upload loras

llama2_13b_peft/tracking_shuffled_objects/README.md

@@ -0,0 +1,69 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: /data1/model/llama2/meta-llama/Llama2-13b
+model-index:
+- name: tracking_shuffled_objects_no_sys
+  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. -->
+
+# tracking_shuffled_objects_no_sys
+
+This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the tracking_shuffled_objects_no_sys dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3650
+
+## 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: 1e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 32
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.3492        | 2.5   | 200  | 0.3666          |
+| 0.3626        | 5.0   | 400  | 0.3644          |
+| 0.3471        | 7.5   | 600  | 0.3638          |
+| 0.3618        | 10.0  | 800  | 0.3650          |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.2.1
+- Datasets 2.18.0
+- Tokenizers 0.15.2

llama2_13b_peft/tracking_shuffled_objects/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
+  "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": [
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

llama2_13b_peft/tracking_shuffled_objects/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e571846c5465fea18bd6b37d18e92ef0832d8401ffc5d3d656d6325b5fcec9a
+size 125248064

llama2_13b_peft/tracking_shuffled_objects/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.3649631142616272,
+    "eval_runtime": 8.1913,
+    "eval_samples_per_second": 54.936,
+    "eval_steps_per_second": 1.831,
+    "train_loss": 0.5546135276556015,
+    "train_runtime": 1438.1753,
+    "train_samples_per_second": 17.731,
+    "train_steps_per_second": 0.556
+}

llama2_13b_peft/tracking_shuffled_objects/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "eval_loss": 0.3649631142616272,
+    "eval_runtime": 8.1913,
+    "eval_samples_per_second": 54.936,
+    "eval_steps_per_second": 1.831
+}

llama2_13b_peft/tracking_shuffled_objects/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
+  }
+}

llama2_13b_peft/tracking_shuffled_objects/tokenizer.model

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

llama2_13b_peft/tracking_shuffled_objects/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\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": false
+}

llama2_13b_peft/tracking_shuffled_objects/train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 10.0,
+    "train_loss": 0.5546135276556015,
+    "train_runtime": 1438.1753,
+    "train_samples_per_second": 17.731,
+    "train_steps_per_second": 0.556
+}

