clean deploy

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

.gitignore

@@ -0,0 +1,7 @@
+**/optimizer.pt
+**/scheduler.pt
+**/scaler.pt
+**/rng_state.pth
+**/trainer_state.json
+**/training_args.bin
+**/pytorch_model.bin

README.md

@@ -0,0 +1,14 @@
+---
+title: ATA Assignment 2
+emoji: 🦀
+colorFrom: green
+colorTo: purple
+sdk: gradio
+python_version: "3.11"
+sdk_version: 6.5.1
+app_file: app.py
+pinned: false
+license: apache-2.0
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,99 @@
+from pathlib import Path
+import gradio as gr
+import torch
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+ROOT = Path(__file__).parent
+MODEL_ROOT = ROOT / "custom_t5_enzh"
+PREFIX = "translate English to Chinese: "
+
+def latest_checkpoint(root: Path) -> Path | None:
+    if not root.exists():
+        return None
+
+    ckpts = [p for p in root.iterdir() if p.is_dir() and p.name.startswith("checkpoint-")]
+    if ckpts:
+        ckpts.sort(key=lambda p: int(p.name.split("-")[-1]))
+        return ckpts[-1]
+
+    # fallback: root itself contains model files
+    if (root / "config.json").exists() or (root / "model.safetensors").exists():
+        return root
+
+    return None
+
+CKPT = latest_checkpoint(MODEL_ROOT)
+
+_pipe = {"tok": None, "model": None, "device": None, "ckpt": None}
+
+def model_ready():
+    return CKPT is not None
+
+def get_model():
+    if _pipe["model"] is None:
+        if CKPT is None:
+            raise RuntimeError("No checkpoint found.")
+
+        device = "cuda" if torch.cuda.is_available() else "cpu"
+
+        # ✅ let HF choose the right tokenizer implementation
+        tok = AutoTokenizer.from_pretrained(CKPT)
+        model = AutoModelForSeq2SeqLM.from_pretrained(CKPT).to(device)
+        model.eval()
+
+        _pipe.update({"tok": tok, "model": model, "device": device, "ckpt": str(CKPT)})
+
+        # quick startup self-test
+        try:
+            test = translate_text("I am happy")
+            print(f"[LOAD OK] ckpt={CKPT} device={device} test_out={repr(test)}")
+        except Exception as e:
+            print(f"[LOAD FAIL] ckpt={CKPT} device={device} err={e}")
+            raise
+
+    return _pipe["tok"], _pipe["model"], _pipe["device"]
+
+def translate_text(text: str):
+    text = (text or "").strip()
+    if not text:
+        return ""
+    if not model_ready():
+        return "[Model not ready — checkpoint folder not found.]"
+
+    tok, model, device = get_model()
+
+    prompt = PREFIX + text
+    inputs = tok(prompt, return_tensors="pt", truncation=True, max_length=256).to(device)
+
+    with torch.no_grad():
+        out_ids = model.generate(
+            **inputs,
+            max_new_tokens=80,
+            num_beams=4,
+            early_stopping=True,
+        )
+
+    result = tok.decode(out_ids[0], skip_special_tokens=True).strip()
+
+    # extra debug if blank
+    if not result:
+        raw = tok.decode(out_ids[0])
+        return f"[Blank output] raw={raw!r} ckpt={_pipe['ckpt']} device={device}"
+
+    return result
+
+title = "EN → ZH Translator"
+status = "✅ Model found" if model_ready() else "⏳ Model not found"
+
+with gr.Blocks() as demo:
+    gr.Markdown(f"# {title}")
+    gr.Markdown(f"**Status:** {status}")
+    gr.Markdown(f"**Loaded path:** `{str(CKPT) if CKPT else 'None'}`")
+
+    inp = gr.Textbox(label="English", lines=4, placeholder="Type English here...")
+    out = gr.Textbox(label="Chinese", lines=4)
+
+    btn = gr.Button("Translate")
+    btn.click(translate_text, inp, out)
+
+demo.launch()

custom_t5_enzh/checkpoint-29688/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 3,
+  "dense_act_fn": "relu",
+  "dropout_rate": 0.1,
+  "eos_token_id": 2,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": false,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 6,
+  "num_heads": 8,
+  "num_layers": 6,
+  "pad_token_id": 3,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "torch_dtype": "float32",
+  "transformers_version": "4.55.0",
+  "use_cache": true,
+  "vocab_size": 32100
+}

custom_t5_enzh/checkpoint-29688/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "decoder_start_token_id": 3,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.55.0"
+}

custom_t5_enzh/checkpoint-29688/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22a3755412d55bc2e8ddaf9d05656bf83f6305e2d3d6b709c393b41f96815611
+size 241984552

custom_t5_enzh/checkpoint-29688/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64b45f39877c482632ccdd5afcca5030d58cd36d1527ca55c881a5455383a71
+size 484048826

custom_t5_enzh/checkpoint-29688/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7959e86c1aa1b8eb7d94f513e7c9aed0577ed1a74cd7b9eaafc1fcdfdce76500
+size 14244

custom_t5_enzh/checkpoint-29688/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fedd999e43515c9c2556ec2ff18a27b6972410a2706a52a92e0f127da24a309
+size 988

custom_t5_enzh/checkpoint-29688/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb53167c045732a134505f0578ddee8eefcd648eb6826870ef1abb00377ad4d1
+size 1064

custom_t5_enzh/checkpoint-29688/special_tokens_map.json

@@ -0,0 +1,126 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "bos_token": "<s>",
+  "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
+  }
+}

custom_t5_enzh/checkpoint-29688/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5df5734af8ff808dbaa1ab4d6de550faa7b9b48303533175fac3bdf96848f689
+size 766228

