",
+    "15": "r1:arg1",
+    "16": "r1:arg2",
+    "17": "r1:root",
+    "18": "r2:arg0",
+    "19": "r2:arg1",
+    "20": "r2:arg2",
+    "21": "r2:root",
+    "22": "r3:arg0",
+    "23": "r3:arg1",
+    "24": "r3:arg2",
+    "25": "r3:root",
+    "26": "r4:arg0",
+    "27": "r4:arg1",
+    "28": "r4:arg2",
+    "29": "r4:root",
+    "30": "r5:arg0",
+    "31": "r5:arg1",
+    "32": "r5:arg2",
+    "33": "r5:root",
+    "34": "r6:arg0",
+    "35": "r6:arg1",
+    "36": "r6:arg2",
+    "37": "r6:root",
+    "38": "r7:arg0",
+    "39": "r7:arg1",
+    "40": "r7:arg2",
+    "41": "r7:root",
+    "42": "r8:arg0",
+    "43": "r8:arg1",
+    "44": "r8:arg2",
+    "45": "r8:root",
+    "46": "r9:arg0",
+    "47": "r9:arg1",
+    "48": "r9:arg2",
+    "49": "r9:root"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "O": 0,
+    "r0:arg0": 1,
+    "r0:arg1": 2,
+    "r0:arg2": 3,
+    "r0:root": 4,
+    "r10:arg0": 5,
+    "r10:arg1": 6,
+    "r10:root": 7,
+    "r11:arg0": 8,
+    "r11:root": 9,
+    "r12:arg1": 10,
+    "r12:root": 11,
+    "r13:arg1": 12,
+    "r13:root": 13,
+    "r1:arg0": 14,
+    "r1:arg1": 15,
+    "r1:arg2": 16,
+    "r1:root": 17,
+    "r2:arg0": 18,
+    "r2:arg1": 19,
+    "r2:arg2": 20,
+    "r2:root": 21,
+    "r3:arg0": 22,
+    "r3:arg1": 23,
+    "r3:arg2": 24,
+    "r3:root": 25,
+    "r4:arg0": 26,
+    "r4:arg1": 27,
+    "r4:arg2": 28,
+    "r4:root": 29,
+    "r5:arg0": 30,
+    "r5:arg1": 31,
+    "r5:arg2": 32,
+    "r5:root": 33,
+    "r6:arg0": 34,
+    "r6:arg1": 35,
+    "r6:arg2": 36,
+    "r6:root": 37,
+    "r7:arg0": 38,
+    "r7:arg1": 39,
+    "r7:arg2": 40,
+    "r7:root": 41,
+    "r8:arg0": 42,
+    "r8:arg1": 43,
+    "r8:arg2": 44,
+    "r8:root": 45,
+    "r9:arg0": 46,
+    "r9:arg1": 47,
+    "r9:arg2": 48,
+    "r9:root": 49
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.4",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e61f35bd7651c584c19a9a00f0469d778bc83e10ef8132d040aba70f73510941
+size 2220047461

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:278bd8f81f2edc24470acdf65f3b847ebfdf4f74836f81f4669aeb34b9276233
+size 1110037105

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:067a3d9d4296a0274f96eb2257ae1d69ee29e64b2d5ab3e3a4d2593d403c095c
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b14881f8352737c801b7e15ff2544419ace05937680ded1c03cfe4be45005e78
+size 623

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2c509a525eb51aebb33fb59c24ee923c1d4c1db23c3ae81fe05ccf354084f7b
+size 17082758

tokenizer_config.json

@@ -0,0 +1,19 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.2869763970375061,
+  "best_model_checkpoint": "gal_sp_XLM-R/checkpoint-1250",
+  "epoch": 6.0,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8985218351324828,
+      "eval_f1": 0.6311757348342715,
+      "eval_loss": 0.3683431148529053,
+      "eval_precision": 0.6882032049096488,
+      "eval_recall": 0.5828761189719897,
+      "eval_runtime": 5.2404,
+      "eval_samples_per_second": 190.252,
+      "eval_steps_per_second": 12.022,
+      "step": 250
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 1.9600000000000002e-05,
+      "loss": 0.4521,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9153888616290481,
+      "eval_f1": 0.7093653817968636,
+      "eval_loss": 0.3080022931098938,
+      "eval_precision": 0.7202380952380952,
+      "eval_recall": 0.6988160554432573,
+      "eval_runtime": 5.2307,
+      "eval_samples_per_second": 190.605,
+      "eval_steps_per_second": 12.044,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9145608439646713,
+      "eval_f1": 0.7130997607992121,
+      "eval_loss": 0.3053981065750122,
+      "eval_precision": 0.6953896816684961,
+      "eval_recall": 0.7317354894600058,
+      "eval_runtime": 5.3687,
+      "eval_samples_per_second": 185.707,
+      "eval_steps_per_second": 11.735,
+      "step": 750
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 1.9200000000000003e-05,
+      "loss": 0.2426,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.919191609421001,
+      "eval_f1": 0.7231791866199699,
+      "eval_loss": 0.3031836450099945,
+      "eval_precision": 0.7160651096956829,
+      "eval_recall": 0.7304360381172393,
+      "eval_runtime": 5.2453,
+      "eval_samples_per_second": 190.075,
+      "eval_steps_per_second": 12.011,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9235157016683022,
+      "eval_f1": 0.7326776277157957,
+      "eval_loss": 0.2869763970375061,
+      "eval_precision": 0.7451478053150195,
+      "eval_recall": 0.7206179613052267,
+      "eval_runtime": 5.215,
+      "eval_samples_per_second": 191.179,
+      "eval_steps_per_second": 12.081,
+      "step": 1250
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 1.88e-05,
+      "loss": 0.1812,
+      "step": 1500
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9199889597644749,
+      "eval_f1": 0.729057033138956,
+      "eval_loss": 0.3071407973766327,
+      "eval_precision": 0.718329596412556,
+      "eval_recall": 0.7401097314467225,
+      "eval_runtime": 5.2244,
+      "eval_samples_per_second": 190.835,
+      "eval_steps_per_second": 12.059,
+      "step": 1500
+    }
+  ],
+  "max_steps": 25000,
+  "num_train_epochs": 100,
+  "total_flos": 925793237842200.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a7619848a0cb6b2fa7cf3db3f5eb737e39b2aeba4baa6dc309c391784450c1b
+size 3503