llama2_13b_peft/tracking_shuffled_objects/trainer_log.jsonl

@@ -0,0 +1,86 @@
+{"current_steps": 10, "total_steps": 800, "loss": 4.3605, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-06, "epoch": 0.12, "percentage": 1.25, "elapsed_time": "0:00:18", "remaining_time": "0:24:23"}
+{"current_steps": 20, "total_steps": 800, "loss": 4.372, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1e-05, "epoch": 0.25, "percentage": 2.5, "elapsed_time": "0:00:35", "remaining_time": "0:23:11"}
+{"current_steps": 30, "total_steps": 800, "loss": 4.0101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.995944990857848e-06, "epoch": 0.38, "percentage": 3.75, "elapsed_time": "0:00:52", "remaining_time": "0:22:38"}
+{"current_steps": 40, "total_steps": 800, "loss": 2.9176, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.983786540671052e-06, "epoch": 0.5, "percentage": 5.0, "elapsed_time": "0:01:10", "remaining_time": "0:22:18"}
+{"current_steps": 50, "total_steps": 800, "loss": 1.6643, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.96354437049027e-06, "epoch": 0.62, "percentage": 6.25, "elapsed_time": "0:01:27", "remaining_time": "0:21:54"}
+{"current_steps": 60, "total_steps": 800, "loss": 0.7889, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.935251313189564e-06, "epoch": 0.75, "percentage": 7.5, "elapsed_time": "0:01:44", "remaining_time": "0:21:32"}
+{"current_steps": 70, "total_steps": 800, "loss": 0.4779, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.89895326021134e-06, "epoch": 0.88, "percentage": 8.75, "elapsed_time": "0:02:02", "remaining_time": "0:21:17"}
+{"current_steps": 80, "total_steps": 800, "loss": 0.3952, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.854709087130261e-06, "epoch": 1.0, "percentage": 10.0, "elapsed_time": "0:02:19", "remaining_time": "0:20:59"}
+{"current_steps": 90, "total_steps": 800, "loss": 0.3717, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.802590558156863e-06, "epoch": 1.12, "percentage": 11.25, "elapsed_time": "0:02:37", "remaining_time": "0:20:41"}
+{"current_steps": 100, "total_steps": 800, "loss": 0.3616, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.742682209735727e-06, "epoch": 1.25, "percentage": 12.5, "elapsed_time": "0:02:55", "remaining_time": "0:20:25"}
+{"current_steps": 110, "total_steps": 800, "loss": 0.3795, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.675081213427076e-06, "epoch": 1.38, "percentage": 13.75, "elapsed_time": "0:03:12", "remaining_time": "0:20:06"}
+{"current_steps": 120, "total_steps": 800, "loss": 0.3667, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.599897218294122e-06, "epoch": 1.5, "percentage": 15.0, "elapsed_time": "0:03:29", "remaining_time": "0:19:49"}
+{"current_steps": 130, "total_steps": 800, "loss": 0.3716, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.517252173051912e-06, "epoch": 1.62, "percentage": 16.25, "elapsed_time": "0:03:47", "remaining_time": "0:19:32"}
+{"current_steps": 140, "total_steps": 800, "loss": 0.3572, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.427280128266049e-06, "epoch": 1.75, "percentage": 17.5, "elapsed_time": "0:04:05", "remaining_time": "0:19:15"}
+{"current_steps": 150, "total_steps": 800, "loss": 0.3568, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.330127018922195e-06, "epoch": 1.88, "percentage": 18.75, "elapsed_time": "0:04:22", "remaining_time": "0:18:58"}
+{"current_steps": 160, "total_steps": 800, "loss": 0.3597, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.225950427718974e-06, "epoch": 2.0, "percentage": 20.0, "elapsed_time": "0:04:40", "remaining_time": "0:18:41"}
+{"current_steps": 170, "total_steps": 800, "loss": 0.3586, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.114919329468283e-06, "epoch": 2.12, "percentage": 21.25, "elapsed_time": "0:04:57", "remaining_time": "0:18:23"}
+{"current_steps": 180, "total_steps": 800, "loss": 0.3536, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.997213817017508e-06, "epoch": 2.25, "percentage": 22.5, "elapsed_time": "0:05:15", "remaining_time": "0:18:06"}
+{"current_steps": 190, "total_steps": 800, "loss": 0.3501, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.873024809138272e-06, "epoch": 2.38, "percentage": 23.75, "elapsed_time": "0:05:33", "remaining_time": "0:17:49"}
+{"current_steps": 200, "total_steps": 800, "loss": 0.3492, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.742553740855507e-06, "epoch": 2.5, "percentage": 25.0, "elapsed_time": "0:05:50", "remaining_time": "0:17:31"}
+{"current_steps": 200, "total_steps": 800, "loss": null, "eval_loss": 0.3665711283683777, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.5, "percentage": 25.0, "elapsed_time": "0:05:50", "remaining_time": "0:17:31"}
+{"current_steps": 210, "total_steps": 800, "loss": 0.3462, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.606012236719073e-06, "epoch": 2.62, "percentage": 26.25, "elapsed_time": "0:06:16", "remaining_time": "0:17:37"}
+{"current_steps": 220, "total_steps": 800, "loss": 0.3805, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.463621767547998e-06, "epoch": 2.75, "percentage": 27.5, "elapsed_time": "0:06:33", "remaining_time": "0:17:17"}
+{"current_steps": 230, "total_steps": 800, "loss": 0.3636, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.315613291203977e-06, "epoch": 2.88, "percentage": 28.75, "elapsed_time": "0:06:51", "remaining_time": "0:16:59"}
+{"current_steps": 240, "total_steps": 800, "loss": 0.3528, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.162226877976886e-06, "epoch": 3.0, "percentage": 30.0, "elapsed_time": "0:07:09", "remaining_time": "0:16:41"}
+{"current_steps": 250, "total_steps": 800, "loss": 0.3543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.003711321189895e-06, "epoch": 3.12, "percentage": 31.25, "elapsed_time": "0:07:26", "remaining_time": "0:16:22"}
+{"current_steps": 260, "total_steps": 800, "loss": 0.3509, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.84032373365578e-06, "epoch": 3.25, "percentage": 32.5, "elapsed_time": "0:07:44", "remaining_time": "0:16:04"}
+{"current_steps": 270, "total_steps": 800, "loss": 0.3611, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.672329130639007e-06, "epoch": 3.38, "percentage": 33.75, "elapsed_time": "0:08:01", "remaining_time": "0:15:45"}
+{"current_steps": 280, "total_steps": 800, "loss": 0.3501, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.500000000000001e-06, "epoch": 3.5, "percentage": 35.0, "elapsed_time": "0:08:19", "remaining_time": "0:15:27"}
+{"current_steps": 290, "total_steps": 800, "loss": 0.3551, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.323615860218844e-06, "epoch": 3.62, "percentage": 36.25, "elapsed_time": "0:08:36", "remaining_time": "0:15:08"}
+{"current_steps": 300, "total_steps": 800, "loss": 0.3624, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.143462807015271e-06, "epoch": 3.75, "percentage": 37.5, "elapsed_time": "0:08:54", "remaining_time": "0:14:50"}
+{"current_steps": 310, "total_steps": 800, "loss": 0.3481, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.959833049300376e-06, "epoch": 3.88, "percentage": 38.75, "elapsed_time": "0:09:11", "remaining_time": "0:14:31"}
+{"current_steps": 320, "total_steps": 800, "loss": 0.3547, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.773024435212678e-06, "epoch": 4.0, "percentage": 40.0, "elapsed_time": "0:09:29", "remaining_time": "0:14:13"}
+{"current_steps": 330, "total_steps": 800, "loss": 0.3483, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.583339969007364e-06, "epoch": 4.12, "percentage": 41.25, "elapsed_time": "0:09:46", "remaining_time": "0:13:55"}
+{"current_steps": 340, "total_steps": 800, "loss": 0.3463, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.391087319582264e-06, "epoch": 4.25, "percentage": 42.5, "elapsed_time": "0:10:04", "remaining_time": "0:13:37"}
+{"current_steps": 350, "total_steps": 800, "loss": 0.3453, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.1965783214377895e-06, "epoch": 4.38, "percentage": 43.75, "elapsed_time": "0:10:21", "remaining_time": "0:13:19"}
+{"current_steps": 360, "total_steps": 800, "loss": 0.3473, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.000128468880223e-06, "epoch": 4.5, "percentage": 45.0, "elapsed_time": "0:10:39", "remaining_time": "0:13:01"}
+{"current_steps": 370, "total_steps": 800, "loss": 0.3585, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.8020564042888015e-06, "epoch": 4.62, "percentage": 46.25, "elapsed_time": "0:10:56", "remaining_time": "0:12:43"}
+{"current_steps": 380, "total_steps": 800, "loss": 0.3557, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.6026834012766155e-06, "epoch": 4.75, "percentage": 47.5, "elapsed_time": "0:11:13", "remaining_time": "0:12:24"}
+{"current_steps": 390, "total_steps": 800, "loss": 0.3526, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.402332843583631e-06, "epoch": 4.88, "percentage": 48.75, "elapsed_time": "0:11:31", "remaining_time": "0:12:06"}
+{"current_steps": 400, "total_steps": 800, "loss": 0.3626, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.201329700547077e-06, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:11:49", "remaining_time": "0:11:49"}
+{"current_steps": 400, "total_steps": 800, "loss": null, "eval_loss": 0.3643595278263092, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 5.0, "percentage": 50.0, "elapsed_time": "0:11:49", "remaining_time": "0:11:49"}
