Training in progress, step 5000, checkpoint

.gitattributes

@@ -38,3 +38,4 @@ checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-5000/config.json

@@ -0,0 +1,35 @@
+{
+  "architectures": [
+    "XLMRobertaForTokenClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "B",
+    "1": "I"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "B": 0,
+    "I": 1
+  },
+  "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",
+  "transformers_version": "4.57.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

checkpoint-5000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6851475dfa56e9957fd24aade53eafba9396483c39126f3a7f15f28895d6c4a
+size 1109842416

checkpoint-5000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed4b971f10987f9f8112a3f7cb853f00311d991a94dd40298602e8ad9be5817c
+size 2219806475

checkpoint-5000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3760687201e034be1d18b3c7d13e26fffba00327ba9efc9a6e351387437b5d5
+size 14645

checkpoint-5000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04d605f989c5d7f32ffff8c53ce9519b2220a388177fad64cbe7eae449887205
+size 1465

checkpoint-5000/sentencepiece.bpe.model

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

checkpoint-5000/special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-5000/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8373f9cd3d27591e1924426bcc1c8799bc5a9affc4fc857982c5d66668dd1f41
+size 17082832

checkpoint-5000/tokenizer_config.json

@@ -0,0 +1,59 @@
+{
+  "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>",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

checkpoint-5000/trainer_state.json

@@ -0,0 +1,164 @@
+{
+  "best_global_step": 5000,
+  "best_metric": 0.11183962970972061,
+  "best_model_checkpoint": "myanmar_text_segmentation_model/checkpoint-5000",
+  "epoch": 0.4594321418726454,
+  "eval_steps": 1000,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04594321418726454,
+      "grad_norm": 0.577109158039093,
+      "learning_rate": 1.9816594688964442e-05,
+      "loss": 0.1144,
+      "step": 500
+    },
+    {
+      "epoch": 0.09188642837452908,
+      "grad_norm": 0.8819814324378967,
+      "learning_rate": 1.9632821832215383e-05,
+      "loss": 0.1133,
+      "step": 1000
+    },
+    {
+      "epoch": 0.09188642837452908,
+      "eval_accuracy": 0.9564004775738034,
+      "eval_f1": 0.7581789101913106,
+      "eval_loss": 0.11448723077774048,
+      "eval_precision": 0.7703745996379334,
+      "eval_recall": 0.7463633395484631,
+      "eval_runtime": 465.4607,
+      "eval_samples_per_second": 61.528,
+      "eval_steps_per_second": 1.231,
+      "step": 1000
+    },
+    {
+      "epoch": 0.1378296425617936,
+      "grad_norm": 0.5137984156608582,
+      "learning_rate": 1.9449048975466325e-05,
+      "loss": 0.1119,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18377285674905816,
+      "grad_norm": 0.6753482222557068,
+      "learning_rate": 1.9265276118717266e-05,
+      "loss": 0.1115,
+      "step": 2000
+    },
+    {
+      "epoch": 0.18377285674905816,
+      "eval_accuracy": 0.9565513036953667,
+      "eval_f1": 0.7631813253052621,
+      "eval_loss": 0.11509840190410614,
+      "eval_precision": 0.7619568901058112,
+      "eval_recall": 0.7644097020785157,
+      "eval_runtime": 471.4797,
+      "eval_samples_per_second": 60.743,
+      "eval_steps_per_second": 1.215,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2297160709363227,
+      "grad_norm": 0.46862444281578064,
+      "learning_rate": 1.9081503261968207e-05,
+      "loss": 0.1083,
+      "step": 2500
+    },
+    {
+      "epoch": 0.2756592851235872,
+      "grad_norm": 0.6514066457748413,
+      "learning_rate": 1.889773040521915e-05,
+      "loss": 0.1085,
+      "step": 3000
+    },
+    {
+      "epoch": 0.2756592851235872,
+      "eval_accuracy": 0.955793370748351,
+      "eval_f1": 0.7617613129080717,
+      "eval_loss": 0.11627302318811417,
+      "eval_precision": 0.7514122514122514,
+      "eval_recall": 0.7723994268768838,
+      "eval_runtime": 464.541,
+      "eval_samples_per_second": 61.65,
+      "eval_steps_per_second": 1.233,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3216024993108518,
+      "grad_norm": 0.5837205052375793,
+      "learning_rate": 1.8713957548470093e-05,
+      "loss": 0.1068,
+      "step": 3500
+    },
+    {
+      "epoch": 0.3675457134981163,
+      "grad_norm": 0.590044379234314,
+      "learning_rate": 1.8530184691721034e-05,
+      "loss": 0.1076,
+      "step": 4000
+    },
+    {
+      "epoch": 0.3675457134981163,
+      "eval_accuracy": 0.9567566300121167,
+      "eval_f1": 0.7569129075628852,
+      "eval_loss": 0.11681018769741058,
+      "eval_precision": 0.7790560842692136,
+      "eval_recall": 0.7359936967250493,
+      "eval_runtime": 464.1614,
+      "eval_samples_per_second": 61.701,
+      "eval_steps_per_second": 1.234,
+      "step": 4000
+    },
+    {
+      "epoch": 0.41348892768538087,
+      "grad_norm": 0.43107616901397705,
+      "learning_rate": 1.8346411834971975e-05,
+      "loss": 0.1071,
+      "step": 4500
+    },
+    {
+      "epoch": 0.4594321418726454,
+      "grad_norm": 0.6132990121841431,
+      "learning_rate": 1.8162638978222916e-05,
+      "loss": 0.1056,
+      "step": 5000
+    },
+    {
+      "epoch": 0.4594321418726454,
+      "eval_accuracy": 0.9576032842071108,
+      "eval_f1": 0.7661190672004459,
+      "eval_loss": 0.11183962970972061,
+      "eval_precision": 0.7719609680194174,
+      "eval_recall": 0.7603649207638403,
+      "eval_runtime": 473.1438,
+      "eval_samples_per_second": 60.529,
+      "eval_steps_per_second": 1.211,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 54415,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.82981898783398e+16,
+  "train_batch_size": 50,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-5000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7075637656e60ad208ce432f8d752d195360885c38d2b55116963dc13f52450d
+size 5841