upload

README.md

@@ -0,0 +1,62 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: upstage/SOLAR-10.7B-Instruct-v1.0
+model-index:
+- name: solar_model
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# solar_model
+
+This model is a fine-tuned version of [upstage/SOLAR-10.7B-Instruct-v1.0](https://huggingface.co/upstage/SOLAR-10.7B-Instruct-v1.0) on the ko_alpaca_style_dataset dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0003
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.37.1
+- Pytorch 2.0.1+cu117
+- Datasets 2.16.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,26 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "upstage/SOLAR-10.7B-Instruct-v1.0",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dbde56073279b46f896f96afafdb41fd82aa0abda97cd01ad3297cce9ab3c58
+size 10248928

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.7295773652993331,
+    "train_runtime": 13470.6062,
+    "train_samples_per_second": 6.356,
+    "train_steps_per_second": 0.05
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n'  + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "train_loss": 0.7295773652993331,
+    "train_runtime": 13470.6062,
+    "train_samples_per_second": 6.356,
+    "train_steps_per_second": 0.05
+}

trainer_log.jsonl

@@ -0,0 +1,67 @@
+{"current_steps": 10, "total_steps": 669, "loss": 1.1033, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002998660541859271, "epoch": 0.01, "percentage": 1.49, "elapsed_time": "0:02:16", "remaining_time": "2:30:24"}
+{"current_steps": 20, "total_steps": 669, "loss": 0.9066, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002994033387324446, "epoch": 0.03, "percentage": 2.99, "elapsed_time": "0:05:24", "remaining_time": "2:55:37"}
+{"current_steps": 30, "total_steps": 669, "loss": 0.846, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002986112199359036, "epoch": 0.04, "percentage": 4.48, "elapsed_time": "0:08:41", "remaining_time": "3:05:10"}
+{"current_steps": 40, "total_steps": 669, "loss": 0.8246, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029749144425379216, "epoch": 0.06, "percentage": 5.98, "elapsed_time": "0:12:02", "remaining_time": "3:09:21"}
+{"current_steps": 50, "total_steps": 669, "loss": 0.8011, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.000296205525182313, "epoch": 0.07, "percentage": 7.47, "elapsed_time": "0:15:24", "remaining_time": "3:10:40"}
+{"current_steps": 60, "total_steps": 669, "loss": 0.7911, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00029447059587783353, "epoch": 0.09, "percentage": 8.97, "elapsed_time": "0:18:44", "remaining_time": "3:10:09"}
+{"current_steps": 70, "total_steps": 669, "loss": 0.7719, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002924171389041629, "epoch": 0.1, "percentage": 10.46, "elapsed_time": "0:22:04", "remaining_time": "3:08:50"}
+{"current_steps": 80, "total_steps": 669, "loss": 0.7793, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002903004140503956, "epoch": 0.12, "percentage": 11.96, "elapsed_time": "0:25:26", "remaining_time": "3:07:16"}
+{"current_steps": 90, "total_steps": 669, "loss": 0.7633, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002876548000410533, "epoch": 0.13, "percentage": 13.45, "elapsed_time": "0:28:45", "remaining_time": "3:05:03"}
+{"current_steps": 100, "total_steps": 669, "loss": 0.7623, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00028470568577725704, "epoch": 0.15, "percentage": 14.95, "elapsed_time": "0:32:04", "remaining_time": "3:02:31"}
+{"current_steps": 110, "total_steps": 669, "loss": 0.7519, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002814595734436687, "epoch": 0.16, "percentage": 16.44, "elapsed_time": "0:35:16", "remaining_time": "2:59:16"}
+{"current_steps": 120, "total_steps": 669, "loss": 0.7471, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002779236200440321, "epoch": 0.18, "percentage": 17.94, "elapsed_time": "0:38:39", "remaining_time": "2:56:50"}
+{"current_steps": 130, "total_steps": 669, "loss": 0.7505, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002741056216214651, "epoch": 0.19, "percentage": 19.43, "elapsed_time": "0:42:01", "remaining_time": "2:54:14"}
+{"current_steps": 140, "total_steps": 669, "loss": 0.7342, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00027001399606980383, "epoch": 0.21, "percentage": 20.93, "elapsed_time": "0:45:22", "remaining_time": "2:51:26"}
+{"current_steps": 150, "total_steps": 669, "loss": 0.7443, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002656577645738938, "epoch": 0.22, "percentage": 22.42, "elapsed_time": "0:48:45", "remaining_time": "2:48:43"}
+{"current_steps": 160, "total_steps": 669, "loss": 0.7247, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002610465317197509, "epoch": 0.24, "percentage": 23.92, "elapsed_time": "0:52:06", "remaining_time": "2:45:44"}
