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

@@ -1,3 +1,48 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+base_model: xlmr_large
+tags:
+- generated_from_trainer
+model-index:
+- name: xlmr_large_emakhuwa
+  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. -->
+
+# xlmr_large_emakhuwa
+
+This model is a fine-tuned version of [xlmr_large](https://huggingface.co/xlmr_large) on an unknown dataset.
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Framework versions
+
+- Transformers 4.46.3
+- Pytorch 2.4.1+cu121
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.202345371246338,
+    "eval_runtime": 73.2928,
+    "eval_samples": 177,
+    "eval_samples_per_second": 2.415,
+    "eval_steps_per_second": 0.164,
+    "perplexity": 3.3279129682384063,
+    "total_flos": 4.846865511470285e+16,
+    "train_loss": 1.5912532506997346,
+    "train_runtime": 107034.0122,
+    "train_samples": 17322,
+    "train_samples_per_second": 0.486,
+    "train_steps_per_second": 0.061
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "xlmr_large",
+  "architectures": [
+    "XLMRobertaForMaskedLM"
+  ],
+  "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": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.202345371246338,
+    "eval_runtime": 73.2928,
+    "eval_samples": 177,
+    "eval_samples_per_second": 2.415,
+    "eval_steps_per_second": 0.164,
+    "perplexity": 3.3279129682384063
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af4ffc1ef8180e998383f612011146db78a27deaefc2956f3ec6b3a7c9008339
+size 2240618752

sentencepiece.bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc8146abe2a0488e9e2a0c56de7952f7c11ab059eca145a0a727afce0db2865
+size 5069051

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_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": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "</s>",
+    "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 sha256:3a56def25aa40facc030ea8b0b87f3688e4b3c39eb8b45d5702b3a1300fe2a20
+size 17082734

tokenizer_config.json

@@ -0,0 +1,54 @@
+{
+  "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
+    },
+    "250001": {
+      "content": "<mask>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "tokenizer_class": "XLMRobertaTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "total_flos": 4.846865511470285e+16,
+    "train_loss": 1.5912532506997346,
+    "train_runtime": 107034.0122,
+    "train_samples": 17322,
+    "train_samples_per_second": 0.486,
+    "train_steps_per_second": 0.061
+}

trainer_state.json

@@ -0,0 +1,126 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 6498,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.23084025854108955,
+      "grad_norm": 10.19813346862793,
+      "learning_rate": 4.615266235764851e-05,
+      "loss": 2.8709,
+      "step": 500
+    },
+    {
+      "epoch": 0.4616805170821791,
+      "grad_norm": 8.437438011169434,
+      "learning_rate": 4.230532471529702e-05,
+      "loss": 2.0854,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6925207756232687,
+      "grad_norm": 8.001243591308594,
+      "learning_rate": 3.845798707294552e-05,
+      "loss": 1.846,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9233610341643582,
+      "grad_norm": 7.907439231872559,
+      "learning_rate": 3.4610649430594035e-05,
+      "loss": 1.6927,
+      "step": 2000
+    },
+    {
+      "epoch": 1.154201292705448,
+      "grad_norm": 6.441333293914795,
+      "learning_rate": 3.076331178824254e-05,
+      "loss": 1.5576,
+      "step": 2500
+    },
+    {
+      "epoch": 1.3850415512465375,
+      "grad_norm": 7.415187358856201,
+      "learning_rate": 2.6915974145891044e-05,
+      "loss": 1.4918,
+      "step": 3000
+    },
+    {
+      "epoch": 1.615881809787627,
+      "grad_norm": 7.552712440490723,
+      "learning_rate": 2.3068636503539552e-05,
+      "loss": 1.4271,
+      "step": 3500
+    },
+    {
+      "epoch": 1.8467220683287167,
+      "grad_norm": 7.328059196472168,
+      "learning_rate": 1.922129886118806e-05,
+      "loss": 1.3894,
+      "step": 4000
+    },
+    {
+      "epoch": 2.0775623268698062,
+      "grad_norm": 7.679264068603516,
+      "learning_rate": 1.5373961218836565e-05,
+      "loss": 1.339,
+      "step": 4500
+    },
+    {
+      "epoch": 2.308402585410896,
+      "grad_norm": 7.513192653656006,
+      "learning_rate": 1.1526623576485073e-05,
+      "loss": 1.2782,
+      "step": 5000
+    },
+    {
+      "epoch": 2.5392428439519854,
+      "grad_norm": 7.99367094039917,
+      "learning_rate": 7.67928593413358e-06,
+      "loss": 1.2609,
+      "step": 5500
+    },
+    {
+      "epoch": 2.770083102493075,
+      "grad_norm": 7.764072418212891,
+      "learning_rate": 3.831948291782087e-06,
+      "loss": 1.2275,
+      "step": 6000
+    },
+    {
+      "epoch": 3.0,
+      "step": 6498,
+      "total_flos": 4.846865511470285e+16,
+      "train_loss": 1.5912532506997346,
+      "train_runtime": 107034.0122,
+      "train_samples_per_second": 0.486,
+      "train_steps_per_second": 0.061
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 6498,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.846865511470285e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0826a19ae0935336a806631371f58d619a8b62007f24c462aa0e9c49b3646b4
+size 5304