Training in progress, step 1000, checkpoint

.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
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

last-checkpoint/config.json

@@ -0,0 +1,25 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc7692416147ac3507d4785684662b73598d63eb3de42d49023c24e2c95f850e
+size 471641972

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:221fc5fa01e76b5c9738ac3e88160d9e81f91cbdf75071248c53106a613d11fb
+size 943408715

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ddef0af302d858629ee6e839c4c03676d7fb5e8ecf72e844bea591625e6c15a
+size 14645

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
+size 1383

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4403fd940f71a33a8adb6adb7bfa8324a48799df328fceb42fc6cd308ce99323
+size 1465

last-checkpoint/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": false,
+    "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
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af54fe549c06785a9c79eaa3f0c67144a19c56e1370229244d49c8a22fcaaec
+size 17082898

last-checkpoint/tokenizer_config.json

@@ -0,0 +1,60 @@
+{
+  "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": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "max_length": 120,
+  "model_max_length": 120,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,111 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.10152026598309688,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.00010152026598309688,
+      "grad_norm": 2.222202777862549,
+      "learning_rate": 0.0,
+      "loss": 3.5311,
+      "step": 1
+    },
+    {
+      "epoch": 0.010152026598309688,
+      "grad_norm": 5.846273422241211,
+      "learning_rate": 2.008113590263692e-05,
+      "loss": 1.9004,
+      "step": 100
+    },
+    {
+      "epoch": 0.020304053196619376,
+      "grad_norm": 6.481254577636719,
+      "learning_rate": 4.036511156186613e-05,
+      "loss": 1.9148,
+      "step": 200
+    },
+    {
+      "epoch": 0.030456079794929064,
+      "grad_norm": 7.6438822746276855,
+      "learning_rate": 6.064908722109534e-05,
+      "loss": 1.9316,
+      "step": 300
+    },
+    {
+      "epoch": 0.04060810639323875,
+      "grad_norm": 7.663699150085449,
+      "learning_rate": 8.093306288032456e-05,
+      "loss": 1.9834,
+      "step": 400
+    },
+    {
+      "epoch": 0.05076013299154844,
+      "grad_norm": 5.96785831451416,
+      "learning_rate": 9.9935883735841e-05,
+      "loss": 1.9575,
+      "step": 500
+    },
+    {
+      "epoch": 0.06091215958985813,
+      "grad_norm": 6.692135810852051,
+      "learning_rate": 9.886727933319086e-05,
+      "loss": 1.9436,
+      "step": 600
+    },
+    {
+      "epoch": 0.07106418618816782,
+      "grad_norm": 5.770139694213867,
+      "learning_rate": 9.779867493054072e-05,
+      "loss": 1.9121,
+      "step": 700
+    },
+    {
+      "epoch": 0.0812162127864775,
+      "grad_norm": 8.034317970275879,
+      "learning_rate": 9.673007052789058e-05,
+      "loss": 1.9588,
+      "step": 800
+    },
+    {
+      "epoch": 0.09136823938478719,
+      "grad_norm": 7.170871257781982,
+      "learning_rate": 9.566146612524043e-05,
+      "loss": 1.8942,
+      "step": 900
+    },
+    {
+      "epoch": 0.10152026598309688,
+      "grad_norm": 6.201202869415283,
+      "learning_rate": 9.45928617225903e-05,
+      "loss": 1.898,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 9851,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 542589699999744.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffa4f691bb08db07a8cac8fa2b5b9fa6e9597ffc5db34c4ac1549cbd15a85dcd
+size 5841