custom_t5_enzh/checkpoint-29688/tokenizer_config.json

@@ -0,0 +1,950 @@
+{
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "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": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "<extra_id_99>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<extra_id_98>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<extra_id_97>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<extra_id_96>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<extra_id_95>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<extra_id_94>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<extra_id_93>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<extra_id_92>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<extra_id_91>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<extra_id_90>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<extra_id_89>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32011": {
+      "content": "<extra_id_88>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32012": {
+      "content": "<extra_id_87>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32013": {
+      "content": "<extra_id_86>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<extra_id_85>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<extra_id_84>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32016": {
+      "content": "<extra_id_83>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32017": {
+      "content": "<extra_id_82>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32018": {
+      "content": "<extra_id_81>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32019": {
+      "content": "<extra_id_80>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32020": {
+      "content": "<extra_id_79>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32021": {
+      "content": "<extra_id_78>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32022": {
+      "content": "<extra_id_77>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32023": {
+      "content": "<extra_id_76>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32024": {
+      "content": "<extra_id_75>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32025": {
+      "content": "<extra_id_74>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32026": {
+      "content": "<extra_id_73>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32027": {
+      "content": "<extra_id_72>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32028": {
+      "content": "<extra_id_71>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32029": {
+      "content": "<extra_id_70>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32030": {
+      "content": "<extra_id_69>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32031": {
+      "content": "<extra_id_68>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32032": {
+      "content": "<extra_id_67>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32033": {
+      "content": "<extra_id_66>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32034": {
+      "content": "<extra_id_65>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32035": {
+      "content": "<extra_id_64>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32036": {
+      "content": "<extra_id_63>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32037": {
+      "content": "<extra_id_62>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32038": {
+      "content": "<extra_id_61>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32039": {
+      "content": "<extra_id_60>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32040": {
+      "content": "<extra_id_59>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32041": {
+      "content": "<extra_id_58>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32042": {
+      "content": "<extra_id_57>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32043": {
+      "content": "<extra_id_56>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32044": {
+      "content": "<extra_id_55>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32045": {
+      "content": "<extra_id_54>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32046": {
+      "content": "<extra_id_53>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32047": {
+      "content": "<extra_id_52>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32048": {
+      "content": "<extra_id_51>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32049": {
+      "content": "<extra_id_50>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32050": {
+      "content": "<extra_id_49>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32051": {
+      "content": "<extra_id_48>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32052": {
+      "content": "<extra_id_47>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32053": {
+      "content": "<extra_id_46>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32054": {
+      "content": "<extra_id_45>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32055": {
+      "content": "<extra_id_44>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32056": {
+      "content": "<extra_id_43>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32057": {
+      "content": "<extra_id_42>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32058": {
+      "content": "<extra_id_41>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32059": {
+      "content": "<extra_id_40>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32060": {
+      "content": "<extra_id_39>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32061": {
+      "content": "<extra_id_38>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32062": {
+      "content": "<extra_id_37>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32063": {
+      "content": "<extra_id_36>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32064": {
+      "content": "<extra_id_35>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32065": {
+      "content": "<extra_id_34>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32066": {
+      "content": "<extra_id_33>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32067": {
+      "content": "<extra_id_32>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32068": {
+      "content": "<extra_id_31>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32069": {
+      "content": "<extra_id_30>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32070": {
+      "content": "<extra_id_29>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32071": {
+      "content": "<extra_id_28>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32072": {
+      "content": "<extra_id_27>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32073": {
+      "content": "<extra_id_26>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32074": {
+      "content": "<extra_id_25>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32075": {
+      "content": "<extra_id_24>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32076": {
+      "content": "<extra_id_23>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32077": {
+      "content": "<extra_id_22>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32078": {
+      "content": "<extra_id_21>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32079": {
+      "content": "<extra_id_20>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32080": {
+      "content": "<extra_id_19>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32081": {
+      "content": "<extra_id_18>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32082": {
+      "content": "<extra_id_17>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32083": {
+      "content": "<extra_id_16>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32084": {
+      "content": "<extra_id_15>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32085": {
+      "content": "<extra_id_14>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32086": {
+      "content": "<extra_id_13>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32087": {
+      "content": "<extra_id_12>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32088": {
+      "content": "<extra_id_11>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32089": {
+      "content": "<extra_id_10>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32090": {
+      "content": "<extra_id_9>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32091": {
+      "content": "<extra_id_8>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32092": {
+      "content": "<extra_id_7>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32093": {
+      "content": "<extra_id_6>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32094": {
+      "content": "<extra_id_5>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32095": {
+      "content": "<extra_id_4>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32096": {
+      "content": "<extra_id_3>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32097": {
+      "content": "<extra_id_2>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32098": {
+      "content": "<extra_id_1>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32099": {
+      "content": "<extra_id_0>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "extra_special_tokens": {},
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