+{"current_steps": 170, "total_steps": 669, "loss": 0.7319, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002561904643184426, "epoch": 0.25, "percentage": 25.41, "elapsed_time": "0:55:30", "remaining_time": "2:42:57"}
+{"current_steps": 180, "total_steps": 669, "loss": 0.7297, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00025110026899038105, "epoch": 0.27, "percentage": 26.91, "elapsed_time": "0:58:51", "remaining_time": "2:39:53"}
+{"current_steps": 190, "total_steps": 669, "loss": 0.7373, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002457871685594478, "epoch": 0.28, "percentage": 28.4, "elapsed_time": "1:02:12", "remaining_time": "2:36:50"}
+{"current_steps": 200, "total_steps": 669, "loss": 0.7267, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002402628773089967, "epoch": 0.3, "percentage": 29.9, "elapsed_time": "1:05:37", "remaining_time": "2:33:54"}
+{"current_steps": 210, "total_steps": 669, "loss": 0.7341, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00023453957515429192, "epoch": 0.31, "percentage": 31.39, "elapsed_time": "1:08:55", "remaining_time": "2:30:38"}
+{"current_steps": 220, "total_steps": 669, "loss": 0.7195, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0002286298807883231, "epoch": 0.33, "percentage": 32.88, "elapsed_time": "1:12:17", "remaining_time": "2:27:32"}
+{"current_steps": 230, "total_steps": 669, "loss": 0.7221, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00022254682386020736, "epoch": 0.34, "percentage": 34.38, "elapsed_time": "1:15:40", "remaining_time": "2:24:25"}
+{"current_steps": 240, "total_steps": 669, "loss": 0.7214, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00021630381624751795, "epoch": 0.36, "percentage": 35.87, "elapsed_time": "1:19:01", "remaining_time": "2:21:16"}
+{"current_steps": 250, "total_steps": 669, "loss": 0.7192, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00020991462248587929, "epoch": 0.37, "percentage": 37.37, "elapsed_time": "1:22:23", "remaining_time": "2:18:05"}
+{"current_steps": 260, "total_steps": 669, "loss": 0.7139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00020339332942102297, "epoch": 0.39, "percentage": 38.86, "elapsed_time": "1:25:44", "remaining_time": "2:14:53"}
+{"current_steps": 270, "total_steps": 669, "loss": 0.7164, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001967543151502182, "epoch": 0.4, "percentage": 40.36, "elapsed_time": "1:29:11", "remaining_time": "2:11:48"}
+{"current_steps": 280, "total_steps": 669, "loss": 0.7219, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00019001221732155218, "epoch": 0.42, "percentage": 41.85, "elapsed_time": "1:32:28", "remaining_time": "2:08:28"}
+{"current_steps": 290, "total_steps": 669, "loss": 0.7237, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001831819008609551, "epoch": 0.43, "percentage": 43.35, "elapsed_time": "1:35:51", "remaining_time": "2:05:16"}
+{"current_steps": 300, "total_steps": 669, "loss": 0.7236, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00017627842519812485, "epoch": 0.45, "percentage": 44.84, "elapsed_time": "1:39:16", "remaining_time": "2:02:06"}
+{"current_steps": 310, "total_steps": 669, "loss": 0.7038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016931701106361107, "epoch": 0.46, "percentage": 46.34, "elapsed_time": "1:42:44", "remaining_time": "1:58:58"}
+{"current_steps": 320, "total_steps": 669, "loss": 0.7073, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00016231300693026433, "epoch": 0.48, "percentage": 47.83, "elapsed_time": "1:46:12", "remaining_time": "1:55:49"}
+{"current_steps": 330, "total_steps": 669, "loss": 0.711, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00015528185517304027, "epoch": 0.49, "percentage": 49.33, "elapsed_time": "1:49:41", "remaining_time": "1:52:41"}
+{"current_steps": 340, "total_steps": 669, "loss": 0.7029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00014823905802176872, "epoch": 0.51, "percentage": 50.82, "elapsed_time": "1:53:07", "remaining_time": "1:49:27"}
+{"current_steps": 350, "total_steps": 669, "loss": 0.7199, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001412001433819556, "epoch": 0.52, "percentage": 52.32, "elapsed_time": "1:56:34", "remaining_time": "1:46:15"}
+{"current_steps": 360, "total_steps": 669, "loss": 0.7229, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00013418063059897524, "epoch": 0.54, "percentage": 53.81, "elapsed_time": "1:59:57", "remaining_time": "1:42:58"}
+{"current_steps": 370, "total_steps": 669, "loss": 0.7189, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012719599624113573, "epoch": 0.55, "percentage": 55.31, "elapsed_time": "2:03:17", "remaining_time": "1:39:38"}
+{"current_steps": 380, "total_steps": 669, "loss": 0.7147, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00012026163997705916, "epoch": 0.57, "percentage": 56.8, "elapsed_time": "2:06:40", "remaining_time": "1:36:20"}
