Checkpoint 2000 - Epoch 0.14

.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
+checkpoints/checkpoint-2000/source.spm filter=lfs diff=lfs merge=lfs -text
+checkpoints/checkpoint-2000/target.spm filter=lfs diff=lfs merge=lfs -text

checkpoints/checkpoint-2000/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": 64171,
+  "decoder_vocab_size": 64172,
+  "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": 64172,
+  "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": 64171,
+  "scale_embedding": true,
+  "share_encoder_decoder_embeddings": true,
+  "static_position_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": true,
+  "vocab_size": 64172
+}

checkpoints/checkpoint-2000/generation_config.json

@@ -0,0 +1,17 @@
+{
+  "bad_words_ids": [
+    [
+      64171
+    ]
+  ],
+  "decoder_start_token_id": 64171,
+  "eos_token_id": [
+    0
+  ],
+  "forced_eos_token_id": 0,
+  "max_length": 512,
+  "num_beams": 6,
+  "pad_token_id": 64171,
+  "renormalize_logits": true,
+  "transformers_version": "4.57.1"
+}

checkpoints/checkpoint-2000/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e423d60bbf8b35a09d8c107e6d5eaeb8db03328d3d91b3403882adaefe9cfbc
+size 308263984

checkpoints/checkpoint-2000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e235555afb9566e0f2f6d9999895252240d2851e4eca887dc78d778d086b2315
+size 616171979

checkpoints/checkpoint-2000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:deb31db6c694109023e3f4bf3a46003fa1957d38b27987be7dfbc3d585c576b3
+size 14645

checkpoints/checkpoint-2000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
+size 1383

checkpoints/checkpoint-2000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:743a762ad2f6d3a96bffd5f7600fb2dd5ad57fadd88dcfad20d27bd4e6f7cc1b
+size 1465

checkpoints/checkpoint-2000/source.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4a99ea3602b29fbf901ade8b93a45efa3d7c64eab8fc5fa812383efa327a87d
+size 706917

checkpoints/checkpoint-2000/special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoints/checkpoint-2000/target.spm

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6dce5fa58fcd7dde9e81e279b8c075bf42ee558278f73d6fb48e342029d7f19
+size 791194

checkpoints/checkpoint-2000/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
+    },
+    "64171": {
+      "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": "mul",
+  "sp_model_kwargs": {},
+  "target_lang": "eng",
+  "tokenizer_class": "MarianTokenizer",
+  "unk_token": "<unk>"
+}

