upload

README.md

@@ -1,3 +1,39 @@
 ---
 license: apache-2.0
+base_model: meta-llama/Llama-2-7b-hf
+datasets:
+- GEM/viggo
+language:
+- en
+pipeline_tag: text2text-generation
+tags:
+- punica
+- llama-factory
+- lora
+- generated_from_trainer
 ---
+
+* Base Model: [Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf)
+* LoRA target: `q_proj,k_proj,v_proj,o_proj,gate_proj,up_proj,down_proj`
+* LoRA rank: 16
+
+See <https://github.com/punica-ai/punica/tree/master/examples/finetune>
+
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 4.0
+
+### Framework versions
+
+- Transformers 4.34.1
+- Pytorch 2.2.0.dev20230911+cu121
+- Datasets 2.14.4
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,28 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16.0,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a84fffc0cce7f7b82caceb8fe13a7a4d455001624f981701c0d90689a598ef98
+size 160069834

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.7563483387231826,
+    "train_runtime": 1265.7157,
+    "train_samples_per_second": 16.127,
+    "train_steps_per_second": 0.506
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.7563483387231826,
+    "train_runtime": 1265.7157,
+    "train_samples_per_second": 16.127,
+    "train_steps_per_second": 0.506
+}

trainer_log.jsonl

@@ -0,0 +1,65 @@
+{"current_steps": 10, "total_steps": 640, "loss": 1.692, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.996988640512931e-05, "epoch": 0.06, "percentage": 1.56, "elapsed_time": "0:00:20", "remaining_time": "0:21:52"}
+{"current_steps": 20, "total_steps": 640, "loss": 1.2657, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.987961816680492e-05, "epoch": 0.12, "percentage": 3.12, "elapsed_time": "0:00:41", "remaining_time": "0:21:15"}
+{"current_steps": 30, "total_steps": 640, "loss": 1.055, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.972941274911953e-05, "epoch": 0.19, "percentage": 4.69, "elapsed_time": "0:01:01", "remaining_time": "0:20:42"}
+{"current_steps": 40, "total_steps": 640, "loss": 0.9921, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.951963201008076e-05, "epoch": 0.25, "percentage": 6.25, "elapsed_time": "0:01:21", "remaining_time": "0:20:17"}
+{"current_steps": 50, "total_steps": 640, "loss": 0.9406, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9250781329863606e-05, "epoch": 0.31, "percentage": 7.81, "elapsed_time": "0:01:40", "remaining_time": "0:19:46"}
+{"current_steps": 60, "total_steps": 640, "loss": 0.8524, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.892350839330522e-05, "epoch": 0.38, "percentage": 9.38, "elapsed_time": "0:02:00", "remaining_time": "0:19:25"}
+{"current_steps": 70, "total_steps": 640, "loss": 0.8515, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.853860162957552e-05, "epoch": 0.44, "percentage": 10.94, "elapsed_time": "0:02:20", "remaining_time": "0:19:01"}
+{"current_steps": 80, "total_steps": 640, "loss": 0.8268, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8096988312782174e-05, "epoch": 0.5, "percentage": 12.5, "elapsed_time": "0:02:40", "remaining_time": "0:18:41"}
+{"current_steps": 90, "total_steps": 640, "loss": 0.8694, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.759973232808609e-05, "epoch": 0.56, "percentage": 14.06, "elapsed_time": "0:02:59", "remaining_time": "0:18:17"}
+{"current_steps": 100, "total_steps": 640, "loss": 0.8054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7048031608708876e-05, "epoch": 0.62, "percentage": 15.62, "elapsed_time": "0:03:18", "remaining_time": "0:17:53"}
+{"current_steps": 110, "total_steps": 640, "loss": 0.7789, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6443215250006806e-05, "epoch": 0.69, "percentage": 17.19, "elapsed_time": "0:03:38", "remaining_time": "0:17:32"}
+{"current_steps": 120, "total_steps": 640, "loss": 0.8142, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5786740307563636e-05, "epoch": 0.75, "percentage": 18.75, "elapsed_time": "0:03:58", "remaining_time": "0:17:12"}