+{"current_steps": 410, "total_steps": 800, "loss": 0.345, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-06, "epoch": 5.12, "percentage": 51.25, "elapsed_time": "0:12:15", "remaining_time": "0:11:39"}
+{"current_steps": 420, "total_steps": 800, "loss": 0.3539, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.798670299452926e-06, "epoch": 5.25, "percentage": 52.5, "elapsed_time": "0:12:32", "remaining_time": "0:11:20"}
+{"current_steps": 430, "total_steps": 800, "loss": 0.3505, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.597667156416371e-06, "epoch": 5.38, "percentage": 53.75, "elapsed_time": "0:12:49", "remaining_time": "0:11:02"}
+{"current_steps": 440, "total_steps": 800, "loss": 0.3558, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.397316598723385e-06, "epoch": 5.5, "percentage": 55.0, "elapsed_time": "0:13:07", "remaining_time": "0:10:44"}
+{"current_steps": 450, "total_steps": 800, "loss": 0.3609, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1979435957111984e-06, "epoch": 5.62, "percentage": 56.25, "elapsed_time": "0:13:24", "remaining_time": "0:10:26"}
+{"current_steps": 460, "total_steps": 800, "loss": 0.3488, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.999871531119779e-06, "epoch": 5.75, "percentage": 57.5, "elapsed_time": "0:13:42", "remaining_time": "0:10:07"}
+{"current_steps": 470, "total_steps": 800, "loss": 0.3484, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.803421678562213e-06, "epoch": 5.88, "percentage": 58.75, "elapsed_time": "0:13:59", "remaining_time": "0:09:49"}
+{"current_steps": 480, "total_steps": 800, "loss": 0.3392, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.6089126804177373e-06, "epoch": 6.0, "percentage": 60.0, "elapsed_time": "0:14:17", "remaining_time": "0:09:31"}
+{"current_steps": 490, "total_steps": 800, "loss": 0.355, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.416660030992639e-06, "epoch": 6.12, "percentage": 61.25, "elapsed_time": "0:14:34", "remaining_time": "0:09:13"}
+{"current_steps": 500, "total_steps": 800, "loss": 0.3463, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.226975564787322e-06, "epoch": 6.25, "percentage": 62.5, "elapsed_time": "0:14:52", "remaining_time": "0:08:55"}
+{"current_steps": 510, "total_steps": 800, "loss": 0.3423, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.040166950699626e-06, "epoch": 6.38, "percentage": 63.75, "elapsed_time": "0:15:09", "remaining_time": "0:08:37"}
+{"current_steps": 520, "total_steps": 800, "loss": 0.3461, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8565371929847286e-06, "epoch": 6.5, "percentage": 65.0, "elapsed_time": "0:15:27", "remaining_time": "0:08:19"}
+{"current_steps": 530, "total_steps": 800, "loss": 0.3496, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6763841397811576e-06, "epoch": 6.62, "percentage": 66.25, "elapsed_time": "0:15:44", "remaining_time": "0:08:01"}
+{"current_steps": 540, "total_steps": 800, "loss": 0.3491, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5000000000000015e-06, "epoch": 6.75, "percentage": 67.5, "elapsed_time": "0:16:02", "remaining_time": "0:07:43"}
+{"current_steps": 550, "total_steps": 800, "loss": 0.3576, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3276708693609947e-06, "epoch": 6.88, "percentage": 68.75, "elapsed_time": "0:16:19", "remaining_time": "0:07:25"}
+{"current_steps": 560, "total_steps": 800, "loss": 0.3498, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.159676266344222e-06, "epoch": 7.0, "percentage": 70.0, "elapsed_time": "0:16:37", "remaining_time": "0:07:07"}
+{"current_steps": 570, "total_steps": 800, "loss": 0.3491, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.996288678810105e-06, "epoch": 7.12, "percentage": 71.25, "elapsed_time": "0:16:55", "remaining_time": "0:06:49"}
+{"current_steps": 580, "total_steps": 800, "loss": 0.3481, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8377731220231144e-06, "epoch": 7.25, "percentage": 72.5, "elapsed_time": "0:17:12", "remaining_time": "0:06:31"}
+{"current_steps": 590, "total_steps": 800, "loss": 0.3573, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6843867087960252e-06, "epoch": 7.38, "percentage": 73.75, "elapsed_time": "0:17:29", "remaining_time": "0:06:13"}
+{"current_steps": 600, "total_steps": 800, "loss": 0.3471, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5363782324520033e-06, "epoch": 7.5, "percentage": 75.0, "elapsed_time": "0:17:47", "remaining_time": "0:05:55"}
+{"current_steps": 600, "total_steps": 800, "loss": null, "eval_loss": 0.3637930452823639, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 7.5, "percentage": 75.0, "elapsed_time": "0:17:47", "remaining_time": "0:05:55"}
+{"current_steps": 610, "total_steps": 800, "loss": 0.3339, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3939877632809279e-06, "epoch": 7.62, "percentage": 76.25, "elapsed_time": "0:18:13", "remaining_time": "0:05:40"}
+{"current_steps": 620, "total_steps": 800, "loss": 0.3583, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.257446259144494e-06, "epoch": 7.75, "percentage": 77.5, "elapsed_time": "0:18:30", "remaining_time": "0:05:22"}
+{"current_steps": 630, "total_steps": 800, "loss": 0.3528, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1269751908617277e-06, "epoch": 7.88, "percentage": 78.75, "elapsed_time": "0:18:48", "remaining_time": "0:05:04"}
+{"current_steps": 640, "total_steps": 800, "loss": 0.3415, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0027861829824953e-06, "epoch": 8.0, "percentage": 80.0, "elapsed_time": "0:19:05", "remaining_time": "0:04:46"}
+{"current_steps": 650, "total_steps": 800, "loss": 0.3465, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.850806705317183e-07, "epoch": 8.12, "percentage": 81.25, "elapsed_time": "0:19:23", "remaining_time": "0:04:28"}
+{"current_steps": 660, "total_steps": 800, "loss": 0.35, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.740495722810271e-07, "epoch": 8.25, "percentage": 82.5, "elapsed_time": "0:19:41", "remaining_time": "0:04:10"}
+{"current_steps": 670, "total_steps": 800, "loss": 0.3725, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.698729810778065e-07, "epoch": 8.38, "percentage": 83.75, "elapsed_time": "0:19:58", "remaining_time": "0:03:52"}
+{"current_steps": 680, "total_steps": 800, "loss": 0.3434, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.727198717339511e-07, "epoch": 8.5, "percentage": 85.0, "elapsed_time": "0:20:16", "remaining_time": "0:03:34"}
+{"current_steps": 690, "total_steps": 800, "loss": 0.3431, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.827478269480895e-07, "epoch": 8.62, "percentage": 86.25, "elapsed_time": "0:20:33", "remaining_time": "0:03:16"}
+{"current_steps": 700, "total_steps": 800, "loss": 0.3382, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.001027817058789e-07, "epoch": 8.75, "percentage": 87.5, "elapsed_time": "0:20:51", "remaining_time": "0:02:58"}
+{"current_steps": 710, "total_steps": 800, "loss": 0.3536, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2491878657292643e-07, "epoch": 8.88, "percentage": 88.75, "elapsed_time": "0:21:08", "remaining_time": "0:02:40"}
+{"current_steps": 720, "total_steps": 800, "loss": 0.3364, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.573177902642726e-07, "epoch": 9.0, "percentage": 90.0, "elapsed_time": "0:21:26", "remaining_time": "0:02:22"}
+{"current_steps": 730, "total_steps": 800, "loss": 0.3477, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9740944184313882e-07, "epoch": 9.12, "percentage": 91.25, "elapsed_time": "0:21:43", "remaining_time": "0:02:05"}
+{"current_steps": 740, "total_steps": 800, "loss": 0.3449, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4529091286973994e-07, "epoch": 9.25, "percentage": 92.5, "elapsed_time": "0:22:01", "remaining_time": "0:01:47"}
+{"current_steps": 750, "total_steps": 800, "loss": 0.3545, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0104673978866164e-07, "epoch": 9.38, "percentage": 93.75, "elapsed_time": "0:22:18", "remaining_time": "0:01:29"}
+{"current_steps": 760, "total_steps": 800, "loss": 0.3375, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.474868681043578e-08, "epoch": 9.5, "percentage": 95.0, "elapsed_time": "0:22:35", "remaining_time": "0:01:11"}
+{"current_steps": 770, "total_steps": 800, "loss": 0.3447, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.645562950973014e-08, "epoch": 9.62, "percentage": 96.25, "elapsed_time": "0:22:53", "remaining_time": "0:00:53"}
+{"current_steps": 780, "total_steps": 800, "loss": 0.3467, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6213459328950355e-08, "epoch": 9.75, "percentage": 97.5, "elapsed_time": "0:23:10", "remaining_time": "0:00:35"}
+{"current_steps": 790, "total_steps": 800, "loss": 0.342, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.055009142152066e-09, "epoch": 9.88, "percentage": 98.75, "elapsed_time": "0:23:28", "remaining_time": "0:00:17"}
+{"current_steps": 800, "total_steps": 800, "loss": 0.3618, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:23:45", "remaining_time": "0:00:00"}
+{"current_steps": 800, "total_steps": 800, "loss": null, "eval_loss": 0.3649631142616272, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:23:45", "remaining_time": "0:00:00"}
+{"current_steps": 800, "total_steps": 800, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:23:45", "remaining_time": "0:00:00"}
+{"current_steps": 15, "total_steps": 15, "loss": null, "eval_loss": 0.3649631142616272, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 10.0, "percentage": 100.0, "elapsed_time": "0:24:02", "remaining_time": "0:00:00"}

