first

.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 +1,56 @@
----
-license: apache-2.0
----
+---
+library_name: transformers
+license: mit
+base_model: Davlan/afro-xlmr-base
+tags:
+- generated_from_trainer
+model-index:
+- name: afro_xlmr_base_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. -->
+
+# afro_xlmr_base_emakhuwa
+
+This model is a fine-tuned version of [Davlan/afro-xlmr-base](https://huggingface.co/Davlan/afro-xlmr-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.3341
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- 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
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.47.0
+- Pytorch 2.1.0a0+4136153
+- Datasets 3.2.0
+- Tokenizers 0.21.0

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.334074854850769,
+    "eval_runtime": 4.3825,
+    "eval_samples": 153,
+    "eval_samples_per_second": 34.912,
+    "eval_steps_per_second": 4.564,
+    "perplexity": 3.7964820242969743,
+    "total_flos": 1.1730479287894016e+16,
+    "train_loss": 1.7010253453222524,
+    "train_runtime": 4017.837,
+    "train_samples": 14818,
+    "train_samples_per_second": 11.064,
+    "train_steps_per_second": 2.766
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "Davlan/afro-xlmr-base",
+  "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": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "xlm-roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "output_past": true,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.47.0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 250002
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_loss": 1.334074854850769,
+    "eval_runtime": 4.3825,
+    "eval_samples": 153,
+    "eval_samples_per_second": 34.912,
+    "eval_steps_per_second": 4.564,
+    "perplexity": 3.7964820242969743
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:07dc81494c85bfdf65faf0845aa33e78f2eaae67b6566f4534581ac86424d86b
+size 1113205088

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 +1,55 @@
+{
+  "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>",
+  "extra_special_tokens": {},
+  "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": 1.1730479287894016e+16,
+    "train_loss": 1.7010253453222524,
+    "train_runtime": 4017.837,
+    "train_samples": 14818,
+    "train_samples_per_second": 11.064,
+    "train_steps_per_second": 2.766
+}

trainer_state.json

@@ -0,0 +1,196 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 11115,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.1349527665317139,
+      "grad_norm": 7.277841567993164,
+      "learning_rate": 4.775078722447144e-05,
+      "loss": 3.0654,
+      "step": 500
+    },
+    {
+      "epoch": 0.2699055330634278,
+      "grad_norm": 7.536296844482422,
+      "learning_rate": 4.550157444894287e-05,
+      "loss": 2.4088,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4048582995951417,
+      "grad_norm": 6.857296466827393,
+      "learning_rate": 4.3252361673414306e-05,
+      "loss": 2.1502,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5398110661268556,
+      "grad_norm": 20.20909309387207,
+      "learning_rate": 4.100314889788574e-05,
+      "loss": 1.9977,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6747638326585695,
+      "grad_norm": 6.654603004455566,
+      "learning_rate": 3.8753936122357176e-05,
+      "loss": 1.8983,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8097165991902834,
+      "grad_norm": 7.12253999710083,
+      "learning_rate": 3.650472334682861e-05,
+      "loss": 1.8103,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9446693657219973,
+      "grad_norm": 6.6242170333862305,
+      "learning_rate": 3.4255510571300045e-05,
+      "loss": 1.7543,
+      "step": 3500
+    },
+    {
+      "epoch": 1.0796221322537112,
+      "grad_norm": 5.963022232055664,
+      "learning_rate": 3.2006297795771486e-05,
+      "loss": 1.6822,
+      "step": 4000
+    },
+    {
+      "epoch": 1.214574898785425,
+      "grad_norm": 6.769837856292725,
+      "learning_rate": 2.9757085020242914e-05,
+      "loss": 1.6501,
+      "step": 4500
+    },
+    {
+      "epoch": 1.349527665317139,
+      "grad_norm": 6.467240333557129,
+      "learning_rate": 2.750787224471435e-05,
+      "loss": 1.612,
+      "step": 5000
+    },
+    {
+      "epoch": 1.484480431848853,
+      "grad_norm": 6.431339740753174,
+      "learning_rate": 2.5258659469185787e-05,
+      "loss": 1.5606,
+      "step": 5500
+    },
+    {
+      "epoch": 1.6194331983805668,
+      "grad_norm": 7.2527289390563965,
+      "learning_rate": 2.300944669365722e-05,
+      "loss": 1.5413,
+      "step": 6000
+    },
+    {
+      "epoch": 1.7543859649122808,
+      "grad_norm": 6.609572887420654,
+      "learning_rate": 2.0760233918128656e-05,
+      "loss": 1.5367,
+      "step": 6500
+    },
+    {
+      "epoch": 1.8893387314439947,
+      "grad_norm": 6.267154216766357,
+      "learning_rate": 1.851102114260009e-05,
+      "loss": 1.5087,
+      "step": 7000
+    },
+    {
+      "epoch": 2.0242914979757085,
+      "grad_norm": 6.8475117683410645,
+      "learning_rate": 1.6261808367071525e-05,
+      "loss": 1.4727,
+      "step": 7500
+    },
+    {
+      "epoch": 2.1592442645074224,
+      "grad_norm": 6.945182800292969,
+      "learning_rate": 1.401259559154296e-05,
+      "loss": 1.4564,
+      "step": 8000
+    },
+    {
+      "epoch": 2.294197031039136,
+      "grad_norm": 6.858353137969971,
+      "learning_rate": 1.1763382816014395e-05,
+      "loss": 1.4325,
+      "step": 8500
+    },
+    {
+      "epoch": 2.42914979757085,
+      "grad_norm": 6.653971195220947,
+      "learning_rate": 9.51417004048583e-06,
+      "loss": 1.4041,
+      "step": 9000
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 5.984017848968506,
+      "learning_rate": 7.264957264957266e-06,
+      "loss": 1.4085,
+      "step": 9500
+    },
+    {
+      "epoch": 2.699055330634278,
+      "grad_norm": 6.64699649810791,
+      "learning_rate": 5.0157444894287e-06,
+      "loss": 1.365,
+      "step": 10000
+    },
+    {
+      "epoch": 2.834008097165992,
+      "grad_norm": 6.052412509918213,
+      "learning_rate": 2.766531713900135e-06,
+      "loss": 1.3799,
+      "step": 10500
+    },
+    {
+      "epoch": 2.968960863697706,
+      "grad_norm": 6.4499711990356445,
+      "learning_rate": 5.1731893837157e-07,
+      "loss": 1.3994,
+      "step": 11000
+    },
+    {
+      "epoch": 3.0,
+      "step": 11115,
+      "total_flos": 1.1730479287894016e+16,
+      "train_loss": 1.7010253453222524,
+      "train_runtime": 4017.837,
+      "train_samples_per_second": 11.064,
+      "train_steps_per_second": 2.766
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11115,
+  "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": 1.1730479287894016e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eff96883c5e6a5c14c2f28312d1ff5255203c4b1777d1d571a18a799c3228ce7
+size 5056