+{"current_steps": 130, "total_steps": 640, "loss": 0.7686, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.508018828701612e-05, "epoch": 0.81, "percentage": 20.31, "elapsed_time": "0:04:17", "remaining_time": "0:16:49"}
+{"current_steps": 140, "total_steps": 640, "loss": 0.7904, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.4325261334068426e-05, "epoch": 0.88, "percentage": 21.88, "elapsed_time": "0:04:37", "remaining_time": "0:16:30"}
+{"current_steps": 150, "total_steps": 640, "loss": 0.8099, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.352377813387398e-05, "epoch": 0.94, "percentage": 23.44, "elapsed_time": "0:04:57", "remaining_time": "0:16:11"}
+{"current_steps": 160, "total_steps": 640, "loss": 0.8211, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.267766952966369e-05, "epoch": 1.0, "percentage": 25.0, "elapsed_time": "0:05:15", "remaining_time": "0:15:47"}
+{"current_steps": 170, "total_steps": 640, "loss": 0.7577, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.178897387117546e-05, "epoch": 1.06, "percentage": 26.56, "elapsed_time": "0:05:34", "remaining_time": "0:15:26"}
+{"current_steps": 180, "total_steps": 640, "loss": 0.778, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.085983210409114e-05, "epoch": 1.12, "percentage": 28.12, "elapsed_time": "0:05:54", "remaining_time": "0:15:07"}
+{"current_steps": 190, "total_steps": 640, "loss": 0.752, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.9892482612310836e-05, "epoch": 1.19, "percentage": 29.69, "elapsed_time": "0:06:14", "remaining_time": "0:14:47"}
+{"current_steps": 200, "total_steps": 640, "loss": 0.7247, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.888925582549006e-05, "epoch": 1.25, "percentage": 31.25, "elapsed_time": "0:06:34", "remaining_time": "0:14:27"}
+{"current_steps": 210, "total_steps": 640, "loss": 0.7593, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.785256860483054e-05, "epoch": 1.31, "percentage": 32.81, "elapsed_time": "0:06:55", "remaining_time": "0:14:10"}
+{"current_steps": 220, "total_steps": 640, "loss": 0.7217, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.678491842064995e-05, "epoch": 1.38, "percentage": 34.38, "elapsed_time": "0:07:14", "remaining_time": "0:13:49"}
+{"current_steps": 230, "total_steps": 640, "loss": 0.7509, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.568887733575706e-05, "epoch": 1.44, "percentage": 35.94, "elapsed_time": "0:07:34", "remaining_time": "0:13:29"}
+{"current_steps": 240, "total_steps": 640, "loss": 0.7367, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.456708580912725e-05, "epoch": 1.5, "percentage": 37.5, "elapsed_time": "0:07:54", "remaining_time": "0:13:11"}
+{"current_steps": 250, "total_steps": 640, "loss": 0.7168, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.34222463348055e-05, "epoch": 1.56, "percentage": 39.06, "elapsed_time": "0:08:14", "remaining_time": "0:12:51"}
+{"current_steps": 260, "total_steps": 640, "loss": 0.7567, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.225711693136156e-05, "epoch": 1.62, "percentage": 40.62, "elapsed_time": "0:08:34", "remaining_time": "0:12:31"}
+{"current_steps": 270, "total_steps": 640, "loss": 0.7534, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.10745044975816e-05, "epoch": 1.69, "percentage": 42.19, "elapsed_time": "0:08:53", "remaining_time": "0:12:11"}
+{"current_steps": 280, "total_steps": 640, "loss": 0.7681, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9877258050403212e-05, "epoch": 1.75, "percentage": 43.75, "elapsed_time": "0:09:13", "remaining_time": "0:11:51"}
+{"current_steps": 290, "total_steps": 640, "loss": 0.7094, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8668261861384045e-05, "epoch": 1.81, "percentage": 45.31, "elapsed_time": "0:09:32", "remaining_time": "0:11:30"}
+{"current_steps": 300, "total_steps": 640, "loss": 0.7504, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7450428508239024e-05, "epoch": 1.88, "percentage": 46.88, "elapsed_time": "0:09:51", "remaining_time": "0:11:10"}