llama2_13b_peft/tracking_shuffled_objects/trainer_state.json

@@ -0,0 +1,622 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 200,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.8619604110717773,
+      "learning_rate": 5e-06,
+      "loss": 4.3605,
+      "step": 10
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 3.857790946960449,
+      "learning_rate": 1e-05,
+      "loss": 4.372,
+      "step": 20
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 5.3878560066223145,
+      "learning_rate": 9.995944990857848e-06,
+      "loss": 4.0101,
+      "step": 30
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 5.896845817565918,
+      "learning_rate": 9.983786540671052e-06,
+      "loss": 2.9176,
+      "step": 40
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 3.613201379776001,
+      "learning_rate": 9.96354437049027e-06,
+      "loss": 1.6643,
+      "step": 50
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 1.5779223442077637,
+      "learning_rate": 9.935251313189564e-06,
+      "loss": 0.7889,
+      "step": 60
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 0.8221031427383423,
+      "learning_rate": 9.89895326021134e-06,
+      "loss": 0.4779,
+      "step": 70
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.5207726955413818,
+      "learning_rate": 9.854709087130261e-06,
+      "loss": 0.3952,
+      "step": 80
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.5719926953315735,
+      "learning_rate": 9.802590558156863e-06,
+      "loss": 0.3717,
+      "step": 90
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.8804627656936646,
+      "learning_rate": 9.742682209735727e-06,
+      "loss": 0.3616,
+      "step": 100
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.4614345133304596,
+      "learning_rate": 9.675081213427076e-06,
+      "loss": 0.3795,
+      "step": 110
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.5621177554130554,
+      "learning_rate": 9.599897218294122e-06,
+      "loss": 0.3667,
+      "step": 120
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.547697901725769,
+      "learning_rate": 9.517252173051912e-06,
+      "loss": 0.3716,
+      "step": 130
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.5013922452926636,
+      "learning_rate": 9.427280128266049e-06,
+      "loss": 0.3572,
+      "step": 140
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 0.4131128489971161,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.3568,
+      "step": 150
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7218930125236511,
+      "learning_rate": 9.225950427718974e-06,
+      "loss": 0.3597,
+      "step": 160
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.5658674240112305,
+      "learning_rate": 9.114919329468283e-06,
+      "loss": 0.3586,
+      "step": 170
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.37311697006225586,
+      "learning_rate": 8.997213817017508e-06,
+      "loss": 0.3536,
+      "step": 180
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.5113855004310608,
+      "learning_rate": 8.873024809138272e-06,
+      "loss": 0.3501,
+      "step": 190
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.5142890810966492,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.3492,
+      "step": 200
+    },
+    {
+      "epoch": 2.5,
+      "eval_loss": 0.3665711283683777,
+      "eval_runtime": 8.1974,
+      "eval_samples_per_second": 54.896,
+      "eval_steps_per_second": 1.83,
+      "step": 200
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.35885754227638245,
+      "learning_rate": 8.606012236719073e-06,
+      "loss": 0.3462,
+      "step": 210
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.5794305801391602,
+      "learning_rate": 8.463621767547998e-06,
+      "loss": 0.3805,
+      "step": 220
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.5061661005020142,
+      "learning_rate": 8.315613291203977e-06,
+      "loss": 0.3636,
+      "step": 230
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.4418283700942993,
+      "learning_rate": 8.162226877976886e-06,
+      "loss": 0.3528,
+      "step": 240
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 0.47025126218795776,
+      "learning_rate": 8.003711321189895e-06,
+      "loss": 0.3543,
+      "step": 250
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.39721566438674927,
+      "learning_rate": 7.84032373365578e-06,
+      "loss": 0.3509,
+      "step": 260
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 0.5492234230041504,
+      "learning_rate": 7.672329130639007e-06,
+      "loss": 0.3611,
+      "step": 270
+    },
+    {
+      "epoch": 3.5,
+      "grad_norm": 0.4932497441768646,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.3501,
+      "step": 280
+    },
+    {
+      "epoch": 3.62,
+      "grad_norm": 0.5507996082305908,
+      "learning_rate": 7.323615860218844e-06,
+      "loss": 0.3551,
+      "step": 290
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.5754275321960449,
+      "learning_rate": 7.143462807015271e-06,
+      "loss": 0.3624,
+      "step": 300
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 0.518661618232727,
+      "learning_rate": 6.959833049300376e-06,
+      "loss": 0.3481,
+      "step": 310
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.5419223308563232,
+      "learning_rate": 6.773024435212678e-06,
+      "loss": 0.3547,
+      "step": 320
+    },
+    {
+      "epoch": 4.12,
+      "grad_norm": 0.4590226709842682,
+      "learning_rate": 6.583339969007364e-06,
+      "loss": 0.3483,
+      "step": 330
+    },
+    {
+      "epoch": 4.25,
+      "grad_norm": 0.6402090787887573,
+      "learning_rate": 6.391087319582264e-06,
+      "loss": 0.3463,
+      "step": 340
+    },
+    {
+      "epoch": 4.38,
+      "grad_norm": 0.4070948362350464,
+      "learning_rate": 6.1965783214377895e-06,
+      "loss": 0.3453,
+      "step": 350
+    },
+    {
+      "epoch": 4.5,
+      "grad_norm": 0.4342328608036041,
+      "learning_rate": 6.000128468880223e-06,
+      "loss": 0.3473,
+      "step": 360
+    },
+    {
+      "epoch": 4.62,
+      "grad_norm": 0.42583146691322327,
+      "learning_rate": 5.8020564042888015e-06,
+      "loss": 0.3585,
+      "step": 370
+    },
+    {
+      "epoch": 4.75,
+      "grad_norm": 0.5823317170143127,
+      "learning_rate": 5.6026834012766155e-06,
+      "loss": 0.3557,
+      "step": 380
+    },
+    {
+      "epoch": 4.88,
+      "grad_norm": 0.5292758941650391,
+      "learning_rate": 5.402332843583631e-06,
+      "loss": 0.3526,
+      "step": 390
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.44697287678718567,
+      "learning_rate": 5.201329700547077e-06,
+      "loss": 0.3626,
+      "step": 400
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.3643595278263092,
+      "eval_runtime": 8.1855,
+      "eval_samples_per_second": 54.975,
+      "eval_steps_per_second": 1.833,
+      "step": 400
+    },
+    {
+      "epoch": 5.12,
+      "grad_norm": 0.44350212812423706,
+      "learning_rate": 5e-06,
+      "loss": 0.345,
+      "step": 410
+    },
+    {
+      "epoch": 5.25,
+      "grad_norm": 0.5301347970962524,
+      "learning_rate": 4.798670299452926e-06,
+      "loss": 0.3539,
+      "step": 420