checkpoints/checkpoint-2000/trainer_state.json

@@ -0,0 +1,334 @@
+{
+  "best_global_step": 2000,
+  "best_metric": 0.11687587046602367,
+  "best_model_checkpoint": "models/finetuned-sw-en-phase2/checkpoint-2000",
+  "epoch": 0.1433383501755895,
+  "eval_steps": 2000,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003583458754389737,
+      "grad_norm": 2.8826961517333984,
+      "learning_rate": 1.1705685618729097e-07,
+      "loss": 3.6787,
+      "step": 50
+    },
+    {
+      "epoch": 0.007166917508779474,
+      "grad_norm": 3.028228521347046,
+      "learning_rate": 2.3650262780697565e-07,
+      "loss": 3.6845,
+      "step": 100
+    },
+    {
+      "epoch": 0.010750376263169211,
+      "grad_norm": 3.1519999504089355,
+      "learning_rate": 3.5594839942666037e-07,
+      "loss": 3.6839,
+      "step": 150
+    },
+    {
+      "epoch": 0.014333835017558949,
+      "grad_norm": 2.8430724143981934,
+      "learning_rate": 4.75394171046345e-07,
+      "loss": 3.6742,
+      "step": 200
+    },
+    {
+      "epoch": 0.017917293771948686,
+      "grad_norm": 2.86275577545166,
+      "learning_rate": 5.948399426660297e-07,
+      "loss": 3.6864,
+      "step": 250
+    },
+    {
+      "epoch": 0.021500752526338422,
+      "grad_norm": 2.787710189819336,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 3.671,
+      "step": 300
+    },
+    {
+      "epoch": 0.025084211280728158,
+      "grad_norm": 2.906496524810791,
+      "learning_rate": 8.337314859053989e-07,
+      "loss": 3.6812,
+      "step": 350
+    },
+    {
+      "epoch": 0.028667670035117897,
+      "grad_norm": 2.733621120452881,
+      "learning_rate": 9.531772575250838e-07,
+      "loss": 3.6657,
+      "step": 400
+    },
+    {
+      "epoch": 0.03225112878950763,
+      "grad_norm": 2.9586291313171387,
+      "learning_rate": 1.0726230291447684e-06,
+      "loss": 3.6776,
+      "step": 450
+    },
+    {
+      "epoch": 0.03583458754389737,
+      "grad_norm": 2.697490930557251,
+      "learning_rate": 1.192068800764453e-06,
+      "loss": 3.6817,
+      "step": 500
+    },
+    {
+      "epoch": 0.03941804629828711,
+      "grad_norm": 2.8789138793945312,
+      "learning_rate": 1.3115145723841377e-06,
+      "loss": 3.6645,
+      "step": 550
+    },
+    {
+      "epoch": 0.043001505052676844,
+      "grad_norm": 2.738499879837036,
+      "learning_rate": 1.4309603440038225e-06,
+      "loss": 3.6701,
+      "step": 600
+    },
+    {
+      "epoch": 0.04658496380706658,
+      "grad_norm": 2.976515293121338,
+      "learning_rate": 1.550406115623507e-06,
+      "loss": 3.6557,
+      "step": 650
+    },
+    {
+      "epoch": 0.050168422561456316,
+      "grad_norm": 2.8300790786743164,
+      "learning_rate": 1.6698518872431918e-06,
+      "loss": 3.6624,
+      "step": 700
+    },
+    {
+      "epoch": 0.05375188131584605,
+      "grad_norm": 2.8557324409484863,
+      "learning_rate": 1.7892976588628764e-06,
+      "loss": 3.6638,
+      "step": 750
+    },
+    {
+      "epoch": 0.057335340070235795,
+      "grad_norm": 2.915972948074341,
+      "learning_rate": 1.9087434304825613e-06,
+      "loss": 3.6746,
+      "step": 800
+    },
+    {
+      "epoch": 0.06091879882462553,
+      "grad_norm": 2.833534002304077,
+      "learning_rate": 2.0281892021022457e-06,
+      "loss": 3.6571,
+      "step": 850
+    },
+    {
+      "epoch": 0.06450225757901526,
+      "grad_norm": 2.786886215209961,
+      "learning_rate": 2.1476349737219305e-06,
+      "loss": 3.6641,
+      "step": 900
+    },
+    {
+      "epoch": 0.068085716333405,
+      "grad_norm": 2.888093948364258,
+      "learning_rate": 2.2670807453416154e-06,
+      "loss": 3.6626,
+      "step": 950
+    },
+    {
+      "epoch": 0.07166917508779475,
+      "grad_norm": 2.935640335083008,
+      "learning_rate": 2.3865265169613e-06,
+      "loss": 3.6669,
+      "step": 1000
+    },
+    {
+      "epoch": 0.07525263384218447,
+      "grad_norm": 2.9223127365112305,
+      "learning_rate": 2.5059722885809846e-06,
+      "loss": 3.6766,
+      "step": 1050
+    },
+    {
+      "epoch": 0.07883609259657422,
+      "grad_norm": 2.855170488357544,
