Model save

README.md

@@ -0,0 +1,71 @@
+---
+tags:
+- generated_from_trainer
+model-index:
+- name: RoBERTa-legal-de-cased_German_legal_SQuAD_17
+  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. -->
+
+# RoBERTa-legal-de-cased_German_legal_SQuAD_17
+
+This model was trained from scratch on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.7026
+
+## 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: 2e-05
+- train_batch_size: 128
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 17
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| No log        | 1.0   | 3    | 5.9725          |
+| No log        | 2.0   | 6    | 5.4679          |
+| No log        | 3.0   | 9    | 4.8936          |
+| No log        | 4.0   | 12   | 4.6404          |
+| No log        | 5.0   | 15   | 3.8267          |
+| No log        | 6.0   | 18   | 3.5252          |
+| No log        | 7.0   | 21   | 3.3880          |
+| No log        | 8.0   | 24   | 3.2478          |
+| No log        | 9.0   | 27   | 3.1329          |
+| No log        | 10.0  | 30   | 3.1052          |
+| No log        | 11.0  | 33   | 2.9603          |
+| No log        | 12.0  | 36   | 2.8132          |
+| No log        | 13.0  | 39   | 2.8544          |
+| No log        | 14.0  | 42   | 2.9655          |
+| No log        | 15.0  | 45   | 2.8565          |
+| No log        | 16.0  | 48   | 2.7496          |
+| No log        | 17.0  | 51   | 2.7026          |
+
+
+### Framework versions
+
+- Transformers 4.36.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.14.7
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/ltstorage/shares/datasets/glllm/data/from_scratch/RoBERTa/RoBERTa-legal-de-cased",
+  "architectures": [
+    "RobertaForQuestionAnswering"
+  ],
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.36.2",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

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
+2024-03-05T20:49:18,codecarbon,7494cee8-9df0-4436-8f3b-c8be89a65ad2,46.5396683216095,0.007144547106689713,0.00015351521324384528,112.5,887.3100000000001,377.88994789123535,0.0014543448686599732,0.013830785513750051,0.004879149363381777,0.0201642797457918,Germany,DEU,free and hanseatic city of hamburg,,,Linux-6.5.0-21-generic-x86_64-with-glibc2.35,3.11.4,2.2.3,128,AMD EPYC 7543 32-Core Processor,4,4 x NVIDIA A40,9.9683,53.5649,1007.7065277099609,machine,N,1.0

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36a766782e28ddc4012cd28163a0916e697b6ae0c626bb7d424487f649323b72
+size 496250232

runs/Mar05_20-48-26_hcdsgpu2/events.out.tfevents.1709671711.hcdsgpu2.321356.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e16e4feaf8aebd54fc93ef116916ee8153e8874f89c8837b17e0e8ca11b8fffc
+size 9576

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a5c1a9b9edced0dcc27c35f34bfc2fcb327da253f3db84ff3cff08dc631ce3
+size 4920