+    },
+    {
+      "epoch": 5.38,
+      "grad_norm": 0.5110909938812256,
+      "learning_rate": 4.597667156416371e-06,
+      "loss": 0.3505,
+      "step": 430
+    },
+    {
+      "epoch": 5.5,
+      "grad_norm": 0.5509496331214905,
+      "learning_rate": 4.397316598723385e-06,
+      "loss": 0.3558,
+      "step": 440
+    },
+    {
+      "epoch": 5.62,
+      "grad_norm": 0.6367918252944946,
+      "learning_rate": 4.1979435957111984e-06,
+      "loss": 0.3609,
+      "step": 450
+    },
+    {
+      "epoch": 5.75,
+      "grad_norm": 0.5148094296455383,
+      "learning_rate": 3.999871531119779e-06,
+      "loss": 0.3488,
+      "step": 460
+    },
+    {
+      "epoch": 5.88,
+      "grad_norm": 0.634175717830658,
+      "learning_rate": 3.803421678562213e-06,
+      "loss": 0.3484,
+      "step": 470
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.4973353147506714,
+      "learning_rate": 3.6089126804177373e-06,
+      "loss": 0.3392,
+      "step": 480
+    },
+    {
+      "epoch": 6.12,
+      "grad_norm": 0.6146537661552429,
+      "learning_rate": 3.416660030992639e-06,
+      "loss": 0.355,
+      "step": 490
+    },
+    {
+      "epoch": 6.25,
+      "grad_norm": 0.47262611985206604,
+      "learning_rate": 3.226975564787322e-06,
+      "loss": 0.3463,
+      "step": 500
+    },
+    {
+      "epoch": 6.38,
+      "grad_norm": 0.5029013752937317,
+      "learning_rate": 3.040166950699626e-06,
+      "loss": 0.3423,
+      "step": 510
+    },
+    {
+      "epoch": 6.5,
+      "grad_norm": 0.5331050753593445,
+      "learning_rate": 2.8565371929847286e-06,
+      "loss": 0.3461,
+      "step": 520
+    },
+    {
+      "epoch": 6.62,
+      "grad_norm": 0.5478771924972534,
+      "learning_rate": 2.6763841397811576e-06,
+      "loss": 0.3496,
+      "step": 530
+    },
+    {
+      "epoch": 6.75,
+      "grad_norm": 0.4656558632850647,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.3491,
+      "step": 540
+    },
+    {
+      "epoch": 6.88,
+      "grad_norm": 0.6048917174339294,
+      "learning_rate": 2.3276708693609947e-06,
+      "loss": 0.3576,
+      "step": 550
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.46934497356414795,
+      "learning_rate": 2.159676266344222e-06,
+      "loss": 0.3498,
+      "step": 560
+    },
+    {
+      "epoch": 7.12,
+      "grad_norm": 0.4495680034160614,
+      "learning_rate": 1.996288678810105e-06,
+      "loss": 0.3491,
+      "step": 570
+    },
+    {
+      "epoch": 7.25,
+      "grad_norm": 0.4595155715942383,
+      "learning_rate": 1.8377731220231144e-06,
+      "loss": 0.3481,
+      "step": 580
+    },
+    {
+      "epoch": 7.38,
+      "grad_norm": 0.5048754811286926,
+      "learning_rate": 1.6843867087960252e-06,
+      "loss": 0.3573,
+      "step": 590
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.5682963728904724,
+      "learning_rate": 1.5363782324520033e-06,
+      "loss": 0.3471,
+      "step": 600
+    },
+    {
+      "epoch": 7.5,
+      "eval_loss": 0.3637930452823639,
+      "eval_runtime": 8.1841,
+      "eval_samples_per_second": 54.985,
+      "eval_steps_per_second": 1.833,
+      "step": 600
+    },
+    {
+      "epoch": 7.62,
+      "grad_norm": 0.6272332072257996,
+      "learning_rate": 1.3939877632809279e-06,
+      "loss": 0.3339,
+      "step": 610
+    },
+    {
+      "epoch": 7.75,
+      "grad_norm": 0.5155446529388428,
+      "learning_rate": 1.257446259144494e-06,
+      "loss": 0.3583,
+      "step": 620
+    },
+    {
+      "epoch": 7.88,
+      "grad_norm": 0.546676516532898,
+      "learning_rate": 1.1269751908617277e-06,
+      "loss": 0.3528,
+      "step": 630
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.4784735143184662,
+      "learning_rate": 1.0027861829824953e-06,
+      "loss": 0.3415,
+      "step": 640
+    },
+    {
+      "epoch": 8.12,
+      "grad_norm": 0.5068591833114624,
+      "learning_rate": 8.850806705317183e-07,
+      "loss": 0.3465,
+      "step": 650
+    },
+    {
+      "epoch": 8.25,
+      "grad_norm": 0.5461397767066956,
+      "learning_rate": 7.740495722810271e-07,
+      "loss": 0.35,
+      "step": 660
+    },
+    {
+      "epoch": 8.38,
+      "grad_norm": 0.4632417857646942,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.3725,
+      "step": 670
+    },
+    {
+      "epoch": 8.5,
+      "grad_norm": 0.44176045060157776,
+      "learning_rate": 5.727198717339511e-07,
+      "loss": 0.3434,
+      "step": 680
+    },
+    {
+      "epoch": 8.62,
+      "grad_norm": 0.46392500400543213,
+      "learning_rate": 4.827478269480895e-07,
+      "loss": 0.3431,
+      "step": 690
+    },
+    {
+      "epoch": 8.75,
+      "grad_norm": 0.4535755515098572,
+      "learning_rate": 4.001027817058789e-07,
+      "loss": 0.3382,
+      "step": 700
+    },
+    {
+      "epoch": 8.88,
+      "grad_norm": 0.4244369566440582,
+      "learning_rate": 3.2491878657292643e-07,
+      "loss": 0.3536,
+      "step": 710
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.553550124168396,
+      "learning_rate": 2.573177902642726e-07,
+      "loss": 0.3364,
+      "step": 720
+    },
+    {
+      "epoch": 9.12,
+      "grad_norm": 0.5430624485015869,
+      "learning_rate": 1.9740944184313882e-07,
+      "loss": 0.3477,
+      "step": 730
+    },
+    {
+      "epoch": 9.25,
+      "grad_norm": 0.5077548623085022,
+      "learning_rate": 1.4529091286973994e-07,
+      "loss": 0.3449,
+      "step": 740
+    },
+    {
+      "epoch": 9.38,
+      "grad_norm": 0.53578120470047,
+      "learning_rate": 1.0104673978866164e-07,
+      "loss": 0.3545,
+      "step": 750
+    },
+    {
+      "epoch": 9.5,
+      "grad_norm": 0.4798441231250763,
+      "learning_rate": 6.474868681043578e-08,
+      "loss": 0.3375,
+      "step": 760
+    },
+    {
+      "epoch": 9.62,
+      "grad_norm": 0.5828143954277039,
+      "learning_rate": 3.645562950973014e-08,
+      "loss": 0.3447,
+      "step": 770
+    },
+    {
+      "epoch": 9.75,
+      "grad_norm": 0.4779021143913269,
+      "learning_rate": 1.6213459328950355e-08,
+      "loss": 0.3467,
+      "step": 780
+    },
+    {
+      "epoch": 9.88,
+      "grad_norm": 0.5191458463668823,
+      "learning_rate": 4.055009142152066e-09,
+      "loss": 0.342,
+      "step": 790
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.5676460862159729,
+      "learning_rate": 0.0,
+      "loss": 0.3618,
+      "step": 800
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 0.3649631142616272,
+      "eval_runtime": 8.1948,
+      "eval_samples_per_second": 54.913,
+      "eval_steps_per_second": 1.83,
+      "step": 800
+    },
+    {
+      "epoch": 10.0,
+      "step": 800,
+      "total_flos": 5.3765115830756966e+17,
+      "train_loss": 0.5546135276556015,
+      "train_runtime": 1438.1753,
+      "train_samples_per_second": 17.731,
+      "train_steps_per_second": 0.556
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 800,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 1000,
+  "total_flos": 5.3765115830756966e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_13b_peft/tracking_shuffled_objects/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4096e9077e2ad41046184b829d1a95f558bc234f6d09fd3080a9de371fda1b04
+size 5112