+{"current_steps": 390, "total_steps": 669, "loss": 0.6928, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00011339285062260957, "epoch": 0.58, "percentage": 58.3, "elapsed_time": "2:10:00", "remaining_time": "1:33:00"}
+{"current_steps": 400, "total_steps": 669, "loss": 0.7002, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.00010660477243222808, "epoch": 0.6, "percentage": 59.79, "elapsed_time": "2:13:21", "remaining_time": "1:29:40"}
+{"current_steps": 410, "total_steps": 669, "loss": 0.7198, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.991237170899614e-05, "epoch": 0.61, "percentage": 61.29, "elapsed_time": "2:16:42", "remaining_time": "1:26:21"}
+{"current_steps": 420, "total_steps": 669, "loss": 0.701, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.33304038070446e-05, "epoch": 0.63, "percentage": 62.78, "elapsed_time": "2:20:05", "remaining_time": "1:23:03"}
+{"current_steps": 430, "total_steps": 669, "loss": 0.6928, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.68733805990611e-05, "epoch": 0.64, "percentage": 64.28, "elapsed_time": "2:23:25", "remaining_time": "1:19:42"}
+{"current_steps": 440, "total_steps": 669, "loss": 0.696, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.055553848062404e-05, "epoch": 0.66, "percentage": 65.77, "elapsed_time": "2:26:47", "remaining_time": "1:16:24"}
+{"current_steps": 450, "total_steps": 669, "loss": 0.7038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.439080698190579e-05, "epoch": 0.67, "percentage": 67.26, "elapsed_time": "2:30:12", "remaining_time": "1:13:06"}
+{"current_steps": 460, "total_steps": 669, "loss": 0.6949, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.839277805595081e-05, "epoch": 0.69, "percentage": 68.76, "elapsed_time": "2:33:34", "remaining_time": "1:09:46"}
+{"current_steps": 470, "total_steps": 669, "loss": 0.7054, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.257467611124105e-05, "epoch": 0.7, "percentage": 70.25, "elapsed_time": "2:36:57", "remaining_time": "1:06:27"}
+{"current_steps": 480, "total_steps": 669, "loss": 0.7013, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.6949328854621045e-05, "epoch": 0.72, "percentage": 71.75, "elapsed_time": "2:40:17", "remaining_time": "1:03:06"}
+{"current_steps": 490, "total_steps": 669, "loss": 0.6976, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.152913900886729e-05, "epoch": 0.73, "percentage": 73.24, "elapsed_time": "2:43:39", "remaining_time": "0:59:46"}
+{"current_steps": 500, "total_steps": 669, "loss": 0.6978, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.632605696725987e-05, "epoch": 0.75, "percentage": 74.74, "elapsed_time": "2:47:01", "remaining_time": "0:56:27"}
+{"current_steps": 510, "total_steps": 669, "loss": 0.6964, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.13515544454462e-05, "epoch": 0.76, "percentage": 76.23, "elapsed_time": "2:50:22", "remaining_time": "0:53:07"}
+{"current_steps": 520, "total_steps": 669, "loss": 0.7135, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.66165991886898e-05, "epoch": 0.78, "percentage": 77.73, "elapsed_time": "2:53:45", "remaining_time": "0:49:47"}
+{"current_steps": 530, "total_steps": 669, "loss": 0.7026, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2131630790269134e-05, "epoch": 0.79, "percentage": 79.22, "elapsed_time": "2:57:10", "remaining_time": "0:46:28"}
+{"current_steps": 540, "total_steps": 669, "loss": 0.6986, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.790653767434181e-05, "epoch": 0.81, "percentage": 80.72, "elapsed_time": "3:00:32", "remaining_time": "0:43:07"}
+{"current_steps": 550, "total_steps": 669, "loss": 0.6809, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3950635294022347e-05, "epoch": 0.82, "percentage": 82.21, "elapsed_time": "3:03:57", "remaining_time": "0:39:48"}
+{"current_steps": 560, "total_steps": 669, "loss": 0.6954, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.027264559274224e-05, "epoch": 0.84, "percentage": 83.71, "elapsed_time": "3:07:21", "remaining_time": "0:36:27"}
+{"current_steps": 570, "total_steps": 669, "loss": 0.7028, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6880677774175354e-05, "epoch": 0.85, "percentage": 85.2, "elapsed_time": "3:10:47", "remaining_time": "0:33:08"}
+{"current_steps": 580, "total_steps": 669, "loss": 0.6802, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3782210423127449e-05, "epoch": 0.87, "percentage": 86.7, "elapsed_time": "3:14:10", "remaining_time": "0:29:47"}
+{"current_steps": 590, "total_steps": 669, "loss": 0.6969, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0984075016809528e-05, "epoch": 0.88, "percentage": 88.19, "elapsed_time": "3:17:36", "remaining_time": "0:26:27"}
+{"current_steps": 600, "total_steps": 669, "loss": 0.6995, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.492440862848787e-06, "epoch": 0.9, "percentage": 89.69, "elapsed_time": "3:21:00", "remaining_time": "0:23:07"}