+{"current_steps": 310, "total_steps": 640, "loss": 0.715, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6226691858185454e-05, "epoch": 1.94, "percentage": 48.44, "elapsed_time": "0:10:11", "remaining_time": "0:10:51"}
+{"current_steps": 320, "total_steps": 640, "loss": 0.7322, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5e-05, "epoch": 2.0, "percentage": 50.0, "elapsed_time": "0:10:30", "remaining_time": "0:10:30"}
+{"current_steps": 330, "total_steps": 640, "loss": 0.7124, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3773308141814552e-05, "epoch": 2.06, "percentage": 51.56, "elapsed_time": "0:10:50", "remaining_time": "0:10:10"}
+{"current_steps": 340, "total_steps": 640, "loss": 0.6626, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2549571491760986e-05, "epoch": 2.12, "percentage": 53.12, "elapsed_time": "0:11:10", "remaining_time": "0:09:51"}
+{"current_steps": 350, "total_steps": 640, "loss": 0.7094, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1331738138615958e-05, "epoch": 2.19, "percentage": 54.69, "elapsed_time": "0:11:29", "remaining_time": "0:09:31"}
+{"current_steps": 360, "total_steps": 640, "loss": 0.7211, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0122741949596797e-05, "epoch": 2.25, "percentage": 56.25, "elapsed_time": "0:11:49", "remaining_time": "0:09:11"}
+{"current_steps": 370, "total_steps": 640, "loss": 0.7176, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8925495502418406e-05, "epoch": 2.31, "percentage": 57.81, "elapsed_time": "0:12:09", "remaining_time": "0:08:52"}
+{"current_steps": 380, "total_steps": 640, "loss": 0.7019, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7742883068638447e-05, "epoch": 2.38, "percentage": 59.38, "elapsed_time": "0:12:28", "remaining_time": "0:08:32"}
+{"current_steps": 390, "total_steps": 640, "loss": 0.6754, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.65777536651945e-05, "epoch": 2.44, "percentage": 60.94, "elapsed_time": "0:12:48", "remaining_time": "0:08:12"}
+{"current_steps": 400, "total_steps": 640, "loss": 0.6761, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5432914190872757e-05, "epoch": 2.5, "percentage": 62.5, "elapsed_time": "0:13:08", "remaining_time": "0:07:53"}
+{"current_steps": 410, "total_steps": 640, "loss": 0.6527, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4311122664242954e-05, "epoch": 2.56, "percentage": 64.06, "elapsed_time": "0:13:29", "remaining_time": "0:07:33"}
+{"current_steps": 420, "total_steps": 640, "loss": 0.678, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3215081579350058e-05, "epoch": 2.62, "percentage": 65.62, "elapsed_time": "0:13:48", "remaining_time": "0:07:14"}
+{"current_steps": 430, "total_steps": 640, "loss": 0.6991, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2147431395169459e-05, "epoch": 2.69, "percentage": 67.19, "elapsed_time": "0:14:08", "remaining_time": "0:06:54"}
+{"current_steps": 440, "total_steps": 640, "loss": 0.6507, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1110744174509952e-05, "epoch": 2.75, "percentage": 68.75, "elapsed_time": "0:14:28", "remaining_time": "0:06:34"}
+{"current_steps": 450, "total_steps": 640, "loss": 0.7174, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0107517387689166e-05, "epoch": 2.81, "percentage": 70.31, "elapsed_time": "0:14:48", "remaining_time": "0:06:15"}
+{"current_steps": 460, "total_steps": 640, "loss": 0.6967, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.140167895908867e-06, "epoch": 2.88, "percentage": 71.88, "elapsed_time": "0:15:08", "remaining_time": "0:05:55"}
+{"current_steps": 470, "total_steps": 640, "loss": 0.6837, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.211026128824539e-06, "epoch": 2.94, "percentage": 73.44, "elapsed_time": "0:15:27", "remaining_time": "0:05:35"}
+{"current_steps": 480, "total_steps": 640, "loss": 0.6855, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.3223304703363135e-06, "epoch": 3.0, "percentage": 75.0, "elapsed_time": "0:15:46", "remaining_time": "0:05:15"}
