Upload checkpoint-1365

.gitattributes

@@ -33,3 +33,4 @@ 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 +1,28 @@
+{
+  "architectures": [
+    "XLMRobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "problem_type": "multi_label_classification",
+  "transformers_version": "4.57.6",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5afe85109b34d54bcdfcd043a611925a1c6d60bbb4981d1cb9762832ae057cb6
+size 1112205008

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e37961b0010459a533447ff73c868d6c8d9ea78223e30f7039eee512ed9db92e
+size 2224532875

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9468bea5147f89b99cb8342b2c15e9c9fd4431e9b3dcb297e5ffa0319bad9539
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:de9873f44982749c625477131e8a40ba78f0297c0bc9d5f5c128d769935154aa
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ee3ddce54887ddb31fdf9ce85d46f40a6644164a1ce7fc32da5986665968d40
+size 1465

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 sha256:3ffb37461c391f096759f4a9bbbc329da0f36952f88bab061fcf84940c022e98
+size 17082999

tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,91 @@
+{
+  "best_global_step": 1365,
+  "best_metric": 0.8721528265204077,
+  "best_model_checkpoint": "../model/checkpoint-1365",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1365,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 12.363642692565918,
+      "learning_rate": 1.3347985347985349e-05,
+      "loss": 0.4356,
+      "step": 455
+    },
+    {
+      "epoch": 1.0,
+      "eval_f1_macro": 0.8346323361157264,
+      "eval_f1_micro": 0.8334897691008072,
+      "eval_loss": 0.30361834168434143,
+      "eval_precision": 0.8729846637829335,
+      "eval_recall": 0.7974137931034483,
+      "eval_runtime": 13.9315,
+      "eval_samples_per_second": 261.135,
+      "eval_steps_per_second": 4.091,
+      "step": 455
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 8.248332023620605,
+      "learning_rate": 6.681318681318681e-06,
+      "loss": 0.2774,
+      "step": 910
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1_macro": 0.8615056948788721,
+      "eval_f1_micro": 0.8600631852815461,
+      "eval_loss": 0.2571789026260376,
+      "eval_precision": 0.8910281093569503,
+      "eval_recall": 0.8311781609195402,
+      "eval_runtime": 14.3265,
+      "eval_samples_per_second": 253.935,
+      "eval_steps_per_second": 3.979,
+      "step": 910
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 8.038055419921875,
+      "learning_rate": 1.4652014652014653e-08,
+      "loss": 0.221,
+      "step": 1365
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1_macro": 0.8721528265204077,
+      "eval_f1_micro": 0.8710601719197708,
+      "eval_loss": 0.25890466570854187,
+      "eval_precision": 0.8685714285714285,
+      "eval_recall": 0.8735632183908046,
+      "eval_runtime": 13.9158,
+      "eval_samples_per_second": 261.429,
+      "eval_steps_per_second": 4.096,
+      "step": 1365
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1365,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.148400823329792e+16,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ece358947c1a7f05b113e7f0bdd313472cf78504cee40430b7e5a6fbfdf8fb62
+size 5841