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: BERT_word2vec
+  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. -->
+
+# BERT_word2vec
+
+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: 2.2223
+
+## 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: 20
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss |
+|:-------------:|:-----:|:------:|:---------------:|
+| 3.4036        | 1.0   | 43283  | 3.2746          |
+| 3.0571        | 2.0   | 86566  | 2.9331          |
+| 2.8967        | 3.0   | 129849 | 2.7814          |
+| 2.7919        | 4.0   | 173132 | 2.6885          |
+| 2.7072        | 5.0   | 216415 | 2.6176          |
+| 2.6512        | 6.0   | 259698 | 2.5633          |
+| 2.6091        | 7.0   | 302981 | 2.5193          |
+| 2.5596        | 8.0   | 346264 | 2.4826          |
+| 2.5291        | 9.0   | 389547 | 2.4491          |
+| 2.4972        | 10.0  | 432830 | 2.4219          |
+| 2.4697        | 11.0  | 476113 | 2.3943          |
+| 2.4311        | 12.0  | 519396 | 2.3714          |
+| 2.4199        | 13.0  | 562679 | 2.3438          |
+| 2.3847        | 14.0  | 605962 | 2.3223          |
+| 2.3508        | 15.0  | 649245 | 2.3042          |
+| 2.3333        | 16.0  | 692528 | 2.2818          |
+| 2.3113        | 17.0  | 735811 | 2.2633          |
+| 2.281         | 18.0  | 779094 | 2.2447          |
+| 2.2749        | 19.0  | 822377 | 2.2316          |
+| 2.2541        | 20.0  | 865660 | 2.2223          |
+
+
+### Framework versions
+
+- Transformers 4.39.3
+- 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": "4.39.3",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 563589
+}

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
+2024-06-07T07:01:02,codecarbon,0e707b53-472d-4cd4-b78f-5c5e6d73a4fb,416750.4111754894,116.75776856311268,0.0002801623356142225,82.5,561.799,282.9607129096985,9.550250337568878,163.45640772660428,31.35254311186798,204.3592011760377,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,39.1165,22.2825,754.5619010925293,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": "4.39.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ac309ff6f5569b658df47ac2061d6bf4e8f9de1dd6c16defa75b1a2440d6c08
+size 1360315460

runs/Jun02_11-14-34_gpu211-06/events.out.tfevents.1717316097.gpu211-06.2407578.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8bc3143ef612f55c8c78574c372310818b549bb2821afac8562a7cad8fb2099c
+size 382443

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 sha256:77743a0923b26a8b87ed0d8d8f7834e33c817308658697f35a93d8c2668af7d0
+size 19451402

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:d94014957bcc286ae71118b773df077939bc95ab148badfc522474f3039a3dff
+size 4984