+      "learning_rate": 2.625418060200669e-06,
+      "loss": 3.6616,
+      "step": 1100
+    },
+    {
+      "epoch": 0.08241955135096395,
+      "grad_norm": 2.822401285171509,
+      "learning_rate": 2.7448638318203535e-06,
+      "loss": 3.6633,
+      "step": 1150
+    },
+    {
+      "epoch": 0.08600301010535369,
+      "grad_norm": 2.8145692348480225,
+      "learning_rate": 2.8643096034400387e-06,
+      "loss": 3.6526,
+      "step": 1200
+    },
+    {
+      "epoch": 0.08958646885974342,
+      "grad_norm": 2.7493700981140137,
+      "learning_rate": 2.983755375059723e-06,
+      "loss": 3.6578,
+      "step": 1250
+    },
+    {
+      "epoch": 0.09316992761413316,
+      "grad_norm": 2.7674636840820312,
+      "learning_rate": 3.1032011466794076e-06,
+      "loss": 3.657,
+      "step": 1300
+    },
+    {
+      "epoch": 0.0967533863685229,
+      "grad_norm": 2.798501491546631,
+      "learning_rate": 3.222646918299093e-06,
+      "loss": 3.6579,
+      "step": 1350
+    },
+    {
+      "epoch": 0.10033684512291263,
+      "grad_norm": 3.045165777206421,
+      "learning_rate": 3.3420926899187773e-06,
+      "loss": 3.6667,
+      "step": 1400
+    },
+    {
+      "epoch": 0.10392030387730238,
+      "grad_norm": 2.730278730392456,
+      "learning_rate": 3.4615384615384617e-06,
+      "loss": 3.6693,
+      "step": 1450
+    },
+    {
+      "epoch": 0.1075037626316921,
+      "grad_norm": 2.8988585472106934,
+      "learning_rate": 3.580984233158146e-06,
+      "loss": 3.6602,
+      "step": 1500
+    },
+    {
+      "epoch": 0.11108722138608185,
+      "grad_norm": 2.9216086864471436,
+      "learning_rate": 3.7004300047778314e-06,
+      "loss": 3.6628,
+      "step": 1550
+    },
+    {
+      "epoch": 0.11467068014047159,
+      "grad_norm": 2.7945556640625,
+      "learning_rate": 3.819875776397516e-06,
+      "loss": 3.6625,
+      "step": 1600
+    },
+    {
+      "epoch": 0.11825413889486132,
+      "grad_norm": 2.895811080932617,
+      "learning_rate": 3.9393215480172e-06,
+      "loss": 3.6457,
+      "step": 1650
+    },
+    {
+      "epoch": 0.12183759764925106,
+      "grad_norm": 2.634783983230591,
+      "learning_rate": 4.0587673196368855e-06,
+      "loss": 3.6572,
+      "step": 1700
+    },
+    {
+      "epoch": 0.1254210564036408,
+      "grad_norm": 2.907348871231079,
+      "learning_rate": 4.17821309125657e-06,
+      "loss": 3.6515,
+      "step": 1750
+    },
+    {
+      "epoch": 0.12900451515803052,
+      "grad_norm": 2.9280805587768555,
+      "learning_rate": 4.297658862876254e-06,
+      "loss": 3.6465,
+      "step": 1800
+    },
+    {
+      "epoch": 0.13258797391242028,
+      "grad_norm": 3.136627197265625,
+      "learning_rate": 4.417104634495939e-06,
+      "loss": 3.6564,
+      "step": 1850
+    },
+    {
+      "epoch": 0.13617143266681,
+      "grad_norm": 2.8626930713653564,
+      "learning_rate": 4.536550406115624e-06,
+      "loss": 3.6438,
+      "step": 1900
+    },
+    {
+      "epoch": 0.13975489142119973,
+      "grad_norm": 2.99165678024292,
+      "learning_rate": 4.6559961777353084e-06,
+      "loss": 3.6442,
+      "step": 1950
+    },
+    {
+      "epoch": 0.1433383501755895,
+      "grad_norm": 2.8795509338378906,
+      "learning_rate": 4.775441949354993e-06,
+      "loss": 3.6556,
+      "step": 2000
+    },
+    {
+      "epoch": 0.1433383501755895,
+      "eval_bleu": 0.11687587046602367,
+      "eval_chrf": 31.48836065140496,
+      "eval_loss": 3.6125245094299316,
+      "eval_model_preparation_time": 0.0025,
+      "eval_runtime": 48.0402,
+      "eval_samples_per_second": 41.632,
+      "eval_steps_per_second": 0.666,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 83718,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 2000,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.001
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8219946714660864.0,
+  "train_batch_size": 256,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-2000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2d57bc67b52fab2e986e6601c38187c6c1f5438f07426ccb4a39e1f5364676b
+size 5969