+{"current_steps": 610, "total_steps": 669, "loss": 0.6908, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.312801497246206e-06, "epoch": 0.91, "percentage": 91.18, "elapsed_time": "3:24:23", "remaining_time": "0:19:46"}
+{"current_steps": 620, "total_steps": 669, "loss": 0.6933, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.44996257227021e-06, "epoch": 0.93, "percentage": 92.68, "elapsed_time": "3:27:46", "remaining_time": "0:16:25"}
+{"current_steps": 630, "total_steps": 669, "loss": 0.6993, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.908031260991195e-06, "epoch": 0.94, "percentage": 94.17, "elapsed_time": "3:31:11", "remaining_time": "0:13:04"}
+{"current_steps": 640, "total_steps": 669, "loss": 0.6977, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6904072018175786e-06, "epoch": 0.96, "percentage": 95.67, "elapsed_time": "3:34:36", "remaining_time": "0:09:43"}
+{"current_steps": 650, "total_steps": 669, "loss": 0.6936, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.997750029989647e-07, "epoch": 0.97, "percentage": 97.16, "elapsed_time": "3:38:01", "remaining_time": "0:06:22"}
+{"current_steps": 660, "total_steps": 669, "loss": 0.6879, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.380983236223377e-07, "epoch": 0.99, "percentage": 98.65, "elapsed_time": "3:41:25", "remaining_time": "0:03:01"}
+{"current_steps": 669, "total_steps": 669, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "3:44:30", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,426 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 669,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "learning_rate": 0.0002998660541859271,
+      "loss": 1.1033,
+      "step": 10
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 0.0002994033387324446,
+      "loss": 0.9066,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 0.0002986112199359036,
+      "loss": 0.846,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 0.00029749144425379216,
+      "loss": 0.8246,
+      "step": 40
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 0.000296205525182313,
+      "loss": 0.8011,
+      "step": 50
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 0.00029447059587783353,
+      "loss": 0.7911,
+      "step": 60
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 0.0002924171389041629,
+      "loss": 0.7719,
+      "step": 70
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 0.0002903004140503956,
+      "loss": 0.7793,
+      "step": 80
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 0.0002876548000410533,
+      "loss": 0.7633,
+      "step": 90
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 0.00028470568577725704,
+      "loss": 0.7623,
+      "step": 100
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 0.0002814595734436687,
+      "loss": 0.7519,
+      "step": 110
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 0.0002779236200440321,
+      "loss": 0.7471,
+      "step": 120
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 0.0002741056216214651,
+      "loss": 0.7505,
+      "step": 130
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 0.00027001399606980383,
+      "loss": 0.7342,
+      "step": 140
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0002656577645738938,
+      "loss": 0.7443,
+      "step": 150
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 0.0002610465317197509,
+      "loss": 0.7247,
+      "step": 160
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 0.0002561904643184426,
+      "loss": 0.7319,
+      "step": 170
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 0.00025110026899038105,
+      "loss": 0.7297,
+      "step": 180
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 0.0002457871685594478,
+      "loss": 0.7373,
+      "step": 190
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 0.0002402628773089967,
+      "loss": 0.7267,
+      "step": 200
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.00023453957515429192,
+      "loss": 0.7341,
+      "step": 210
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 0.0002286298807883231,
+      "loss": 0.7195,
+      "step": 220
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.00022254682386020736,
+      "loss": 0.7221,
+      "step": 230
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 0.00021630381624751795,
+      "loss": 0.7214,
+      "step": 240
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 0.00020991462248587929,
+      "loss": 0.7192,
+      "step": 250
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.00020339332942102297,
+      "loss": 0.7139,
+      "step": 260
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 0.0001967543151502182,
+      "loss": 0.7164,
+      "step": 270
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 0.00019001221732155218,
+      "loss": 0.7219,
+      "step": 280
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 0.0001831819008609551,
+      "loss": 0.7237,
+      "step": 290