llama2_13b_peft/vitaminc_fact_verification/README.md

@@ -0,0 +1,78 @@
+---
+license: other
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: /data1/model/llama2/meta-llama/Llama2-13b
+model-index:
+- name: vitaminc_fact_verification_no_sys
+  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. -->
+
+# vitaminc_fact_verification_no_sys
+
+This model is a fine-tuned version of [/data1/model/llama2/meta-llama/Llama2-13b](https://huggingface.co//data1/model/llama2/meta-llama/Llama2-13b) on the vitaminc_fact_verification_no_sys dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.1413
+
+## 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: 0.0001
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 3
+- total_train_batch_size: 24
+- total_eval_batch_size: 24
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 20
+- num_epochs: 10.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.4369        | 0.03  | 50   | 0.3792          |
+| 0.2145        | 0.06  | 100  | 0.2272          |
+| 0.2037        | 0.1   | 150  | 0.1837          |
+| 0.1913        | 0.13  | 200  | 0.2707          |
+| 0.1781        | 0.16  | 250  | 0.1783          |
+| 0.2087        | 0.19  | 300  | 0.2067          |
+| 0.2029        | 0.23  | 350  | 0.1516          |
+| 0.1081        | 0.26  | 400  | 0.1555          |
+| 0.1619        | 0.29  | 450  | 0.1446          |
+| 0.111         | 0.32  | 500  | 0.1413          |
+| 0.1546        | 0.36  | 550  | 0.1476          |
+| 0.14          | 0.39  | 600  | 0.1437          |
+| 0.1082        | 0.42  | 650  | 0.1483          |
+
+
+### Framework versions
+
+- PEFT 0.9.0
+- Transformers 4.38.2
+- Pytorch 2.2.1
+- Datasets 2.18.0
+- Tokenizers 0.15.2

llama2_13b_peft/vitaminc_fact_verification/adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "/data1/model/llama2/meta-llama/Llama2-13b",
+  "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",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

llama2_13b_peft/vitaminc_fact_verification/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e8501f5bcb7191ccc6be34271e2cc59743375b55859db909aa1224980444dc23
+size 125248064

llama2_13b_peft/vitaminc_fact_verification/all_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 0.42,
+    "eval_loss": 0.1412981152534485,
+    "eval_runtime": 63.9749,
+    "eval_samples_per_second": 102.556,
+    "eval_steps_per_second": 4.283,
+    "train_loss": 0.3310180792441735,
+    "train_runtime": 1340.7166,
+    "train_samples_per_second": 277.27,
+    "train_steps_per_second": 11.554
+}

llama2_13b_peft/vitaminc_fact_verification/eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.42,
+    "eval_loss": 0.1412981152534485,
+    "eval_runtime": 63.9749,
+    "eval_samples_per_second": 102.556,
+    "eval_steps_per_second": 4.283
+}

llama2_13b_peft/vitaminc_fact_verification/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
+  }
+}

llama2_13b_peft/vitaminc_fact_verification/tokenizer.model

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

llama2_13b_peft/vitaminc_fact_verification/tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ content }}{% elif message['role'] == 'assistant' %}{{ content + '\\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": false
+}

llama2_13b_peft/vitaminc_fact_verification/train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 0.42,
+    "train_loss": 0.3310180792441735,
+    "train_runtime": 1340.7166,
+    "train_samples_per_second": 277.27,
+    "train_steps_per_second": 11.554
+}