custom_t5_enzh/checkpoint-29688/trainer_state.json

@@ -0,0 +1,1331 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 1000,
+  "global_step": 29688,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006736842105263158,
+      "grad_norm": 4.254439830780029,
+      "learning_rate": 0.0004966484774993264,
+      "loss": 8.8092,
+      "step": 200
+    },
+    {
+      "epoch": 0.013473684210526317,
+      "grad_norm": 3.3755834102630615,
+      "learning_rate": 0.0004932801131770412,
+      "loss": 8.1379,
+      "step": 400
+    },
+    {
+      "epoch": 0.020210526315789474,
+      "grad_norm": 1.1486470699310303,
+      "learning_rate": 0.0004899285906763676,
+      "loss": 7.8786,
+      "step": 600
+    },
+    {
+      "epoch": 0.026947368421052633,
+      "grad_norm": 1.2390578985214233,
+      "learning_rate": 0.0004865602263540825,
+      "loss": 7.7022,
+      "step": 800
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "grad_norm": 1.7450668811798096,
+      "learning_rate": 0.0004832087038534088,
+      "loss": 7.6146,
+      "step": 1000
+    },
+    {
+      "epoch": 0.03368421052631579,
+      "eval_chrf": 0.005726559318726246,
+      "eval_loss": 8.076652526855469,
+      "eval_runtime": 209.4663,
+      "eval_samples_per_second": 9.548,
+      "eval_steps_per_second": 0.597,
+      "step": 1000
+    },
+    {
+      "epoch": 0.04042105263157895,
+      "grad_norm": 2.2363343238830566,
+      "learning_rate": 0.0004798403395311237,
+      "loss": 7.5643,
+      "step": 1200
+    },
+    {
+      "epoch": 0.04715789473684211,
+      "grad_norm": 1.5633487701416016,
+      "learning_rate": 0.00047648881703045003,
+      "loss": 7.527,
+      "step": 1400
+    },
+    {
+      "epoch": 0.053894736842105266,
+      "grad_norm": 2.2892746925354004,
+      "learning_rate": 0.00047312045270816495,
+      "loss": 7.4918,
+      "step": 1600
+    },
+    {
+      "epoch": 0.06063157894736842,
+      "grad_norm": 1.7377341985702515,
+      "learning_rate": 0.00046976893020749124,
+      "loss": 7.4903,
+      "step": 1800
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "grad_norm": 1.7025725841522217,
+      "learning_rate": 0.0004664005658852061,
+      "loss": 7.4449,
+      "step": 2000
+    },
+    {
+      "epoch": 0.06736842105263158,
+      "eval_chrf": 0.0019243755855956966,
+      "eval_loss": 8.043418884277344,
+      "eval_runtime": 210.6222,
+      "eval_samples_per_second": 9.496,
+      "eval_steps_per_second": 0.593,
+      "step": 2000
+    },
+    {
+      "epoch": 0.07410526315789474,
+      "grad_norm": 2.077467679977417,
+      "learning_rate": 0.000463032201562921,
+      "loss": 7.4266,
+      "step": 2200
+    },
+    {
+      "epoch": 0.0808421052631579,
+      "grad_norm": 1.6652511358261108,
+      "learning_rate": 0.00045966383724063594,
+      "loss": 7.4337,
+      "step": 2400
+    },
+    {
+      "epoch": 0.08757894736842105,
+      "grad_norm": 1.4601976871490479,
+      "learning_rate": 0.00045629547291835086,
+      "loss": 7.3881,
+      "step": 2600
+    },
+    {
+      "epoch": 0.09431578947368421,
+      "grad_norm": 2.035797595977783,
+      "learning_rate": 0.00045294395041767715,
+      "loss": 7.3976,
+      "step": 2800
+    },
+    {
+      "epoch": 0.10105263157894737,
+      "grad_norm": 11.324400901794434,
+      "learning_rate": 0.00044957558609539207,
+      "loss": 7.3977,
+      "step": 3000
+    },
+    {
+      "epoch": 0.10105263157894737,
+      "eval_chrf": 0.002352741368315669,
+      "eval_loss": 8.023853302001953,
+      "eval_runtime": 212.3438,
+      "eval_samples_per_second": 9.419,
+      "eval_steps_per_second": 0.589,
+      "step": 3000
+    },
+    {
+      "epoch": 0.10778947368421053,
+      "grad_norm": 3.328237533569336,
+      "learning_rate": 0.00044620722177310694,
+      "loss": 7.3749,
+      "step": 3200
+    },
+    {
+      "epoch": 0.11452631578947368,
+      "grad_norm": 4.6249189376831055,
+      "learning_rate": 0.00044283885745082186,
+      "loss": 7.3797,
+      "step": 3400
+    },
+    {
+      "epoch": 0.12126315789473684,
+      "grad_norm": 7.7165913581848145,
+      "learning_rate": 0.00043947049312853683,
+      "loss": 7.3639,
+      "step": 3600
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 592.001220703125,
+      "learning_rate": 0.0004361189706278631,
+      "loss": 7.3774,
+      "step": 3800
+    },
+    {
+      "epoch": 0.13473684210526315,
+      "grad_norm": 10.053915023803711,
+      "learning_rate": 0.000432750606305578,
+      "loss": 7.3629,
+      "step": 4000
+    },
+    {
+      "epoch": 0.13473684210526315,
+      "eval_chrf": 0.0026428740107985933,
+      "eval_loss": 7.972915172576904,
+      "eval_runtime": 208.7087,
+      "eval_samples_per_second": 9.583,
+      "eval_steps_per_second": 0.599,
+      "step": 4000
+    },
+    {
+      "epoch": 0.1414736842105263,
+      "grad_norm": 12.676908493041992,
+      "learning_rate": 0.0004293822419832929,
+      "loss": 7.3723,
+      "step": 4200
+    },
+    {
+      "epoch": 0.1482105263157895,
+      "grad_norm": 3.955014228820801,
+      "learning_rate": 0.0004260138776610078,
+      "loss": 7.3371,
+      "step": 4400
+    },
+    {
+      "epoch": 0.15494736842105264,
+      "grad_norm": 7.863338470458984,
+      "learning_rate": 0.0004226455133387227,
+      "loss": 7.3359,
+      "step": 4600
+    },
+    {
+      "epoch": 0.1616842105263158,
+      "grad_norm": 1.5261688232421875,
+      "learning_rate": 0.00041927714901643766,
+      "loss": 7.3433,
+      "step": 4800
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "grad_norm": 8.192843437194824,
+      "learning_rate": 0.00041590878469415253,
+      "loss": 7.3336,
+      "step": 5000
+    },
+    {
+      "epoch": 0.16842105263157894,
+      "eval_chrf": 0.002056091763873794,