checkpoints/checkpoint-2000/training_metrics_snapshot.json

@@ -0,0 +1,300 @@
+{
+  "checkpoint": 2000,
+  "epoch": 0.1433383501755895,
+  "timestamp": "2025-11-23T04:25:55.565519",
+  "training_history": [
+    {
+      "loss": 3.6787,
+      "grad_norm": 2.8826961517333984,
+      "learning_rate": 1.1705685618729097e-07,
+      "epoch": 0.003583458754389737,
+      "step": 50
+    },
+    {
+      "loss": 3.6845,
+      "grad_norm": 3.028228521347046,
+      "learning_rate": 2.3650262780697565e-07,
+      "epoch": 0.007166917508779474,
+      "step": 100
+    },
+    {
+      "loss": 3.6839,
+      "grad_norm": 3.1519999504089355,
+      "learning_rate": 3.5594839942666037e-07,
+      "epoch": 0.010750376263169211,
+      "step": 150
+    },
+    {
+      "loss": 3.6742,
+      "grad_norm": 2.8430724143981934,
+      "learning_rate": 4.75394171046345e-07,
+      "epoch": 0.014333835017558949,
+      "step": 200
+    },
+    {
+      "loss": 3.6864,
+      "grad_norm": 2.86275577545166,
+      "learning_rate": 5.948399426660297e-07,
+      "epoch": 0.017917293771948686,
+      "step": 250
+    },
+    {
+      "loss": 3.671,
+      "grad_norm": 2.787710189819336,
+      "learning_rate": 7.142857142857143e-07,
+      "epoch": 0.021500752526338422,
+      "step": 300
+    },
+    {
+      "loss": 3.6812,
+      "grad_norm": 2.906496524810791,
+      "learning_rate": 8.337314859053989e-07,
+      "epoch": 0.025084211280728158,
+      "step": 350
+    },
+    {
+      "loss": 3.6657,
+      "grad_norm": 2.733621120452881,
+      "learning_rate": 9.531772575250838e-07,
+      "epoch": 0.028667670035117897,
+      "step": 400
+    },
+    {
+      "loss": 3.6776,
+      "grad_norm": 2.9586291313171387,
+      "learning_rate": 1.0726230291447684e-06,
+      "epoch": 0.03225112878950763,
+      "step": 450
+    },
+    {
+      "loss": 3.6817,
+      "grad_norm": 2.697490930557251,
+      "learning_rate": 1.192068800764453e-06,
+      "epoch": 0.03583458754389737,
+      "step": 500
+    },
+    {
+      "loss": 3.6645,
+      "grad_norm": 2.8789138793945312,
+      "learning_rate": 1.3115145723841377e-06,
+      "epoch": 0.03941804629828711,
+      "step": 550
+    },
+    {
+      "loss": 3.6701,
+      "grad_norm": 2.738499879837036,
+      "learning_rate": 1.4309603440038225e-06,
+      "epoch": 0.043001505052676844,
+      "step": 600
+    },
+    {
+      "loss": 3.6557,
+      "grad_norm": 2.976515293121338,
+      "learning_rate": 1.550406115623507e-06,
+      "epoch": 0.04658496380706658,
+      "step": 650
+    },
+    {
+      "loss": 3.6624,
+      "grad_norm": 2.8300790786743164,
+      "learning_rate": 1.6698518872431918e-06,
+      "epoch": 0.050168422561456316,
+      "step": 700
+    },
+    {
+      "loss": 3.6638,
+      "grad_norm": 2.8557324409484863,
+      "learning_rate": 1.7892976588628764e-06,
+      "epoch": 0.05375188131584605,
+      "step": 750
+    },
+    {
+      "loss": 3.6746,
+      "grad_norm": 2.915972948074341,
+      "learning_rate": 1.9087434304825613e-06,
+      "epoch": 0.057335340070235795,
+      "step": 800
+    },
+    {
+      "loss": 3.6571,
+      "grad_norm": 2.833534002304077,
+      "learning_rate": 2.0281892021022457e-06,
+      "epoch": 0.06091879882462553,
+      "step": 850
+    },
+    {
+      "loss": 3.6641,
+      "grad_norm": 2.786886215209961,
+      "learning_rate": 2.1476349737219305e-06,
+      "epoch": 0.06450225757901526,
+      "step": 900
+    },
+    {
+      "loss": 3.6626,
+      "grad_norm": 2.888093948364258,
+      "learning_rate": 2.2670807453416154e-06,
+      "epoch": 0.068085716333405,
+      "step": 950
+    },
+    {
+      "loss": 3.6669,
+      "grad_norm": 2.935640335083008,
+      "learning_rate": 2.3865265169613e-06,
+      "epoch": 0.07166917508779475,
+      "step": 1000
+    },
+    {
+      "loss": 3.6766,
+      "grad_norm": 2.9223127365112305,
+      "learning_rate": 2.5059722885809846e-06,
