Training in progress, step 1000, checkpoint

.gitattributes

@@ -35,3 +35,5 @@ saved_model/**/* 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
+last-checkpoint/source.spm filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/target.spm filter=lfs diff=lfs merge=lfs -text

last-checkpoint/config.json

@@ -0,0 +1,54 @@
+{
+  "activation_dropout": 0.0,
+  "activation_function": "swish",
+  "add_bias_logits": false,
+  "add_final_layer_norm": false,
+  "architectures": [
+    "MarianMTModel"
+  ],
+  "attention_dropout": 0.0,
+  "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": 64109,
+  "decoder_vocab_size": 64110,
+  "dropout": 0.1,
+  "dtype": "float32",
+  "encoder_attention_heads": 8,
+  "encoder_ffn_dim": 2048,
+  "encoder_layerdrop": 0.0,
+  "encoder_layers": 6,
+  "eos_token_id": 0,
+  "extra_pos_embeddings": 64110,
+  "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": null,
+  "max_position_embeddings": 512,
+  "model_type": "marian",
+  "normalize_before": false,
+  "normalize_embedding": false,
+  "num_beams": null,
+  "num_hidden_layers": 6,
+  "pad_token_id": 64109,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.57.3",
+  "use_cache": true,
+  "vocab_size": 64110
+}

last-checkpoint/generation_config.json

@@ -0,0 +1,17 @@
+{
+  "bad_words_ids": [
+    [
+      64109
+    ]
+  ],
+  "decoder_start_token_id": 64109,
+  "eos_token_id": [
+    0
+  ],
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 4,
+  "pad_token_id": 64109,
+  "renormalize_logits": true,
+  "transformers_version": "4.57.3"
+}

last-checkpoint/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9095f8f4b09f5ac990f0f5a29fada4677f683368b4241bfc2f445ec24cd32f17
+size 308136760

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63bbc30f30dd76a085db013210508d0a520062d24abcb883c042786584262935
+size 615918027

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9bf27ae5fc465cacc575c82fcf640ea163c1ef9c099c54ea1e77e18d43cd99b
+size 14645

last-checkpoint/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f61b50ac58556fb5ddabe26ca60d44c13d0ea7faf3bf7f86dbfa4e99343e6a
+size 1383

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f0a9fbc27bd8041e9c0979b03c45a1bff18010be17c72323614773a30a2199c
+size 1465

last-checkpoint/source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9129bf81ef9d5fcc1797ea3061e789dc5f9e5602786b0490238d207d4219e0f5
+size 790473

last-checkpoint/special_tokens_map.json

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

last-checkpoint/target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a0a52318dac3247455ec889eb3bd8da9bdf234974be8b9b0f99ad5378f474c9
+size 706659

last-checkpoint/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
+    },
+    "64109": {
+      "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": "eng",
+  "sp_model_kwargs": {},
+  "target_lang": "mul",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,112 @@
+{
+  "best_global_step": 1000,
+  "best_metric": 0.6297275424003601,
+  "best_model_checkpoint": "./en-wal-checkpoints/checkpoint-1000",
+  "epoch": 0.13962580284836637,
+  "eval_steps": 1000,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.013962580284836637,
+      "grad_norm": 1.8059194087982178,
+      "learning_rate": 1.990784697012008e-05,
+      "loss": 2.3977,
+      "step": 100
+    },
+    {
+      "epoch": 0.027925160569673275,
+      "grad_norm": 1.7286276817321777,
+      "learning_rate": 1.98147631015545e-05,
+      "loss": 1.1677,
+      "step": 200
+    },
+    {
+      "epoch": 0.041887740854509914,
+      "grad_norm": 1.5416228771209717,
+      "learning_rate": 1.9721679232988925e-05,
+      "loss": 1.0428,
+      "step": 300
+    },
+    {
+      "epoch": 0.05585032113934655,
+      "grad_norm": 2.0110714435577393,
+      "learning_rate": 1.9628595364423345e-05,
+      "loss": 0.9278,
+      "step": 400
+    },
+    {
+      "epoch": 0.06981290142418319,
+      "grad_norm": 1.5851672887802124,
+      "learning_rate": 1.953551149585777e-05,
+      "loss": 0.8565,
+      "step": 500
+    },
+    {
+      "epoch": 0.08377548170901983,
+      "grad_norm": 1.6291816234588623,
+      "learning_rate": 1.944242762729219e-05,
+      "loss": 0.8211,
+      "step": 600
+    },
+    {
+      "epoch": 0.09773806199385647,
+      "grad_norm": 1.455430269241333,
+      "learning_rate": 1.9349343758726614e-05,
+      "loss": 0.7689,
+      "step": 700
+    },
+    {
+      "epoch": 0.1117006422786931,
+      "grad_norm": 1.8033580780029297,
+      "learning_rate": 1.9256259890161038e-05,
+      "loss": 0.7457,
+      "step": 800
+    },
+    {
+      "epoch": 0.12566322256352974,
+      "grad_norm": 1.815686821937561,
+      "learning_rate": 1.916317602159546e-05,
+      "loss": 0.7194,
+      "step": 900
+    },
+    {
+      "epoch": 0.13962580284836637,
+      "grad_norm": 1.4914112091064453,
+      "learning_rate": 1.9070092153029882e-05,
+      "loss": 0.6944,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13962580284836637,
+      "eval_loss": 0.6297275424003601,
+      "eval_runtime": 16.8076,
+      "eval_samples_per_second": 358.826,
+      "eval_steps_per_second": 22.43,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 21486,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 542373838848000.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e10d4e3e16a17bf82487d3f04f2bd2ddb944691afefdf7975162f453899e25a3
+size 6033