+      "eval_loss": 7.981015682220459,
+      "eval_runtime": 210.934,
+      "eval_samples_per_second": 9.482,
+      "eval_steps_per_second": 0.593,
+      "step": 5000
+    },
+    {
+      "epoch": 0.1751578947368421,
+      "grad_norm": 7.735596179962158,
+      "learning_rate": 0.00041254042037186745,
+      "loss": 7.3357,
+      "step": 5200
+    },
+    {
+      "epoch": 0.18189473684210528,
+      "grad_norm": 3.6393988132476807,
+      "learning_rate": 0.00040917205604958237,
+      "loss": 7.3266,
+      "step": 5400
+    },
+    {
+      "epoch": 0.18863157894736843,
+      "grad_norm": 6.396200656890869,
+      "learning_rate": 0.00040580369172729723,
+      "loss": 7.339,
+      "step": 5600
+    },
+    {
+      "epoch": 0.19536842105263158,
+      "grad_norm": 2.8999171257019043,
+      "learning_rate": 0.00040243532740501215,
+      "loss": 7.2893,
+      "step": 5800
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "grad_norm": 63.303401947021484,
+      "learning_rate": 0.0003991174885475613,
+      "loss": 7.3111,
+      "step": 6000
+    },
+    {
+      "epoch": 0.20210526315789473,
+      "eval_chrf": 0.004042745883260306,
+      "eval_loss": 7.9859795570373535,
+      "eval_runtime": 209.8571,
+      "eval_samples_per_second": 9.53,
+      "eval_steps_per_second": 0.596,
+      "step": 6000
+    },
+    {
+      "epoch": 0.20884210526315788,
+      "grad_norm": 5.230437755584717,
+      "learning_rate": 0.0003957491242252762,
+      "loss": 7.2863,
+      "step": 6200
+    },
+    {
+      "epoch": 0.21557894736842106,
+      "grad_norm": 29.289928436279297,
+      "learning_rate": 0.0003923807599029911,
+      "loss": 7.3219,
+      "step": 6400
+    },
+    {
+      "epoch": 0.22231578947368422,
+      "grad_norm": 161.98826599121094,
+      "learning_rate": 0.0003890292374023174,
+      "loss": 7.3044,
+      "step": 6600
+    },
+    {
+      "epoch": 0.22905263157894737,
+      "grad_norm": 137.97628784179688,
+      "learning_rate": 0.00038566087308003233,
+      "loss": 7.3067,
+      "step": 6800
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "grad_norm": 11.88398265838623,
+      "learning_rate": 0.00038229250875774725,
+      "loss": 7.3083,
+      "step": 7000
+    },
+    {
+      "epoch": 0.23578947368421052,
+      "eval_chrf": 0.0052247493110234265,
+      "eval_loss": 7.974218845367432,
+      "eval_runtime": 209.3818,
+      "eval_samples_per_second": 9.552,
+      "eval_steps_per_second": 0.597,
+      "step": 7000
+    },
+    {
+      "epoch": 0.24252631578947367,
+      "grad_norm": 1372.63525390625,
+      "learning_rate": 0.0003789241444354621,
+      "loss": 7.287,
+      "step": 7200
+    },
+    {
+      "epoch": 0.24926315789473685,
+      "grad_norm": 4.1067352294921875,
+      "learning_rate": 0.00037555578011317704,
+      "loss": 7.3108,
+      "step": 7400
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 16.280475616455078,
+      "learning_rate": 0.00037218741579089196,
+      "loss": 7.3079,
+      "step": 7600
+    },
+    {
+      "epoch": 0.26273684210526316,
+      "grad_norm": 5.811795234680176,
+      "learning_rate": 0.0003688190514686068,
+      "loss": 7.2741,
+      "step": 7800
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "grad_norm": 12.810831069946289,
+      "learning_rate": 0.00036546752896793317,
+      "loss": 7.2951,
+      "step": 8000
+    },
+    {
+      "epoch": 0.2694736842105263,
+      "eval_chrf": 0.0018270964000608395,
+      "eval_loss": 7.971038341522217,
+      "eval_runtime": 208.8802,
+      "eval_samples_per_second": 9.575,
+      "eval_steps_per_second": 0.598,
+      "step": 8000
+    },
+    {
+      "epoch": 0.27621052631578946,
+      "grad_norm": 3.149369716644287,
+      "learning_rate": 0.0003620991646456481,
+      "loss": 7.276,
+      "step": 8200
+    },
+    {
+      "epoch": 0.2829473684210526,
+      "grad_norm": 8.988630294799805,
+      "learning_rate": 0.00035873080032336295,
+      "loss": 7.2858,
+      "step": 8400
+    },
+    {
+      "epoch": 0.28968421052631577,
+      "grad_norm": 3.606241464614868,
+      "learning_rate": 0.00035536243600107787,
+      "loss": 7.2752,
+      "step": 8600
+    },
+    {
+      "epoch": 0.296421052631579,
+      "grad_norm": 17.486343383789062,
+      "learning_rate": 0.0003519940716787928,
+      "loss": 7.2741,
+      "step": 8800
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "grad_norm": 14.639832496643066,
+      "learning_rate": 0.00034862570735650765,
+      "loss": 7.2818,
+      "step": 9000
+    },
+    {
+      "epoch": 0.3031578947368421,
+      "eval_chrf": 0.0028106490006736635,
+      "eval_loss": 7.982977867126465,
+      "eval_runtime": 208.2552,
+      "eval_samples_per_second": 9.604,
+      "eval_steps_per_second": 0.6,
+      "step": 9000
+    },
+    {
+      "epoch": 0.3098947368421053,
+      "grad_norm": 26.35228157043457,
+      "learning_rate": 0.0003452573430342226,
+      "loss": 7.2879,
+      "step": 9200
+    },
+    {
+      "epoch": 0.31663157894736843,
+      "grad_norm": 521.87890625,
+      "learning_rate": 0.0003418889787119375,
+      "loss": 7.2615,
+      "step": 9400
+    },
+    {
+      "epoch": 0.3233684210526316,
+      "grad_norm": 11.705015182495117,
+      "learning_rate": 0.00033852061438965236,
+      "loss": 7.2654,
+      "step": 9600
+    },
+    {
+      "epoch": 0.33010526315789473,
+      "grad_norm": 165.28273010253906,
+      "learning_rate": 0.0003351522500673673,
+      "loss": 7.2716,
+      "step": 9800
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "grad_norm": 3.113431215286255,
+      "learning_rate": 0.0003317838857450822,
+      "loss": 7.3123,
+      "step": 10000
+    },
+    {
+      "epoch": 0.3368421052631579,
+      "eval_chrf": 0.002015902006176986,
