Upload 14 files

.gitattributes

@@ -32,3 +32,4 @@ 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
+checkpoint-6000/source.spm filter=lfs diff=lfs merge=lfs -text

checkpoint-6000/config.json

@@ -0,0 +1,61 @@
+{
+  "_name_or_path": "Helsinki-NLP/opus-mt-uk-en",
+  "_num_labels": 3,
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "bad_words_ids": [
+    [
+      61586
+    ]
+  ],
+  "bos_token_id": 0,
+  "classif_dropout": 0.0,
+  "classifier_dropout": 0.0,
+  "d_model": 512,
+  "decoder_attention_heads": 8,
+  "decoder_ffn_dim": 2048,
+  "decoder_layerdrop": 0.0,
+  "decoder_layers": 6,
+  "decoder_start_token_id": 61586,
+  "decoder_vocab_size": 61587,
+  "dropout": 0.1,
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2"
+  },
+  "init_std": 0.02,
+  "is_encoder_decoder": true,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_2": 2
+  },
+  "max_length": 512,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": 6,
+  "num_hidden_layers": 6,
+  "pad_token_id": 61586,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.27.2",
+  "use_cache": true,
+  "vocab_size": 61587
+}

checkpoint-6000/generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bad_words_ids": [
+    [
+      61586
+    ]
+  ],
+  "bos_token_id": 0,
+  "decoder_start_token_id": 61586,
+  "eos_token_id": 0,
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 61586,
+  "transformers_version": "4.27.2"
+}

checkpoint-6000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a62a8244b4a5a34247972e3a020bd779e4ab400da14954b0ab251d33117d95e
+size 303017029

checkpoint-6000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b92cf4897eefbf37b39c509683dc2d707afc2adfea1419a11fcf94abc6329010
+size 14511

checkpoint-6000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a66a5602f25583c0eab6bdb12a320a7a7569ffde6cf171f2307d6725cb3afcb
+size 627

checkpoint-6000/source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7abd810b2df512e6fe177f8732f6a0b3107614c84cc52aba20d805b4cb0d7b6b
+size 1007605

checkpoint-6000/special_tokens_map.json

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

checkpoint-6000/tokenizer_config.json

@@ -0,0 +1,12 @@
+{
+  "eos_token": "</s>",
+  "model_max_length": 512,
+  "pad_token": "<pad>",
+  "separate_vocabs": false,
+  "source_lang": "uk",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": null,
+  "target_lang": "en",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

checkpoint-6000/trainer_state.json

@@ -0,0 +1,128 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.893964110929853,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.8368678629690052e-05,
+      "loss": 1.8033,
+      "step": 500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 1.67373572593801e-05,
+      "loss": 1.3748,
+      "step": 1000
+    },
+    {
+      "epoch": 1.0,
+      "eval_bleu": 56.2549,
+      "eval_gen_len": 46.4902,
+      "eval_loss": 1.0630319118499756,
+      "eval_runtime": 198.2655,
+      "eval_samples_per_second": 4.363,
+      "eval_steps_per_second": 0.55,
+      "step": 1226
+    },
+    {
+      "epoch": 1.22,
+      "learning_rate": 1.5106035889070147e-05,
+      "loss": 1.2066,
+      "step": 1500
+    },
+    {
+      "epoch": 1.63,
+      "learning_rate": 1.3474714518760197e-05,
+      "loss": 1.0606,
+      "step": 2000
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 59.9691,
+      "eval_gen_len": 41.7179,
+      "eval_loss": 0.8989508748054504,
+      "eval_runtime": 167.0597,
+      "eval_samples_per_second": 5.178,
+      "eval_steps_per_second": 0.652,
+      "step": 2452
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.1843393148450246e-05,
+      "loss": 1.0004,
+      "step": 2500
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 1.0212071778140294e-05,
+      "loss": 0.9003,
+      "step": 3000
+    },
+    {
+      "epoch": 2.85,
+      "learning_rate": 8.580750407830342e-06,
+      "loss": 0.8476,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu": 62.2787,
+      "eval_gen_len": 43.8925,
+      "eval_loss": 0.8091979622840881,
+      "eval_runtime": 172.38,
+      "eval_samples_per_second": 5.018,
+      "eval_steps_per_second": 0.632,
+      "step": 3678
+    },
+    {
+      "epoch": 3.26,
+      "learning_rate": 6.949429037520392e-06,
+      "loss": 0.8063,
+      "step": 4000
+    },
+    {
+      "epoch": 3.67,
+      "learning_rate": 5.31810766721044e-06,
+      "loss": 0.7727,
+      "step": 4500
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu": 63.4386,
+      "eval_gen_len": 43.7595,
+      "eval_loss": 0.7679935693740845,
+      "eval_runtime": 172.1652,
+      "eval_samples_per_second": 5.024,
+      "eval_steps_per_second": 0.633,
+      "step": 4904
+    },
+    {
+      "epoch": 4.08,
+      "learning_rate": 3.68678629690049e-06,
+      "loss": 0.7669,
+      "step": 5000
+    },
+    {
+      "epoch": 4.49,
+      "learning_rate": 2.0554649265905383e-06,
+      "loss": 0.7119,
+      "step": 5500
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 4.2414355628058736e-07,
+      "loss": 0.7228,
+      "step": 6000
+    }
+  ],
+  "max_steps": 6130,
+  "num_train_epochs": 5,
+  "total_flos": 922220642893824.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-6000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea08773408e7d2dca501393943d5c496789da7036703b0c33341f984d75c3444
+size 3707

runs/Mar21_01-33-37_36f8bb4e9310/1679362458.9652426/events.out.tfevents.1679362458.36f8bb4e9310.1360.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dca39733253829b5050fa79033e038a355edb6cb157cbcfe89f4e135da4f895
+size 6049

runs/Mar21_01-33-37_36f8bb4e9310/events.out.tfevents.1679362458.36f8bb4e9310.1360.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c76b243b89e6f86b6bd3d808b13ab5a641deafe2cb6dfc363154b9519f1cbd6c
+size 8899