+      "epoch": 0.07525263384218447,
+      "step": 1050
+    },
+    {
+      "loss": 3.6616,
+      "grad_norm": 2.855170488357544,
+      "learning_rate": 2.625418060200669e-06,
+      "epoch": 0.07883609259657422,
+      "step": 1100
+    },
+    {
+      "loss": 3.6633,
+      "grad_norm": 2.822401285171509,
+      "learning_rate": 2.7448638318203535e-06,
+      "epoch": 0.08241955135096395,
+      "step": 1150
+    },
+    {
+      "loss": 3.6526,
+      "grad_norm": 2.8145692348480225,
+      "learning_rate": 2.8643096034400387e-06,
+      "epoch": 0.08600301010535369,
+      "step": 1200
+    },
+    {
+      "loss": 3.6578,
+      "grad_norm": 2.7493700981140137,
+      "learning_rate": 2.983755375059723e-06,
+      "epoch": 0.08958646885974342,
+      "step": 1250
+    },
+    {
+      "loss": 3.657,
+      "grad_norm": 2.7674636840820312,
+      "learning_rate": 3.1032011466794076e-06,
+      "epoch": 0.09316992761413316,
+      "step": 1300
+    },
+    {
+      "loss": 3.6579,
+      "grad_norm": 2.798501491546631,
+      "learning_rate": 3.222646918299093e-06,
+      "epoch": 0.0967533863685229,
+      "step": 1350
+    },
+    {
+      "loss": 3.6667,
+      "grad_norm": 3.045165777206421,
+      "learning_rate": 3.3420926899187773e-06,
+      "epoch": 0.10033684512291263,
+      "step": 1400
+    },
+    {
+      "loss": 3.6693,
+      "grad_norm": 2.730278730392456,
+      "learning_rate": 3.4615384615384617e-06,
+      "epoch": 0.10392030387730238,
+      "step": 1450
+    },
+    {
+      "loss": 3.6602,
+      "grad_norm": 2.8988585472106934,
+      "learning_rate": 3.580984233158146e-06,
+      "epoch": 0.1075037626316921,
+      "step": 1500
+    },
+    {
+      "loss": 3.6628,
+      "grad_norm": 2.9216086864471436,
+      "learning_rate": 3.7004300047778314e-06,
+      "epoch": 0.11108722138608185,
+      "step": 1550
+    },
+    {
+      "loss": 3.6625,
+      "grad_norm": 2.7945556640625,
+      "learning_rate": 3.819875776397516e-06,
+      "epoch": 0.11467068014047159,
+      "step": 1600
+    },
+    {
+      "loss": 3.6457,
+      "grad_norm": 2.895811080932617,
+      "learning_rate": 3.9393215480172e-06,
+      "epoch": 0.11825413889486132,
+      "step": 1650
+    },
+    {
+      "loss": 3.6572,
+      "grad_norm": 2.634783983230591,
+      "learning_rate": 4.0587673196368855e-06,
+      "epoch": 0.12183759764925106,
+      "step": 1700
+    },
+    {
+      "loss": 3.6515,
+      "grad_norm": 2.907348871231079,
+      "learning_rate": 4.17821309125657e-06,
+      "epoch": 0.1254210564036408,
+      "step": 1750
+    },
+    {
+      "loss": 3.6465,
+      "grad_norm": 2.9280805587768555,
+      "learning_rate": 4.297658862876254e-06,
+      "epoch": 0.12900451515803052,
+      "step": 1800
+    },
+    {
+      "loss": 3.6564,
+      "grad_norm": 3.136627197265625,
+      "learning_rate": 4.417104634495939e-06,
+      "epoch": 0.13258797391242028,
+      "step": 1850
+    },
+    {
+      "loss": 3.6438,
+      "grad_norm": 2.8626930713653564,
+      "learning_rate": 4.536550406115624e-06,
+      "epoch": 0.13617143266681,
+      "step": 1900
+    },
+    {
+      "loss": 3.6442,
+      "grad_norm": 2.99165678024292,
+      "learning_rate": 4.6559961777353084e-06,
+      "epoch": 0.13975489142119973,
+      "step": 1950
+    },
+    {
+      "loss": 3.6556,
+      "grad_norm": 2.8795509338378906,
+      "learning_rate": 4.775441949354993e-06,
+      "epoch": 0.1433383501755895,
+      "step": 2000
+    },
+    {
+      "eval_loss": 3.6125245094299316,
+      "eval_model_preparation_time": 0.0025,
+      "eval_bleu": 0.11687587046602367,
+      "eval_chrf": 31.48836065140496,
+      "eval_runtime": 48.0402,
+      "eval_samples_per_second": 41.632,
+      "eval_steps_per_second": 0.666,
+      "epoch": 0.1433383501755895,
+      "step": 2000
+    }
+  ],
+  "best_metric": 0.11687587046602367,
+  "total_steps": 83718
+}