+      "eval_loss": 7.978994369506836,
+      "eval_runtime": 208.0446,
+      "eval_samples_per_second": 9.613,
+      "eval_steps_per_second": 0.601,
+      "step": 10000
+    },
+    {
+      "epoch": 0.34357894736842104,
+      "grad_norm": 21.174518585205078,
+      "learning_rate": 0.00032841552142279706,
+      "loss": 7.2841,
+      "step": 10200
+    },
+    {
+      "epoch": 0.3503157894736842,
+      "grad_norm": 6.507296562194824,
+      "learning_rate": 0.00032504715710051204,
+      "loss": 7.2824,
+      "step": 10400
+    },
+    {
+      "epoch": 0.35705263157894734,
+      "grad_norm": 8.37975025177002,
+      "learning_rate": 0.0003216787927782269,
+      "loss": 7.2624,
+      "step": 10600
+    },
+    {
+      "epoch": 0.36378947368421055,
+      "grad_norm": 6.058104038238525,
+      "learning_rate": 0.0003183104284559418,
+      "loss": 7.257,
+      "step": 10800
+    },
+    {
+      "epoch": 0.3705263157894737,
+      "grad_norm": 6.78323221206665,
+      "learning_rate": 0.00031494206413365674,
+      "loss": 7.2562,
+      "step": 11000
+    },
+    {
+      "epoch": 0.3705263157894737,
+      "eval_chrf": 0.002412227558600064,
+      "eval_loss": 7.9691162109375,
+      "eval_runtime": 206.8952,
+      "eval_samples_per_second": 9.667,
+      "eval_steps_per_second": 0.604,
+      "step": 11000
+    },
+    {
+      "epoch": 0.37726315789473686,
+      "grad_norm": 1.8443028926849365,
+      "learning_rate": 0.0003115736998113716,
+      "loss": 7.2435,
+      "step": 11200
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 3.558148145675659,
+      "learning_rate": 0.0003082053354890865,
+      "loss": 7.2501,
+      "step": 11400
+    },
+    {
+      "epoch": 0.39073684210526316,
+      "grad_norm": 3.3841934204101562,
+      "learning_rate": 0.00030483697116680144,
+      "loss": 7.275,
+      "step": 11600
+    },
+    {
+      "epoch": 0.3974736842105263,
+      "grad_norm": 13.780865669250488,
+      "learning_rate": 0.0003014686068445163,
+      "loss": 7.2607,
+      "step": 11800
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "grad_norm": 3.4634478092193604,
+      "learning_rate": 0.00029810024252223123,
+      "loss": 7.2695,
+      "step": 12000
+    },
+    {
+      "epoch": 0.40421052631578946,
+      "eval_chrf": 0.0018869151022955536,
+      "eval_loss": 7.95875358581543,
+      "eval_runtime": 207.586,
+      "eval_samples_per_second": 9.635,
+      "eval_steps_per_second": 0.602,
+      "step": 12000
+    },
+    {
+      "epoch": 0.4109473684210526,
+      "grad_norm": 13.57261848449707,
+      "learning_rate": 0.00029474872002155757,
+      "loss": 7.235,
+      "step": 12200
+    },
+    {
+      "epoch": 0.41768421052631577,
+      "grad_norm": 33.69303512573242,
+      "learning_rate": 0.00029138035569927244,
+      "loss": 7.2566,
+      "step": 12400
+    },
+    {
+      "epoch": 0.4244210526315789,
+      "grad_norm": 4.82642936706543,
+      "learning_rate": 0.00028801199137698736,
+      "loss": 7.2449,
+      "step": 12600
+    },
+    {
+      "epoch": 0.43115789473684213,
+      "grad_norm": 4.952188014984131,
+      "learning_rate": 0.0002846436270547023,
+      "loss": 7.256,
+      "step": 12800
+    },
+    {
+      "epoch": 0.4378947368421053,
+      "grad_norm": 9.873923301696777,
+      "learning_rate": 0.0002812921045540286,
+      "loss": 7.2354,
+      "step": 13000
+    },
+    {
+      "epoch": 0.4378947368421053,
+      "eval_chrf": 0.0038042034767471226,
+      "eval_loss": 7.933071613311768,
+      "eval_runtime": 206.7339,
+      "eval_samples_per_second": 9.674,
+      "eval_steps_per_second": 0.605,
+      "step": 13000
+    },
+    {
+      "epoch": 0.44463157894736843,
+      "grad_norm": 5.142228603363037,
+      "learning_rate": 0.00027794058205335485,
+      "loss": 7.2259,
+      "step": 13200
+    },
+    {
+      "epoch": 0.4513684210526316,
+      "grad_norm": 2.419574499130249,
+      "learning_rate": 0.00027457221773106977,
+      "loss": 7.2377,
+      "step": 13400
+    },
+    {
+      "epoch": 0.45810526315789474,
+      "grad_norm": 7.151025295257568,
+      "learning_rate": 0.0002712038534087847,
+      "loss": 7.2411,
+      "step": 13600
+    },
+    {
+      "epoch": 0.4648421052631579,
+      "grad_norm": 3.4384608268737793,
+      "learning_rate": 0.0002678354890864996,
+      "loss": 7.2342,
+      "step": 13800
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "grad_norm": 16.630428314208984,
+      "learning_rate": 0.0002644839665858259,
+      "loss": 7.2102,
+      "step": 14000
+    },
+    {
+      "epoch": 0.47157894736842104,
+      "eval_chrf": 0.0,
+      "eval_loss": 7.95149040222168,
+      "eval_runtime": 207.8298,
+      "eval_samples_per_second": 9.623,
+      "eval_steps_per_second": 0.601,
+      "step": 14000
+    },
+    {
+      "epoch": 0.4783157894736842,
+      "grad_norm": 92.76679992675781,
+      "learning_rate": 0.0002611156022635408,
+      "loss": 7.2328,
+      "step": 14200
+    },
+    {
+      "epoch": 0.48505263157894735,
+      "grad_norm": 4.76525354385376,
+      "learning_rate": 0.0002577472379412557,
+      "loss": 7.2187,
+      "step": 14400
+    },
+    {
+      "epoch": 0.4917894736842105,
+      "grad_norm": 21.399099349975586,
+      "learning_rate": 0.00025439571544058203,
+      "loss": 7.2287,
+      "step": 14600
+    },
+    {
+      "epoch": 0.4985263157894737,
+      "grad_norm": 52.742637634277344,
+      "learning_rate": 0.00025102735111829695,
+      "loss": 7.2321,
+      "step": 14800
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "grad_norm": 52.75876235961914,
+      "learning_rate": 0.00024765898679601187,
+      "loss": 7.1982,
+      "step": 15000
+    },
+    {
+      "epoch": 0.5052631578947369,
+      "eval_chrf": 0.08103163954254806,
+      "eval_loss": 7.952453136444092,