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 0.00017627842519812485,
+      "loss": 0.7236,
+      "step": 300
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 0.00016931701106361107,
+      "loss": 0.7038,
+      "step": 310
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 0.00016231300693026433,
+      "loss": 0.7073,
+      "step": 320
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 0.00015528185517304027,
+      "loss": 0.711,
+      "step": 330
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 0.00014823905802176872,
+      "loss": 0.7029,
+      "step": 340
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 0.0001412001433819556,
+      "loss": 0.7199,
+      "step": 350
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 0.00013418063059897524,
+      "loss": 0.7229,
+      "step": 360
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 0.00012719599624113573,
+      "loss": 0.7189,
+      "step": 370
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 0.00012026163997705916,
+      "loss": 0.7147,
+      "step": 380
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 0.00011339285062260957,
+      "loss": 0.6928,
+      "step": 390
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 0.00010660477243222808,
+      "loss": 0.7002,
+      "step": 400
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 9.991237170899614e-05,
+      "loss": 0.7198,
+      "step": 410
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 9.33304038070446e-05,
+      "loss": 0.701,
+      "step": 420
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 8.68733805990611e-05,
+      "loss": 0.6928,
+      "step": 430
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 8.055553848062404e-05,
+      "loss": 0.696,
+      "step": 440
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 7.439080698190579e-05,
+      "loss": 0.7038,
+      "step": 450
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 6.839277805595081e-05,
+      "loss": 0.6949,
+      "step": 460
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 6.257467611124105e-05,
+      "loss": 0.7054,
+      "step": 470
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 5.6949328854621045e-05,
+      "loss": 0.7013,
+      "step": 480
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 5.152913900886729e-05,
+      "loss": 0.6976,
+      "step": 490
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 4.632605696725987e-05,
+      "loss": 0.6978,
+      "step": 500
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.13515544454462e-05,
+      "loss": 0.6964,
+      "step": 510
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.66165991886898e-05,
+      "loss": 0.7135,
+      "step": 520
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 3.2131630790269134e-05,
+      "loss": 0.7026,
+      "step": 530
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 2.790653767434181e-05,
+      "loss": 0.6986,
+      "step": 540
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 2.3950635294022347e-05,
+      "loss": 0.6809,
+      "step": 550
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 2.027264559274224e-05,
+      "loss": 0.6954,
+      "step": 560
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 1.6880677774175354e-05,
+      "loss": 0.7028,
+      "step": 570
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 1.3782210423127449e-05,
+      "loss": 0.6802,
+      "step": 580
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 1.0984075016809528e-05,
+      "loss": 0.6969,
+      "step": 590
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 8.492440862848787e-06,
+      "loss": 0.6995,
+      "step": 600
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.312801497246206e-06,
+      "loss": 0.6908,
+      "step": 610
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 4.44996257227021e-06,
+      "loss": 0.6933,
+      "step": 620
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.908031260991195e-06,
+      "loss": 0.6993,
+      "step": 630
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.6904072018175786e-06,
+      "loss": 0.6977,
+      "step": 640
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 7.997750029989647e-07,
+      "loss": 0.6936,
+      "step": 650
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 2.380983236223377e-07,
+      "loss": 0.6879,
+      "step": 660
+    },
+    {
+      "epoch": 1.0,
+      "step": 669,
+      "total_flos": 5.563883205708218e+18,
+      "train_loss": 0.7295773652993331,
+      "train_runtime": 13470.6062,
+      "train_samples_per_second": 6.356,
+      "train_steps_per_second": 0.05
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 669,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 1000,
+  "total_flos": 5.563883205708218e+18,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc87bbaa13f71825201a1de0cb24b5aa9e9629ec1fd59d0534029f20b9458d38
+size 5627