Training in progress, epoch 1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "\n": 50265
+}

config.json

@@ -0,0 +1,56 @@
+{
+  "_name_or_path": "models/codebert-base-mlm-finetune-logchunks",
+  "architectures": [
+    "RobertaForTokenClassification"
+  ],
+  "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": [
+    "eol",
+    "msg",
+    "cmd",
+    "var",
+    "dff",
+    "pgr",
+    "stk",
+    "itm",
+    "hex",
+    "yml",
+    "obj",
+    "tre"
+  ],
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "cmd": 2,
+    "dff": 4,
+    "eol": 0,
+    "hex": 8,
+    "itm": 7,
+    "msg": 1,
+    "obj": 10,
+    "pgr": 5,
+    "stk": 6,
+    "tre": 11,
+    "var": 3,
+    "yml": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "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": "4.48.1",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cdefe642c4182dfeb95979af9a12c1a1588ce8d34a2a30413d545b1d5b34535
+size 496281000

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,66 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50118": {
+      "content": "Ċ",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50264": {
+      "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>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,75 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.24907063197026022,
+  "eval_steps": 500,
+  "global_step": 67,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03717472118959108,
+      "grad_norm": 13.546404838562012,
+      "learning_rate": 1.8587360594795542e-07,
+      "loss": 2.8346,
+      "step": 10
+    },
+    {
+      "epoch": 0.07434944237918216,
+      "grad_norm": 19.084455490112305,
+      "learning_rate": 3.7174721189591085e-07,
+      "loss": 2.7026,
+      "step": 20
+    },
+    {
+      "epoch": 0.11152416356877323,
+      "grad_norm": 13.80436897277832,
+      "learning_rate": 5.576208178438662e-07,
+      "loss": 2.6825,
+      "step": 30
+    },
+    {
+      "epoch": 0.14869888475836432,
+      "grad_norm": 12.587150573730469,
+      "learning_rate": 7.434944237918217e-07,
+      "loss": 2.6652,
+      "step": 40
+    },
+    {
+      "epoch": 0.18587360594795538,
+      "grad_norm": 21.958721160888672,
+      "learning_rate": 9.29368029739777e-07,
+      "loss": 2.5917,
+      "step": 50
+    },
+    {
+      "epoch": 0.22304832713754646,
+      "grad_norm": 13.547331809997559,
+      "learning_rate": 1.1152416356877324e-06,
+      "loss": 2.5062,
+      "step": 60
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2690,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 28652861008152.0,
+  "train_batch_size": 3,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a299b61fdd81851a0ed09d68c87c48192c980c0558d8489aa9a65a0f20d7dd5
+size 5368