+      "eval_runtime": 208.516,
+      "eval_samples_per_second": 9.592,
+      "eval_steps_per_second": 0.599,
+      "step": 15000
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 458.2991027832031,
+      "learning_rate": 0.0002442906224737268,
+      "loss": 7.2178,
+      "step": 15200
+    },
+    {
+      "epoch": 0.5187368421052632,
+      "grad_norm": 18.82977867126465,
+      "learning_rate": 0.00024092225815144168,
+      "loss": 7.2092,
+      "step": 15400
+    },
+    {
+      "epoch": 0.5254736842105263,
+      "grad_norm": 7.6946892738342285,
+      "learning_rate": 0.00023755389382915657,
+      "loss": 7.1814,
+      "step": 15600
+    },
+    {
+      "epoch": 0.5322105263157895,
+      "grad_norm": 75.808837890625,
+      "learning_rate": 0.00023418552950687146,
+      "loss": 7.198,
+      "step": 15800
+    },
+    {
+      "epoch": 0.5389473684210526,
+      "grad_norm": 6.179436683654785,
+      "learning_rate": 0.00023081716518458638,
+      "loss": 7.2108,
+      "step": 16000
+    },
+    {
+      "epoch": 0.5389473684210526,
+      "eval_chrf": 0.003132385941953158,
+      "eval_loss": 7.934022426605225,
+      "eval_runtime": 208.7048,
+      "eval_samples_per_second": 9.583,
+      "eval_steps_per_second": 0.599,
+      "step": 16000
+    },
+    {
+      "epoch": 0.5456842105263158,
+      "grad_norm": 11.434579849243164,
+      "learning_rate": 0.00022744880086230128,
+      "loss": 7.2084,
+      "step": 16200
+    },
+    {
+      "epoch": 0.5524210526315789,
+      "grad_norm": 8.820486068725586,
+      "learning_rate": 0.00022408043654001617,
+      "loss": 7.2035,
+      "step": 16400
+    },
+    {
+      "epoch": 0.5591578947368421,
+      "grad_norm": 152.7312469482422,
+      "learning_rate": 0.00022071207221773106,
+      "loss": 7.1938,
+      "step": 16600
+    },
+    {
+      "epoch": 0.5658947368421052,
+      "grad_norm": 25.932987213134766,
+      "learning_rate": 0.00021734370789544598,
+      "loss": 7.1847,
+      "step": 16800
+    },
+    {
+      "epoch": 0.5726315789473684,
+      "grad_norm": 2.2950472831726074,
+      "learning_rate": 0.00021397534357316087,
+      "loss": 7.1826,
+      "step": 17000
+    },
+    {
+      "epoch": 0.5726315789473684,
+      "eval_chrf": 0.0019444598388038512,
+      "eval_loss": 7.9318037033081055,
+      "eval_runtime": 209.2532,
+      "eval_samples_per_second": 9.558,
+      "eval_steps_per_second": 0.597,
+      "step": 17000
+    },
+    {
+      "epoch": 0.5793684210526315,
+      "grad_norm": 2.543137788772583,
+      "learning_rate": 0.00021060697925087576,
+      "loss": 7.2089,
+      "step": 17200
+    },
+    {
+      "epoch": 0.5861052631578947,
+      "grad_norm": 2.32310152053833,
+      "learning_rate": 0.0002072554567502021,
+      "loss": 7.1882,
+      "step": 17400
+    },
+    {
+      "epoch": 0.592842105263158,
+      "grad_norm": 4.159054279327393,
+      "learning_rate": 0.000203887092427917,
+      "loss": 7.1915,
+      "step": 17600
+    },
+    {
+      "epoch": 0.5995789473684211,
+      "grad_norm": 2.6347360610961914,
+      "learning_rate": 0.0002005187281056319,
+      "loss": 7.1964,
+      "step": 17800
+    },
+    {
+      "epoch": 0.6063157894736843,
+      "grad_norm": 30.20026969909668,
+      "learning_rate": 0.0001971503637833468,
+      "loss": 7.1968,
+      "step": 18000
+    },
+    {
+      "epoch": 0.6063157894736843,
+      "eval_chrf": 0.004562467509283169,
+      "eval_loss": 7.917642593383789,
+      "eval_runtime": 205.2953,
+      "eval_samples_per_second": 9.742,
+      "eval_steps_per_second": 0.609,
+      "step": 18000
+    },
+    {
+      "epoch": 0.6130526315789474,
+      "grad_norm": 14.687439918518066,
+      "learning_rate": 0.0001937819994610617,
+      "loss": 7.164,
+      "step": 18200
+    },
+    {
+      "epoch": 0.6197894736842106,
+      "grad_norm": 2.020901918411255,
+      "learning_rate": 0.0001904136351387766,
+      "loss": 7.1797,
+      "step": 18400
+    },
+    {
+      "epoch": 0.6265263157894737,
+      "grad_norm": 3.653233051300049,
+      "learning_rate": 0.00018704527081649152,
+      "loss": 7.1938,
+      "step": 18600
+    },
+    {
+      "epoch": 0.6332631578947369,
+      "grad_norm": 3.1946516036987305,
+      "learning_rate": 0.00018367690649420643,
+      "loss": 7.1726,
+      "step": 18800
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 7.460574150085449,
+      "learning_rate": 0.00018030854217192133,
+      "loss": 7.1489,
+      "step": 19000
+    },
+    {
+      "epoch": 0.64,
+      "eval_chrf": 0.006730491793968211,
+      "eval_loss": 7.91720724105835,
+      "eval_runtime": 206.4462,
+      "eval_samples_per_second": 9.688,
+      "eval_steps_per_second": 0.605,
+      "step": 19000
+    },
+    {
+      "epoch": 0.6467368421052632,
+      "grad_norm": 3.547877311706543,
+      "learning_rate": 0.00017694017784963622,
+      "loss": 7.1717,
+      "step": 19200
+    },
+    {
+      "epoch": 0.6534736842105263,
+      "grad_norm": 6.870595932006836,
+      "learning_rate": 0.00017357181352735114,
+      "loss": 7.1649,
+      "step": 19400
+    },
+    {
+      "epoch": 0.6602105263157895,
+      "grad_norm": 30.911413192749023,
+      "learning_rate": 0.00017020344920506603,
+      "loss": 7.1932,
+      "step": 19600
+    },
+    {
+      "epoch": 0.6669473684210526,
+      "grad_norm": 27.14822769165039,
+      "learning_rate": 0.00016683508488278092,
+      "loss": 7.1748,
+      "step": 19800
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "grad_norm": 6.460318565368652,
+      "learning_rate": 0.00016346672056049584,
+      "loss": 7.1696,
+      "step": 20000
+    },
+    {
+      "epoch": 0.6736842105263158,
+      "eval_chrf": 0.0110937211817252,
+      "eval_loss": 7.917947292327881,