+{"current_steps": 490, "total_steps": 640, "loss": 0.6642, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.476221866126029e-06, "epoch": 3.06, "percentage": 76.56, "elapsed_time": "0:16:06", "remaining_time": "0:04:55"}
+{"current_steps": 500, "total_steps": 640, "loss": 0.6427, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.674738665931575e-06, "epoch": 3.12, "percentage": 78.12, "elapsed_time": "0:16:26", "remaining_time": "0:04:36"}
+{"current_steps": 510, "total_steps": 640, "loss": 0.6512, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.91981171298388e-06, "epoch": 3.19, "percentage": 79.69, "elapsed_time": "0:16:46", "remaining_time": "0:04:16"}
+{"current_steps": 520, "total_steps": 640, "loss": 0.677, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.213259692436367e-06, "epoch": 3.25, "percentage": 81.25, "elapsed_time": "0:17:05", "remaining_time": "0:03:56"}
+{"current_steps": 530, "total_steps": 640, "loss": 0.6549, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5567847499932e-06, "epoch": 3.31, "percentage": 82.81, "elapsed_time": "0:17:26", "remaining_time": "0:03:37"}
+{"current_steps": 540, "total_steps": 640, "loss": 0.668, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9519683912911266e-06, "epoch": 3.38, "percentage": 84.38, "elapsed_time": "0:17:46", "remaining_time": "0:03:17"}
+{"current_steps": 550, "total_steps": 640, "loss": 0.6617, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4002676719139166e-06, "epoch": 3.44, "percentage": 85.94, "elapsed_time": "0:18:05", "remaining_time": "0:02:57"}
+{"current_steps": 560, "total_steps": 640, "loss": 0.6543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9030116872178316e-06, "epoch": 3.5, "percentage": 87.5, "elapsed_time": "0:18:24", "remaining_time": "0:02:37"}
+{"current_steps": 570, "total_steps": 640, "loss": 0.6546, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4613983704244826e-06, "epoch": 3.56, "percentage": 89.06, "elapsed_time": "0:18:44", "remaining_time": "0:02:18"}
+{"current_steps": 580, "total_steps": 640, "loss": 0.6451, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0764916066947794e-06, "epoch": 3.62, "percentage": 90.62, "elapsed_time": "0:19:04", "remaining_time": "0:01:58"}
+{"current_steps": 590, "total_steps": 640, "loss": 0.6726, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.492186701364007e-07, "epoch": 3.69, "percentage": 92.19, "elapsed_time": "0:19:24", "remaining_time": "0:01:38"}
+{"current_steps": 600, "total_steps": 640, "loss": 0.6451, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.803679899192392e-07, "epoch": 3.75, "percentage": 93.75, "elapsed_time": "0:19:44", "remaining_time": "0:01:18"}
+{"current_steps": 610, "total_steps": 640, "loss": 0.6687, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.705872508804747e-07, "epoch": 3.81, "percentage": 95.31, "elapsed_time": "0:20:03", "remaining_time": "0:00:59"}
+{"current_steps": 620, "total_steps": 640, "loss": 0.644, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2038183319507955e-07, "epoch": 3.88, "percentage": 96.88, "elapsed_time": "0:20:23", "remaining_time": "0:00:39"}
+{"current_steps": 630, "total_steps": 640, "loss": 0.6766, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.011359487068987e-08, "epoch": 3.94, "percentage": 98.44, "elapsed_time": "0:20:43", "remaining_time": "0:00:19"}
+{"current_steps": 640, "total_steps": 640, "loss": 0.6681, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:21:02", "remaining_time": "0:00:00"}
+{"current_steps": 640, "total_steps": 640, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "0:21:02", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,412 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 640,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.996988640512931e-05,
+      "loss": 1.692,
+      "step": 10
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.987961816680492e-05,
+      "loss": 1.2657,
