End of training

.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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,73 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: interpro_bert_2
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# interpro_bert_2
+
+This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4333
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 256
+- eval_batch_size: 128
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 2048
+- total_eval_batch_size: 1024
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 15
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss |
+|:-------------:|:-----:|:------:|:---------------:|
+| 1.2702        | 1.0   | 14395  | 1.1699          |
+| 0.9079        | 2.0   | 28790  | 0.8665          |
+| 0.7738        | 3.0   | 43185  | 0.7505          |
+| 0.6959        | 4.0   | 57580  | 0.6820          |
+| 0.6327        | 5.0   | 71975  | 0.6302          |
+| 0.5899        | 6.0   | 86370  | 0.5956          |
+| 0.5462        | 7.0   | 100765 | 0.5654          |
+| 0.5155        | 8.0   | 115160 | 0.5395          |
+| 0.4836        | 9.0   | 129555 | 0.5149          |
+| 0.4633        | 10.0  | 143950 | 0.4984          |
+| 0.441         | 11.0  | 158345 | 0.4774          |
+| 0.4212        | 12.0  | 172740 | 0.4641          |
+| 0.404         | 13.0  | 187135 | 0.4479          |
+| 0.3883        | 14.0  | 201530 | 0.4401          |
+| 0.3781        | 15.0  | 215925 | 0.4333          |
+
+
+### Framework versions
+
+- Transformers 4.39.2
+- Pytorch 2.2.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

config.json

@@ -0,0 +1,26 @@
+{
+  "architectures": [
+    "BertForMaskedLM"
+  ],
+  "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": 512,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 544998
+}

emissions.csv

@@ -0,0 +1,2 @@
+timestamp,project_name,run_id,duration,emissions,emissions_rate,cpu_power,gpu_power,ram_power,cpu_energy,gpu_energy,ram_energy,energy_consumed,country_name,country_iso_code,region,cloud_provider,cloud_region,os,python_version,codecarbon_version,cpu_count,cpu_model,gpu_count,gpu_model,longitude,latitude,ram_total_size,tracking_mode,on_cloud,pue
+2024-04-16T22:21:05,codecarbon,5a2e845a-9a28-4553-baea-6df6b302b6e5,86121.84868121147,4.914109508444094,5.705996310685521e-05,82.5,0.0,282.9607129096985,1.973434579470256,0.0,6.627650436079404,8.601085015549682,Saudi Arabia,SAU,mecca region,,,Linux-5.14.0-162.23.1.el9_1.x86_64-x86_64-with-glibc2.34,3.9.13,2.2.3,24,Intel(R) Xeon(R) Platinum 8260 CPU @ 2.40GHz,8,8 x Tesla V100-SXM2-32GB,39.192,21.4849,754.5619010925293,machine,N,1.0

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf9356a2196574c17ba3a6f45bfb6bb053fe060a624a868f96f4a7201c4f1f8a
+size 1322166728

runs/Apr15_22-07-13_gpu212-06/events.out.tfevents.1713209127.gpu212-06.700827.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a03cacc5053bdb744c6a1d2e225c380cfbd0fd4601b5f2215d8854622eb1fcb7
+size 101564

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "bos_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
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:228af9df9af4161ad4520213548c2d26ac237b2d24af9517dda7e005a1e96fa9
+size 16215843

tokenizer_config.json

@@ -0,0 +1,52 @@
+{
+  "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
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44afdbc5df6b0cb53559d7fea40b29f4c6dc7ef2818525ef43d615cd2b816b18
+size 4920