llama2_13b_peft/vitaminc_fact_verification/trainer_log.jsonl

@@ -0,0 +1,80 @@
+{"current_steps": 10, "total_steps": 15490, "loss": 7.5989, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 0.01, "percentage": 0.06, "elapsed_time": "0:00:09", "remaining_time": "3:56:43"}
+{"current_steps": 20, "total_steps": 15490, "loss": 1.8506, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 0.0001, "epoch": 0.01, "percentage": 0.13, "elapsed_time": "0:00:16", "remaining_time": "3:35:58"}
+{"current_steps": 30, "total_steps": 15490, "loss": 0.5371, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99998968999259e-05, "epoch": 0.02, "percentage": 0.19, "elapsed_time": "0:00:24", "remaining_time": "3:33:50"}
+{"current_steps": 40, "total_steps": 15490, "loss": 0.4742, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99995876001288e-05, "epoch": 0.03, "percentage": 0.26, "elapsed_time": "0:00:32", "remaining_time": "3:28:00"}
+{"current_steps": 50, "total_steps": 15490, "loss": 0.4369, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999907210188424e-05, "epoch": 0.03, "percentage": 0.32, "elapsed_time": "0:00:40", "remaining_time": "3:26:14"}
+{"current_steps": 50, "total_steps": 15490, "loss": null, "eval_loss": 0.3792226016521454, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.03, "percentage": 0.32, "elapsed_time": "0:00:40", "remaining_time": "3:26:14"}
+{"current_steps": 60, "total_steps": 15490, "loss": 0.3655, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999835040731813e-05, "epoch": 0.04, "percentage": 0.39, "elapsed_time": "0:01:51", "remaining_time": "7:58:48"}
+{"current_steps": 70, "total_steps": 15490, "loss": 0.2957, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999742251940676e-05, "epoch": 0.05, "percentage": 0.45, "elapsed_time": "0:01:59", "remaining_time": "7:18:24"}
+{"current_steps": 80, "total_steps": 15490, "loss": 0.3023, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999628844197672e-05, "epoch": 0.05, "percentage": 0.52, "elapsed_time": "0:02:06", "remaining_time": "6:46:12"}
+{"current_steps": 90, "total_steps": 15490, "loss": 0.2589, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999494817970498e-05, "epoch": 0.06, "percentage": 0.58, "elapsed_time": "0:02:14", "remaining_time": "6:22:25"}
+{"current_steps": 100, "total_steps": 15490, "loss": 0.2145, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999340173811875e-05, "epoch": 0.06, "percentage": 0.65, "elapsed_time": "0:02:21", "remaining_time": "6:03:03"}
+{"current_steps": 100, "total_steps": 15490, "loss": null, "eval_loss": 0.22720637917518616, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.06, "percentage": 0.65, "elapsed_time": "0:02:21", "remaining_time": "6:03:03"}
+{"current_steps": 110, "total_steps": 15490, "loss": 0.2288, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.999164912359557e-05, "epoch": 0.07, "percentage": 0.71, "elapsed_time": "0:03:33", "remaining_time": "8:17:20"}
+{"current_steps": 120, "total_steps": 15490, "loss": 0.2672, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.998969034336327e-05, "epoch": 0.08, "percentage": 0.77, "elapsed_time": "0:03:41", "remaining_time": "7:51:56"}
+{"current_steps": 130, "total_steps": 15490, "loss": 0.2312, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99875254054998e-05, "epoch": 0.08, "percentage": 0.84, "elapsed_time": "0:03:49", "remaining_time": "7:32:41"}
+{"current_steps": 140, "total_steps": 15490, "loss": 0.1959, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.99851543189334e-05, "epoch": 0.09, "percentage": 0.9, "elapsed_time": "0:03:57", "remaining_time": "7:13:49"}
+{"current_steps": 150, "total_steps": 15490, "loss": 0.2037, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.998257709344246e-05, "epoch": 0.1, "percentage": 0.97, "elapsed_time": "0:04:05", "remaining_time": "6:57:47"}
+{"current_steps": 150, "total_steps": 15490, "loss": null, "eval_loss": 0.1836628019809723, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.1, "percentage": 0.97, "elapsed_time": "0:04:05", "remaining_time": "6:57:47"}
+{"current_steps": 160, "total_steps": 15490, "loss": 0.2029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.997979373965541e-05, "epoch": 0.1, "percentage": 1.03, "elapsed_time": "0:05:16", "remaining_time": "8:25:22"}
+{"current_steps": 170, "total_steps": 15490, "loss": 0.1685, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.997680426905086e-05, "epoch": 0.11, "percentage": 1.1, "elapsed_time": "0:05:23", "remaining_time": "8:06:23"}
+{"current_steps": 180, "total_steps": 15490, "loss": 0.2626, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.997360869395738e-05, "epoch": 0.12, "percentage": 1.16, "elapsed_time": "0:05:31", "remaining_time": "7:50:28"}
+{"current_steps": 190, "total_steps": 15490, "loss": 0.2029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.997020702755353e-05, "epoch": 0.12, "percentage": 1.23, "elapsed_time": "0:05:40", "remaining_time": "7:37:25"}
+{"current_steps": 200, "total_steps": 15490, "loss": 0.1913, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.996659928386778e-05, "epoch": 0.13, "percentage": 1.29, "elapsed_time": "0:05:49", "remaining_time": "7:24:58"}
+{"current_steps": 200, "total_steps": 15490, "loss": null, "eval_loss": 0.27072426676750183, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.13, "percentage": 1.29, "elapsed_time": "0:05:49", "remaining_time": "7:24:58"}
+{"current_steps": 210, "total_steps": 15490, "loss": 0.225, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.996278547777851e-05, "epoch": 0.14, "percentage": 1.36, "elapsed_time": "0:07:00", "remaining_time": "8:30:31"}
+{"current_steps": 220, "total_steps": 15490, "loss": 0.2244, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.995876562501383e-05, "epoch": 0.14, "percentage": 1.42, "elapsed_time": "0:07:08", "remaining_time": "8:15:39"}
+{"current_steps": 230, "total_steps": 15490, "loss": 0.1903, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.995453974215163e-05, "epoch": 0.15, "percentage": 1.48, "elapsed_time": "0:07:16", "remaining_time": "8:02:35"}
+{"current_steps": 240, "total_steps": 15490, "loss": 0.1813, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.995010784661948e-05, "epoch": 0.15, "percentage": 1.55, "elapsed_time": "0:07:25", "remaining_time": "7:51:39"}
+{"current_steps": 250, "total_steps": 15490, "loss": 0.1781, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.994546995669454e-05, "epoch": 0.16, "percentage": 1.61, "elapsed_time": "0:07:33", "remaining_time": "7:40:25"}
+{"current_steps": 250, "total_steps": 15490, "loss": null, "eval_loss": 0.17831701040267944, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.16, "percentage": 1.61, "elapsed_time": "0:07:33", "remaining_time": "7:40:25"}
+{"current_steps": 260, "total_steps": 15490, "loss": 0.194, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.994062609150345e-05, "epoch": 0.17, "percentage": 1.68, "elapsed_time": "0:08:45", "remaining_time": "8:32:51"}
+{"current_steps": 270, "total_steps": 15490, "loss": 0.2086, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.993557627102234e-05, "epoch": 0.17, "percentage": 1.74, "elapsed_time": "0:08:52", "remaining_time": "8:20:21"}
+{"current_steps": 280, "total_steps": 15490, "loss": 0.1526, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.993032051607669e-05, "epoch": 0.18, "percentage": 1.81, "elapsed_time": "0:09:00", "remaining_time": "8:09:02"}
+{"current_steps": 290, "total_steps": 15490, "loss": 0.1478, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.992485884834124e-05, "epoch": 0.19, "percentage": 1.87, "elapsed_time": "0:09:07", "remaining_time": "7:58:21"}
+{"current_steps": 300, "total_steps": 15490, "loss": 0.2087, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.991919129033994e-05, "epoch": 0.19, "percentage": 1.94, "elapsed_time": "0:09:15", "remaining_time": "7:48:26"}
