added model files

.gitattributes

@@ -25,3 +25,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text
+tf_model.h5 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,9 @@
 ---
+
+language: 
+- java
 license: mit
+datasets:
+- anjandash/java-8m-methods-v1
+
 ---

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/Users/anjandash/Desktop/HF_MODELS/JavaBERT-mini",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 2,
+  "classifier_dropout": null,
+  "eos_token_id": 3,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "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",
+  "torch_dtype": "float32",
+  "transformers_version": "4.9.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 64000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0c371486c3dbeba52fa5dfdf0339d683e07ad48f522bb5591e7b05b29b168e4
+size 541120363

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c63473cbc227f7e033c718d5fe751c9fc06b04c77f134c7501e3dfea031f4a61
+size 15523

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61f32f894187fb542f29cbbe7f61fa211719166ef17c8a5665f9cdb762ff442f
+size 559

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44017bf2efe324f988668a411fe5cb0bc3c79dce3ffb98f210b9bb0c3b61a0ff
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "[CLS]", "eos_token": "[SEP]", "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tf_model.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7de810b3f312aecc96faaa27da7b5425ea9d6418a37703829905d079efb83af8
+size 541067608

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": true, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "/home/akarmakar/Project2/tokenizer/jemma-java-bert-tokenizer", "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,128 @@
+{
+  "best_metric": 1.2563587427139282,
+  "best_model_checkpoint": "finetuned-bert__java-8m-methods__jemma-java-bert-tokenizer/checkpoint-5000",
+  "epoch": 4.669020454611771,
+  "global_step": 40000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.0004888116319438376,
+      "loss": 3.0057,
+      "step": 5000
+    },
+    {
+      "epoch": 0.58,
+      "eval_loss": 1.2563587427139282,
+      "eval_runtime": 836.9828,
+      "eval_samples_per_second": 59.343,
+      "eval_steps_per_second": 7.418,
+      "step": 5000
+    },
+    {
+      "epoch": 1.17,
+      "learning_rate": 0.00044517243817696517,
+      "loss": 1.5788,
+      "step": 10000
+    },
+    {
+      "epoch": 1.17,
+      "eval_loss": 6.417298793792725,
+      "eval_runtime": 835.6884,
+      "eval_samples_per_second": 59.435,
+      "eval_steps_per_second": 7.43,
+      "step": 10000
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 0.00037428394451934934,
+      "loss": 5.9109,
+      "step": 15000
+    },
+    {
+      "epoch": 1.75,
+      "eval_loss": 6.413046836853027,
+      "eval_runtime": 833.6127,
+      "eval_samples_per_second": 59.583,
+      "eval_steps_per_second": 7.448,
+      "step": 15000
+    },
+    {
+      "epoch": 2.33,
+      "learning_rate": 0.00028607867802092244,
+      "loss": 5.9036,
+      "step": 20000
+    },
+    {
+      "epoch": 2.33,
+      "eval_loss": 6.433701038360596,
+      "eval_runtime": 833.0303,
+      "eval_samples_per_second": 59.624,
+      "eval_steps_per_second": 7.454,
+      "step": 20000
+    },
+    {
+      "epoch": 2.92,
+      "learning_rate": 0.00019284648488204127,
+      "loss": 5.9003,
+      "step": 25000
+    },
+    {
+      "epoch": 2.92,
+      "eval_loss": 6.432703971862793,
+      "eval_runtime": 833.1905,
+      "eval_samples_per_second": 59.613,
+      "eval_steps_per_second": 7.452,
+      "step": 25000
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 0.00010757762475595697,
+      "loss": 5.8971,
+      "step": 30000
+    },
+    {
+      "epoch": 3.5,
+      "eval_loss": 6.4252238273620605,
+      "eval_runtime": 846.7073,
+      "eval_samples_per_second": 58.661,
+      "eval_steps_per_second": 7.333,
+      "step": 30000
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 4.217367458660157e-05,
+      "loss": 5.8972,
+      "step": 35000
+    },
+    {
+      "epoch": 4.09,
+      "eval_loss": 6.429380416870117,
+      "eval_runtime": 846.9722,
+      "eval_samples_per_second": 58.643,
+      "eval_steps_per_second": 7.331,
+      "step": 35000
+    },
+    {
+      "epoch": 4.67,
+      "learning_rate": 5.6997776508484205e-06,
+      "loss": 5.892,
+      "step": 40000
+    },
+    {
+      "epoch": 4.67,
+      "eval_loss": 6.426671504974365,
+      "eval_runtime": 847.0538,
+      "eval_samples_per_second": 58.637,
+      "eval_steps_per_second": 7.33,
+      "step": 40000
+    }
+  ],
+  "max_steps": 42835,
+  "num_train_epochs": 5,
+  "total_flos": 6.741181575431455e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7628d68fa5e1ff99fb88c4d7a4d4a6a705ba610323f735887ff2919aecec2661
+size 3119