+      "eval_runtime": 205.7528,
+      "eval_samples_per_second": 9.72,
+      "eval_steps_per_second": 0.608,
+      "step": 20000
+    },
+    {
+      "epoch": 0.6804210526315789,
+      "grad_norm": 27.423723220825195,
+      "learning_rate": 0.00016009835623821074,
+      "loss": 7.1587,
+      "step": 20200
+    },
+    {
+      "epoch": 0.6871578947368421,
+      "grad_norm": 36.06264114379883,
+      "learning_rate": 0.00015672999191592563,
+      "loss": 7.162,
+      "step": 20400
+    },
+    {
+      "epoch": 0.6938947368421052,
+      "grad_norm": 21.235185623168945,
+      "learning_rate": 0.00015336162759364052,
+      "loss": 7.1682,
+      "step": 20600
+    },
+    {
+      "epoch": 0.7006315789473684,
+      "grad_norm": 63.7025032043457,
+      "learning_rate": 0.00014999326327135544,
+      "loss": 7.1485,
+      "step": 20800
+    },
+    {
+      "epoch": 0.7073684210526315,
+      "grad_norm": 24.675535202026367,
+      "learning_rate": 0.00014662489894907033,
+      "loss": 7.1642,
+      "step": 21000
+    },
+    {
+      "epoch": 0.7073684210526315,
+      "eval_chrf": 0.001302284516081954,
+      "eval_loss": 7.913628101348877,
+      "eval_runtime": 206.9451,
+      "eval_samples_per_second": 9.664,
+      "eval_steps_per_second": 0.604,
+      "step": 21000
+    },
+    {
+      "epoch": 0.7141052631578947,
+      "grad_norm": 8.021008491516113,
+      "learning_rate": 0.00014325653462678522,
+      "loss": 7.1759,
+      "step": 21200
+    },
+    {
+      "epoch": 0.7208421052631578,
+      "grad_norm": 7.012975215911865,
+      "learning_rate": 0.00013988817030450012,
+      "loss": 7.1351,
+      "step": 21400
+    },
+    {
+      "epoch": 0.7275789473684211,
+      "grad_norm": 10.689805030822754,
+      "learning_rate": 0.00013651980598221504,
+      "loss": 7.1471,
+      "step": 21600
+    },
+    {
+      "epoch": 0.7343157894736843,
+      "grad_norm": 5.859151840209961,
+      "learning_rate": 0.00013315144165992993,
+      "loss": 7.1629,
+      "step": 21800
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "grad_norm": 7.223715782165527,
+      "learning_rate": 0.00012978307733764485,
+      "loss": 7.1661,
+      "step": 22000
+    },
+    {
+      "epoch": 0.7410526315789474,
+      "eval_chrf": 0.0011799654844890197,
+      "eval_loss": 7.905208110809326,
+      "eval_runtime": 207.646,
+      "eval_samples_per_second": 9.632,
+      "eval_steps_per_second": 0.602,
+      "step": 22000
+    },
+    {
+      "epoch": 0.7477894736842106,
+      "grad_norm": 9.268714904785156,
+      "learning_rate": 0.00012641471301535977,
+      "loss": 7.157,
+      "step": 22200
+    },
+    {
+      "epoch": 0.7545263157894737,
+      "grad_norm": 12.853730201721191,
+      "learning_rate": 0.00012304634869307463,
+      "loss": 7.149,
+      "step": 22400
+    },
+    {
+      "epoch": 0.7612631578947369,
+      "grad_norm": 17.167985916137695,
+      "learning_rate": 0.00011967798437078954,
+      "loss": 7.1557,
+      "step": 22600
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 2.593167543411255,
+      "learning_rate": 0.00011630962004850446,
+      "loss": 7.1546,
+      "step": 22800
+    },
+    {
+      "epoch": 0.7747368421052632,
+      "grad_norm": 14.160483360290527,
+      "learning_rate": 0.00011294125572621935,
+      "loss": 7.1355,
+      "step": 23000
+    },
+    {
+      "epoch": 0.7747368421052632,
+      "eval_chrf": 0.0041122119540037425,
+      "eval_loss": 7.90371561050415,
+      "eval_runtime": 207.9982,
+      "eval_samples_per_second": 9.615,
+      "eval_steps_per_second": 0.601,
+      "step": 23000
+    },
+    {
+      "epoch": 0.7814736842105263,
+      "grad_norm": 10556.6650390625,
+      "learning_rate": 0.00010957289140393426,
+      "loss": 7.1865,
+      "step": 23200
+    },
+    {
+      "epoch": 0.7882105263157895,
+      "grad_norm": 4.445006847381592,
+      "learning_rate": 0.00010620452708164916,
+      "loss": 7.1488,
+      "step": 23400
+    },
+    {
+      "epoch": 0.7949473684210526,
+      "grad_norm": 85.52156829833984,
+      "learning_rate": 0.00010283616275936405,
+      "loss": 7.1588,
+      "step": 23600
+    },
+    {
+      "epoch": 0.8016842105263158,
+      "grad_norm": 6.259866714477539,
+      "learning_rate": 9.946779843707896e-05,
+      "loss": 7.1447,
+      "step": 23800
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "grad_norm": 224.35865783691406,
+      "learning_rate": 9.609943411479385e-05,
+      "loss": 7.129,
+      "step": 24000
+    },
+    {
+      "epoch": 0.8084210526315789,
+      "eval_chrf": 0.0,
+      "eval_loss": 7.911408424377441,
+      "eval_runtime": 207.0244,
+      "eval_samples_per_second": 9.661,
+      "eval_steps_per_second": 0.604,
+      "step": 24000
+    },
+    {
+      "epoch": 0.8151578947368421,
+      "grad_norm": 23.08391571044922,
+      "learning_rate": 9.273106979250876e-05,
+      "loss": 7.1423,
+      "step": 24200
+    },
+    {
+      "epoch": 0.8218947368421052,
+      "grad_norm": 245.7853546142578,
+      "learning_rate": 8.937954729183509e-05,
+      "loss": 7.1328,
+      "step": 24400
+    },
+    {
+      "epoch": 0.8286315789473684,
+      "grad_norm": 15.29963493347168,
+      "learning_rate": 8.601118296954999e-05,
+      "loss": 7.129,
+      "step": 24600
+    },
+    {
+      "epoch": 0.8353684210526315,
+      "grad_norm": 2.8458406925201416,
+      "learning_rate": 8.264281864726489e-05,
+      "loss": 7.1198,
+      "step": 24800
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 13.018074035644531,
+      "learning_rate": 7.927445432497979e-05,
+      "loss": 7.1327,
+      "step": 25000
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_chrf": 0.013941249868227827,
+      "eval_loss": 7.8870368003845215,
+      "eval_runtime": 207.43,
