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 +1,78 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: interpro_bert3
+  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_bert3
+
+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: 0.4142
+
+## 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: 200
+- eval_batch_size: 128
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 1600
+- total_eval_batch_size: 1024
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss |
+|:-------------:|:-----:|:------:|:---------------:|
+| 1.2045        | 1.0   | 18425  | 1.1198          |
+| 0.8936        | 2.0   | 36850  | 0.8563          |
+| 0.7736        | 3.0   | 55275  | 0.7475          |
+| 0.6946        | 4.0   | 73700  | 0.6877          |
+| 0.8083        | 5.0   | 92125  | 0.7509          |
+| 0.677         | 6.0   | 110550 | 0.6578          |
+| 0.778         | 7.0   | 128975 | 0.7306          |
+| 0.6017        | 8.0   | 147400 | 0.5994          |
+| 0.5646        | 9.0   | 165825 | 0.5704          |
+| 0.5352        | 10.0  | 184250 | 0.5479          |
+| 0.532         | 11.0  | 202675 | 0.5496          |
+| 0.495         | 12.0  | 221100 | 0.5198          |
+| 0.4714        | 13.0  | 239525 | 0.4971          |
+| 0.4497        | 14.0  | 257950 | 0.4797          |
+| 0.4312        | 15.0  | 276375 | 0.4670          |
+| 0.4131        | 16.0  | 294800 | 0.4494          |
+| 0.4001        | 17.0  | 313225 | 0.4411          |
+| 0.3828        | 18.0  | 331650 | 0.4316          |
+| 0.3665        | 19.0  | 350075 | 0.4201          |
+| 0.3592        | 20.0  | 368500 | 0.4142          |
+
+
+### 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
+2024-04-19T08:03:26,codecarbon,406677fa-329b-4b7a-ad5a-500fdfb72070,142771.33202195168,8.083916199850524,5.6621424521048725e-05,82.5,0.0,282.960711479187,3.2709128527954356,0.0,10.878232658515762,14.149145511311248,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,39.1165,22.2825,754.561897277832,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:f5383d800ebfaed84604f04c3c3e941e36f77f5140c54273d752ee9055a8b133
+size 1322166728

runs/Apr17_16-23-22_gpu212-10/events.out.tfevents.1713360221.gpu212-10.1770419.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:328ba0cac1ee5b1965d04b7dc6a68c985fc6f293c06f3548ac21b2c9d76435ce
+size 168736

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 sha256:83a5545665cd1cfd5f1a357671b3ae1aae543f6fc9065ec1313525c72e09fda8
+size 16216692

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 sha256:3dffd18810dc8445ed4926635d6da9a77e5b78722a8d9c546f40e6835514ef36
+size 4920