End of training

.gitattributes

@@ -33,3 +33,5 @@ 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
+source.spm filter=lfs diff=lfs merge=lfs -text
+target.spm filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,71 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: Helsinki-NLP/opus-mt-ha-en
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+- f1
+- wer
+model-index:
+- name: opus_mt_trial2
+  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. -->
+
+# opus_mt_trial2
+
+This model is a fine-tuned version of [Helsinki-NLP/opus-mt-ha-en](https://huggingface.co/Helsinki-NLP/opus-mt-ha-en) on the None dataset.
+It achieves the following results on the evaluation set:
+- Bleu: 0.3386
+- F1: 0.6154
+- Wer: 0.5062
+- Cer: 0.2815
+- Meteor: 0.6028
+- Loss: 0.3820
+
+## 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: 0.0005
+- train_batch_size: 32
+- eval_batch_size: 32
+- 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
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step  | Bleu   | F1     | Wer    | Cer    | Meteor | Validation Loss |
+|:-------------:|:-----:|:-----:|:------:|:------:|:------:|:------:|:------:|:---------------:|
+| 0.4955        | 1.0   | 12500 | 0.3163 | 0.5995 | 0.5200 | 0.3027 | 0.5806 | 0.4086          |
+| 0.4557        | 2.0   | 25000 | 0.3319 | 0.6108 | 0.5211 | 0.2907 | 0.5967 | 0.3889          |
+| 0.4371        | 3.0   | 37500 | 0.3386 | 0.6154 | 0.5062 | 0.2815 | 0.6028 | 0.3820          |
+
+
+### Framework versions
+
+- PEFT 0.15.2
+- Transformers 4.50.0
+- Pytorch 2.6.0+cu124
+- Datasets 3.4.1
+- Tokenizers 0.21.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Helsinki-NLP/opus-mt-ha-en",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "SEQ_2_SEQ_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27682f79a6d6209e9ee51a9ed679b5c7bf722884c195db075f0463f9c8d2d9e0
+size 2369344

all_results.json

@@ -0,0 +1,17 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 0.3386404997587714,
+    "eval_cer": 0.28147095294898533,
+    "eval_f1": 0.6153534805079603,
+    "eval_loss": 0.3820163309574127,
+    "eval_meteor": 0.6028071424520438,
+    "eval_runtime": 237.8269,
+    "eval_samples_per_second": 21.024,
+    "eval_steps_per_second": 0.66,
+    "eval_wer": 0.5062094115300532,
+    "total_flos": 8.244262109970432e+16,
+    "train_loss": 0.4885604788208008,
+    "train_runtime": 4587.9371,
+    "train_samples_per_second": 261.553,
+    "train_steps_per_second": 8.174
+}

eval_final_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 0.3386404997587714,
+    "eval_cer": 0.28147095294898533,
+    "eval_f1": 0.6153534805079603,
+    "eval_loss": 0.3820163309574127,
+    "eval_meteor": 0.6028071424520438,
+    "eval_runtime": 237.8269,
+    "eval_samples_per_second": 21.024,
+    "eval_steps_per_second": 0.66,
+    "eval_wer": 0.5062094115300532
+}

logs/events.out.tfevents.1748754697.c1279aa5eb8f.2405597.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0db6ca9892529b483dc78ef28ba43960acb53eb2249cc0495490fe4b8e2ca8cd
+size 169901

logs/events.out.tfevents.1748759523.c1279aa5eb8f.2405597.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d5ac2191736679828f3048f1432dffe93f9e7a92b634eac96460eebbc2d2ce9
+size 607

source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ff009c3f913456abb6fd297ec49eacad54fb6027c3994b0d936cbe371fcbba7
+size 782683

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:142ff4b7d573fd3e868afe4d31c94625ae57e7351bc37b0197279797773e6dc9
+size 812660

tokenizer_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "58088": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "ha",
+  "sp_model_kwargs": {},
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "total_flos": 8.244262109970432e+16,
+    "train_loss": 0.4885604788208008,
+    "train_runtime": 4587.9371,
+    "train_samples_per_second": 261.553,
+    "train_steps_per_second": 8.174
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd749e809704f91dc9f92a2d5e75ee594fd1ee1117fec565bc9befe3d9feaa7a
+size 7928