+      "eval_samples_per_second": 9.642,
+      "eval_steps_per_second": 0.603,
+      "step": 25000
+    },
+    {
+      "epoch": 0.8488421052631578,
+      "grad_norm": 5.2148823738098145,
+      "learning_rate": 7.590609000269468e-05,
+      "loss": 7.1452,
+      "step": 25200
+    },
+    {
+      "epoch": 0.8555789473684211,
+      "grad_norm": 19.233739852905273,
+      "learning_rate": 7.253772568040959e-05,
+      "loss": 7.1447,
+      "step": 25400
+    },
+    {
+      "epoch": 0.8623157894736843,
+      "grad_norm": 14.095065116882324,
+      "learning_rate": 6.916936135812451e-05,
+      "loss": 7.1247,
+      "step": 25600
+    },
+    {
+      "epoch": 0.8690526315789474,
+      "grad_norm": 7.621742248535156,
+      "learning_rate": 6.58009970358394e-05,
+      "loss": 7.1332,
+      "step": 25800
+    },
+    {
+      "epoch": 0.8757894736842106,
+      "grad_norm": 29.361238479614258,
+      "learning_rate": 6.243263271355431e-05,
+      "loss": 7.1217,
+      "step": 26000
+    },
+    {
+      "epoch": 0.8757894736842106,
+      "eval_chrf": 0.014676119312534507,
+      "eval_loss": 7.898392200469971,
+      "eval_runtime": 209.4371,
+      "eval_samples_per_second": 9.549,
+      "eval_steps_per_second": 0.597,
+      "step": 26000
+    },
+    {
+      "epoch": 0.8825263157894737,
+      "grad_norm": 5.2996015548706055,
+      "learning_rate": 5.90642683912692e-05,
+      "loss": 7.1288,
+      "step": 26200
+    },
+    {
+      "epoch": 0.8892631578947369,
+      "grad_norm": 11.741786003112793,
+      "learning_rate": 5.56959040689841e-05,
+      "loss": 7.1358,
+      "step": 26400
+    },
+    {
+      "epoch": 0.896,
+      "grad_norm": 11.052619934082031,
+      "learning_rate": 5.2327539746699005e-05,
+      "loss": 7.1089,
+      "step": 26600
+    },
+    {
+      "epoch": 0.9027368421052632,
+      "grad_norm": 43.7511100769043,
+      "learning_rate": 4.895917542441391e-05,
+      "loss": 7.1314,
+      "step": 26800
+    },
+    {
+      "epoch": 0.9094736842105263,
+      "grad_norm": 3.492421865463257,
+      "learning_rate": 4.559081110212881e-05,
+      "loss": 7.1272,
+      "step": 27000
+    },
+    {
+      "epoch": 0.9094736842105263,
+      "eval_chrf": 0.016404275037183086,
+      "eval_loss": 7.888070106506348,
+      "eval_runtime": 208.0677,
+      "eval_samples_per_second": 9.612,
+      "eval_steps_per_second": 0.601,
+      "step": 27000
+    },
+    {
+      "epoch": 0.9162105263157895,
+      "grad_norm": 4.310942649841309,
+      "learning_rate": 4.222244677984371e-05,
+      "loss": 7.1517,
+      "step": 27200
+    },
+    {
+      "epoch": 0.9229473684210526,
+      "grad_norm": 2.516460657119751,
+      "learning_rate": 3.885408245755861e-05,
+      "loss": 7.1274,
+      "step": 27400
+    },
+    {
+      "epoch": 0.9296842105263158,
+      "grad_norm": 16.778484344482422,
+      "learning_rate": 3.5485718135273514e-05,
+      "loss": 7.1142,
+      "step": 27600
+    },
+    {
+      "epoch": 0.9364210526315789,
+      "grad_norm": 12.279007911682129,
+      "learning_rate": 3.211735381298841e-05,
+      "loss": 7.1103,
+      "step": 27800
+    },
+    {
+      "epoch": 0.9431578947368421,
+      "grad_norm": 17.17557716369629,
+      "learning_rate": 2.876583131231474e-05,
+      "loss": 7.1172,
+      "step": 28000
+    },
+    {
+      "epoch": 0.9431578947368421,
+      "eval_chrf": 0.011932768282003571,
+      "eval_loss": 7.885815143585205,
+      "eval_runtime": 206.9267,
+      "eval_samples_per_second": 9.665,
+      "eval_steps_per_second": 0.604,
+      "step": 28000
+    },
+    {
+      "epoch": 0.9498947368421052,
+      "grad_norm": 10.02868366241455,
+      "learning_rate": 2.5414308811641068e-05,
+      "loss": 7.125,
+      "step": 28200
+    },
+    {
+      "epoch": 0.9566315789473684,
+      "grad_norm": 62.310943603515625,
+      "learning_rate": 2.204594448935597e-05,
+      "loss": 7.129,
+      "step": 28400
+    },
+    {
+      "epoch": 0.9633684210526315,
+      "grad_norm": 15.6820068359375,
+      "learning_rate": 1.867758016707087e-05,
+      "loss": 7.1403,
+      "step": 28600
+    },
+    {
+      "epoch": 0.9701052631578947,
+      "grad_norm": 29.801271438598633,
+      "learning_rate": 1.5309215844785772e-05,
+      "loss": 7.1221,
+      "step": 28800
+    },
+    {
+      "epoch": 0.9768421052631578,
+      "grad_norm": 10.878236770629883,
+      "learning_rate": 1.1940851522500673e-05,
+      "loss": 7.117,
+      "step": 29000
+    },
+    {
+      "epoch": 0.9768421052631578,
+      "eval_chrf": 0.007758678698519381,
+      "eval_loss": 7.882614612579346,
+      "eval_runtime": 206.9708,
+      "eval_samples_per_second": 9.663,
+      "eval_steps_per_second": 0.604,
+      "step": 29000
+    },
+    {
+      "epoch": 0.983578947368421,
+      "grad_norm": 12.309194564819336,
+      "learning_rate": 8.572487200215576e-06,
+      "loss": 7.1325,
+      "step": 29200
+    },
+    {
+      "epoch": 0.9903157894736843,
+      "grad_norm": 9.50011920928955,
+      "learning_rate": 5.204122877930477e-06,
+      "loss": 7.1155,
+      "step": 29400
+    },
+    {
+      "epoch": 0.9970526315789474,
+      "grad_norm": 10.140064239501953,
+      "learning_rate": 1.8357585556453785e-06,
+      "loss": 7.1061,
+      "step": 29600
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 29688,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1855167823020032e+16,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

custom_t5_enzh/checkpoint-29688/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:add135644272834a16fd6d191289d331be161e3f79fee156a1d67d95b81a509d
+size 5432

requirements.txt

@@ -0,0 +1,5 @@
+gradio==4.44.1
+transformers==4.44.2
+sentencepiece
+torch
+accelerate==0.33.0

runtime.txt

@@ -0,0 +1 @@
+python-3.10.13