Training in progress, step 6

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 1.0,
+    "eval_DISORDER_FINDING_f1": 0.2105263157894737,
+    "eval_DISORDER_FINDING_number": 11,
+    "eval_DISORDER_FINDING_precision": 0.25,
+    "eval_DISORDER_FINDING_recall": 0.18181818181818182,
+    "eval_loss": 0.4071013033390045,
+    "eval_overall_accuracy": 0.9285714285714286,
+    "eval_overall_f1": 0.2105263157894737,
+    "eval_overall_precision": 0.25,
+    "eval_overall_recall": 0.18181818181818182,
+    "eval_runtime": 0.111,
+    "eval_samples": 8,
+    "eval_samples_per_second": 72.05,
+    "eval_steps_per_second": 9.006,
+    "total_flos": 169988587296.0,
+    "train_loss": 0.5826312402884165,
+    "train_runtime": 1.8733,
+    "train_samples": 364,
+    "train_samples_per_second": 194.314,
+    "train_steps_per_second": 3.203
+}

config.json

@@ -0,0 +1,36 @@
+{
+  "_name_or_path": "DedalusHealthCare/tinybert-mlm-de",
+  "architectures": [
+    "BertForTokenClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "finetuning_task": "ner",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 312,
+  "id2label": {
+    "0": "B-DISORDER_FINDING",
+    "1": "O"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 312,
+  "label2id": {
+    "B-DISORDER_FINDING": 0,
+    "O": 1
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 4,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "pre_trained": "",
+  "torch_dtype": "float32",
+  "training": "",
+  "transformers_version": "4.45.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 31102
+}

eval_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.0,
+    "eval_DISORDER_FINDING_f1": 0.2105263157894737,
+    "eval_DISORDER_FINDING_number": 11,
+    "eval_DISORDER_FINDING_precision": 0.25,
+    "eval_DISORDER_FINDING_recall": 0.18181818181818182,
+    "eval_loss": 0.4071013033390045,
+    "eval_overall_accuracy": 0.9285714285714286,
+    "eval_overall_f1": 0.2105263157894737,
+    "eval_overall_precision": 0.25,
+    "eval_overall_recall": 0.18181818181818182,
+    "eval_runtime": 0.111,
+    "eval_samples": 8,
+    "eval_samples_per_second": 72.05,
+    "eval_steps_per_second": 9.006
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0854af4c01065989cc4a56fcfb52c5770bfc553b2f42511a7b9dd218278bd7e
+size 48864824

runs/Sep15_15-34-43_ce4383d2c132/events.out.tfevents.1757943289.ce4383d2c132.1231.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dd147baf1824531878e3f4107377ff3b8b0c2a3a145a46b016495acfea9b774
+size 82616

runs/Sep15_15-37-05_ce4383d2c132/events.out.tfevents.1757943430.ce4383d2c132.1324.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66257206bc26436905f5f3531cbd8eb147766649e9d1ccec03ff46e44f8de915
+size 82616

runs/Sep15_20-28-36_a27e4585d89f/events.out.tfevents.1757960922.a27e4585d89f.190.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce8eff20293c459931c769859744b1bfa83665c279d93d663b72bbce0eb289c9
+size 82616

runs/Sep15_20-32-25_a27e4585d89f/events.out.tfevents.1757961151.a27e4585d89f.283.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e69341215a7f269a0115974f938d72c0469ca30f514ec66708a834b3344066fe
+size 82616

runs/Sep15_20-34-16_a27e4585d89f/events.out.tfevents.1757961262.a27e4585d89f.376.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44cb84865bf4c532caff61b7dbd1223a1d251c341166d2ea3cd8fbf4d8c9174f
+size 82616

runs/Sep15_20-37-59_a27e4585d89f/events.out.tfevents.1757961484.a27e4585d89f.469.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fded66a4605fc56e0ccf72794096864dda36d3396106cb06fbf8043ee53a840
+size 82616

runs/Sep24_11-47-55_4328ad0fab36/events.out.tfevents.1758707283.4328ad0fab36.261.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:561722b0fe0ae0051b5f91a7ccb0f18753cee793f2ecb4d5be606d5c6064f848
+size 82616

runs/Sep24_13-01-03_4328ad0fab36/events.out.tfevents.1758711668.4328ad0fab36.374.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15d26168c329ca809e454798699c2e537d7a19abd5df46e99c36500301e595d2
+size 5210

runs/Sep24_13-18-09_4328ad0fab36/events.out.tfevents.1758712694.4328ad0fab36.467.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:939448090a43718996f2a09be6ca71de99001d416b243e1398a623ff2cd9b82a
+size 5765

runs/Sep24_13-18-09_4328ad0fab36/events.out.tfevents.1758712696.4328ad0fab36.467.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0a786e0edc19caf097d6f992bdedc113113ecb1dab9fc1169fb489078b5c1e9
+size 846

runs/Sep24_13-53-35_4328ad0fab36/events.out.tfevents.1758714820.4328ad0fab36.578.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae1daa2747fc184ce5046a2e22a3ade2c4b3963c9af5a2d1c7d20db2af947020
+size 5765

runs/Sep24_13-53-35_4328ad0fab36/events.out.tfevents.1758714822.4328ad0fab36.578.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e45ce1702c7eea47b1a34fa7a1271de9ee447f72e63d8271ba2df5d8957b237
+size 846

runs/Sep24_15-11-25_4328ad0fab36/events.out.tfevents.1758719492.4328ad0fab36.689.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb17cb6aa5f400ce27e7e821030f16a6f94d5a4882da80f33b625733aac0b3f0
+size 5796

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "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": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "104": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 256,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": true,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 169988587296.0,
+    "train_loss": 0.5826312402884165,
+    "train_runtime": 1.8733,
+    "train_samples": 364,
+    "train_samples_per_second": 194.314,
+    "train_steps_per_second": 3.203
+}

trainer_state.json

@@ -0,0 +1,49 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 10000,
+  "global_step": 6,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 6.2256364822387695,
+      "learning_rate": 5e-05,
+      "loss": 0.6898,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "step": 6,
+      "total_flos": 169988587296.0,
+      "train_loss": 0.5826312402884165,
+      "train_runtime": 1.8733,
+      "train_samples_per_second": 194.314,
+      "train_steps_per_second": 3.203
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 6,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 15000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 169988587296.0,
+  "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:a963432714c3e0f5657852b8d170f72e057164e7fc25066f74315376d6409d9f
+size 5304