+      "step": 20
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.972941274911953e-05,
+      "loss": 1.055,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.951963201008076e-05,
+      "loss": 0.9921,
+      "step": 40
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.9250781329863606e-05,
+      "loss": 0.9406,
+      "step": 50
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.892350839330522e-05,
+      "loss": 0.8524,
+      "step": 60
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.853860162957552e-05,
+      "loss": 0.8515,
+      "step": 70
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.8096988312782174e-05,
+      "loss": 0.8268,
+      "step": 80
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.759973232808609e-05,
+      "loss": 0.8694,
+      "step": 90
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.7048031608708876e-05,
+      "loss": 0.8054,
+      "step": 100
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.6443215250006806e-05,
+      "loss": 0.7789,
+      "step": 110
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.5786740307563636e-05,
+      "loss": 0.8142,
+      "step": 120
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 4.508018828701612e-05,
+      "loss": 0.7686,
+      "step": 130
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 4.4325261334068426e-05,
+      "loss": 0.7904,
+      "step": 140
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 4.352377813387398e-05,
+      "loss": 0.8099,
+      "step": 150
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.267766952966369e-05,
+      "loss": 0.8211,
+      "step": 160
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 4.178897387117546e-05,
+      "loss": 0.7577,
+      "step": 170
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 4.085983210409114e-05,
+      "loss": 0.778,
+      "step": 180
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 3.9892482612310836e-05,
+      "loss": 0.752,
+      "step": 190
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 3.888925582549006e-05,
+      "loss": 0.7247,
+      "step": 200
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 3.785256860483054e-05,
+      "loss": 0.7593,
+      "step": 210
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 3.678491842064995e-05,
+      "loss": 0.7217,
+      "step": 220
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 3.568887733575706e-05,
+      "loss": 0.7509,
+      "step": 230
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 3.456708580912725e-05,
+      "loss": 0.7367,
+      "step": 240
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 3.34222463348055e-05,
+      "loss": 0.7168,
+      "step": 250
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 3.225711693136156e-05,
+      "loss": 0.7567,
+      "step": 260
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 3.10745044975816e-05,
+      "loss": 0.7534,
+      "step": 270
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 2.9877258050403212e-05,
+      "loss": 0.7681,
+      "step": 280
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 2.8668261861384045e-05,
+      "loss": 0.7094,
+      "step": 290
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 2.7450428508239024e-05,
+      "loss": 0.7504,
+      "step": 300
+    },
+    {
+      "epoch": 1.94,
+      "learning_rate": 2.6226691858185454e-05,
+      "loss": 0.715,
+      "step": 310
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.5e-05,
+      "loss": 0.7322,
+      "step": 320
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 2.3773308141814552e-05,
+      "loss": 0.7124,
+      "step": 330
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 2.2549571491760986e-05,
+      "loss": 0.6626,
+      "step": 340
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 2.1331738138615958e-05,
+      "loss": 0.7094,
+      "step": 350
+    },
+    {
+      "epoch": 2.25,
+      "learning_rate": 2.0122741949596797e-05,
+      "loss": 0.7211,
+      "step": 360
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.8925495502418406e-05,
+      "loss": 0.7176,
+      "step": 370
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 1.7742883068638447e-05,
+      "loss": 0.7019,
+      "step": 380
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.65777536651945e-05,
+      "loss": 0.6754,
+      "step": 390
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 1.5432914190872757e-05,
+      "loss": 0.6761,
+      "step": 400
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 1.4311122664242954e-05,
+      "loss": 0.6527,
+      "step": 410
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 1.3215081579350058e-05,
+      "loss": 0.678,
+      "step": 420
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 1.2147431395169459e-05,
+      "loss": 0.6991,
+      "step": 430
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 1.1110744174509952e-05,
+      "loss": 0.6507,
+      "step": 440
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 1.0107517387689166e-05,
+      "loss": 0.7174,
+      "step": 450
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 9.140167895908867e-06,
+      "loss": 0.6967,
+      "step": 460
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 8.211026128824539e-06,
+      "loss": 0.6837,
+      "step": 470
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.6855,
+      "step": 480
+    },
+    {
+      "epoch": 3.06,
+      "learning_rate": 6.476221866126029e-06,
+      "loss": 0.6642,
+      "step": 490
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 5.674738665931575e-06,
+      "loss": 0.6427,
+      "step": 500
+    },
+    {
+      "epoch": 3.19,
+      "learning_rate": 4.91981171298388e-06,
+      "loss": 0.6512,
+      "step": 510
+    },
+    {
+      "epoch": 3.25,
+      "learning_rate": 4.213259692436367e-06,
+      "loss": 0.677,
+      "step": 520
+    },
+    {
+      "epoch": 3.31,
+      "learning_rate": 3.5567847499932e-06,
+      "loss": 0.6549,
+      "step": 530
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 2.9519683912911266e-06,
+      "loss": 0.668,
+      "step": 540
+    },
+    {
+      "epoch": 3.44,
+      "learning_rate": 2.4002676719139166e-06,
+      "loss": 0.6617,
+      "step": 550
+    },
+    {
+      "epoch": 3.5,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.6543,
+      "step": 560
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 1.4613983704244826e-06,
+      "loss": 0.6546,
+      "step": 570
+    },
+    {
+      "epoch": 3.62,
+      "learning_rate": 1.0764916066947794e-06,
+      "loss": 0.6451,
+      "step": 580
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 7.492186701364007e-07,
+      "loss": 0.6726,
+      "step": 590
+    },
+    {
+      "epoch": 3.75,
+      "learning_rate": 4.803679899192392e-07,
+      "loss": 0.6451,
+      "step": 600
+    },
+    {
+      "epoch": 3.81,
+      "learning_rate": 2.705872508804747e-07,
+      "loss": 0.6687,
+      "step": 610
+    },
+    {
+      "epoch": 3.88,
+      "learning_rate": 1.2038183319507955e-07,
+      "loss": 0.644,
+      "step": 620
+    },
+    {
+      "epoch": 3.94,
+      "learning_rate": 3.011359487068987e-08,
+      "loss": 0.6766,
+      "step": 630
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 0.0,
+      "loss": 0.6681,
+      "step": 640
+    },
+    {
+      "epoch": 4.0,
+      "step": 640,
+      "total_flos": 1.3862359554185626e+17,
+      "train_loss": 0.7563483387231826,
+      "train_runtime": 1265.7157,
+      "train_samples_per_second": 16.127,
+      "train_steps_per_second": 0.506
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 640,
+  "num_train_epochs": 4,
+  "save_steps": 200,
+  "total_flos": 1.3862359554185626e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8964ebf0d40688644816d8995a9f6e8d6c6496768317c70d553f9ab98f59e673
+size 4664

viggo-r16.punica.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21c5ede53e3b3015eb9fc6d4f861baa9b5aa8fd551e11fbe2fe9d0fa67c855d2
+size 159912654