+{"current_steps": 300, "total_steps": 15490, "loss": null, "eval_loss": 0.2066759169101715, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.19, "percentage": 1.94, "elapsed_time": "0:09:15", "remaining_time": "7:48:26"}
+{"current_steps": 310, "total_steps": 15490, "loss": 0.1824, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.991331786544577e-05, "epoch": 0.2, "percentage": 2.0, "elapsed_time": "0:10:27", "remaining_time": "8:31:43"}
+{"current_steps": 320, "total_steps": 15490, "loss": 0.1129, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.990723859788081e-05, "epoch": 0.21, "percentage": 2.07, "elapsed_time": "0:10:35", "remaining_time": "8:22:03"}
+{"current_steps": 330, "total_steps": 15490, "loss": 0.1886, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.990095351271594e-05, "epoch": 0.21, "percentage": 2.13, "elapsed_time": "0:10:43", "remaining_time": "8:12:22"}
+{"current_steps": 340, "total_steps": 15490, "loss": 0.1969, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.98944626358709e-05, "epoch": 0.22, "percentage": 2.19, "elapsed_time": "0:10:50", "remaining_time": "8:03:13"}
+{"current_steps": 350, "total_steps": 15490, "loss": 0.2029, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.988776599411405e-05, "epoch": 0.23, "percentage": 2.26, "elapsed_time": "0:10:57", "remaining_time": "7:54:14"}
+{"current_steps": 350, "total_steps": 15490, "loss": null, "eval_loss": 0.15160420536994934, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.23, "percentage": 2.26, "elapsed_time": "0:10:57", "remaining_time": "7:54:14"}
+{"current_steps": 360, "total_steps": 15490, "loss": 0.1585, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.98808636150624e-05, "epoch": 0.23, "percentage": 2.32, "elapsed_time": "0:12:09", "remaining_time": "8:31:04"}
+{"current_steps": 370, "total_steps": 15490, "loss": 0.108, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.987375552718133e-05, "epoch": 0.24, "percentage": 2.39, "elapsed_time": "0:12:17", "remaining_time": "8:22:03"}
+{"current_steps": 380, "total_steps": 15490, "loss": 0.135, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.986644175978466e-05, "epoch": 0.25, "percentage": 2.45, "elapsed_time": "0:12:24", "remaining_time": "8:13:16"}
+{"current_steps": 390, "total_steps": 15490, "loss": 0.1606, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.985892234303438e-05, "epoch": 0.25, "percentage": 2.52, "elapsed_time": "0:12:32", "remaining_time": "8:05:16"}
+{"current_steps": 400, "total_steps": 15490, "loss": 0.1081, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.985119730794056e-05, "epoch": 0.26, "percentage": 2.58, "elapsed_time": "0:12:39", "remaining_time": "7:57:21"}
+{"current_steps": 400, "total_steps": 15490, "loss": null, "eval_loss": 0.15552477538585663, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.26, "percentage": 2.58, "elapsed_time": "0:12:39", "remaining_time": "7:57:21"}
+{"current_steps": 410, "total_steps": 15490, "loss": 0.1763, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.984326668636131e-05, "epoch": 0.26, "percentage": 2.65, "elapsed_time": "0:13:51", "remaining_time": "8:29:40"}
+{"current_steps": 420, "total_steps": 15490, "loss": 0.1041, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.98351305110025e-05, "epoch": 0.27, "percentage": 2.71, "elapsed_time": "0:13:58", "remaining_time": "8:21:39"}
+{"current_steps": 430, "total_steps": 15490, "loss": 0.145, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.982678881541776e-05, "epoch": 0.28, "percentage": 2.78, "elapsed_time": "0:14:06", "remaining_time": "8:14:15"}
+{"current_steps": 440, "total_steps": 15490, "loss": 0.1629, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.981824163400827e-05, "epoch": 0.28, "percentage": 2.84, "elapsed_time": "0:14:14", "remaining_time": "8:07:10"}
+{"current_steps": 450, "total_steps": 15490, "loss": 0.1619, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.980948900202262e-05, "epoch": 0.29, "percentage": 2.91, "elapsed_time": "0:14:22", "remaining_time": "8:00:16"}
+{"current_steps": 450, "total_steps": 15490, "loss": null, "eval_loss": 0.14458192884922028, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.29, "percentage": 2.91, "elapsed_time": "0:14:22", "remaining_time": "8:00:16"}
+{"current_steps": 460, "total_steps": 15490, "loss": 0.136, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.98005309555567e-05, "epoch": 0.3, "percentage": 2.97, "elapsed_time": "0:15:33", "remaining_time": "8:28:26"}
+{"current_steps": 470, "total_steps": 15490, "loss": 0.1194, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.979136753155351e-05, "epoch": 0.3, "percentage": 3.03, "elapsed_time": "0:15:41", "remaining_time": "8:21:33"}
+{"current_steps": 480, "total_steps": 15490, "loss": 0.1498, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.978199876780304e-05, "epoch": 0.31, "percentage": 3.1, "elapsed_time": "0:15:48", "remaining_time": "8:14:31"}
+{"current_steps": 490, "total_steps": 15490, "loss": 0.1561, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.977242470294212e-05, "epoch": 0.32, "percentage": 3.16, "elapsed_time": "0:15:57", "remaining_time": "8:08:20"}
+{"current_steps": 500, "total_steps": 15490, "loss": 0.111, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.97626453764542e-05, "epoch": 0.32, "percentage": 3.23, "elapsed_time": "0:16:04", "remaining_time": "8:02:07"}
+{"current_steps": 500, "total_steps": 15490, "loss": null, "eval_loss": 0.1412981152534485, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.32, "percentage": 3.23, "elapsed_time": "0:16:04", "remaining_time": "8:02:07"}
+{"current_steps": 510, "total_steps": 15490, "loss": 0.1407, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.975266082866923e-05, "epoch": 0.33, "percentage": 3.29, "elapsed_time": "0:17:17", "remaining_time": "8:27:50"}
+{"current_steps": 520, "total_steps": 15490, "loss": 0.1087, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.974247110076355e-05, "epoch": 0.34, "percentage": 3.36, "elapsed_time": "0:17:24", "remaining_time": "8:21:20"}
+{"current_steps": 530, "total_steps": 15490, "loss": 0.1808, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.973207623475965e-05, "epoch": 0.34, "percentage": 3.42, "elapsed_time": "0:17:31", "remaining_time": "8:14:48"}
+{"current_steps": 540, "total_steps": 15490, "loss": 0.1508, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.972147627352592e-05, "epoch": 0.35, "percentage": 3.49, "elapsed_time": "0:17:39", "remaining_time": "8:08:53"}
+{"current_steps": 550, "total_steps": 15490, "loss": 0.1546, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.971067126077669e-05, "epoch": 0.36, "percentage": 3.55, "elapsed_time": "0:17:47", "remaining_time": "8:03:12"}
+{"current_steps": 550, "total_steps": 15490, "loss": null, "eval_loss": 0.14756999909877777, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.36, "percentage": 3.55, "elapsed_time": "0:17:47", "remaining_time": "8:03:12"}
+{"current_steps": 560, "total_steps": 15490, "loss": 0.1303, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.969966124107183e-05, "epoch": 0.36, "percentage": 3.62, "elapsed_time": "0:18:58", "remaining_time": "8:26:03"}
+{"current_steps": 570, "total_steps": 15490, "loss": 0.1683, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.968844625981672e-05, "epoch": 0.37, "percentage": 3.68, "elapsed_time": "0:19:06", "remaining_time": "8:20:21"}
+{"current_steps": 580, "total_steps": 15490, "loss": 0.1199, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.967702636326194e-05, "epoch": 0.37, "percentage": 3.74, "elapsed_time": "0:19:14", "remaining_time": "8:14:39"}
+{"current_steps": 590, "total_steps": 15490, "loss": 0.1296, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.966540159850323e-05, "epoch": 0.38, "percentage": 3.81, "elapsed_time": "0:19:22", "remaining_time": "8:09:06"}
+{"current_steps": 600, "total_steps": 15490, "loss": 0.14, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.965357201348111e-05, "epoch": 0.39, "percentage": 3.87, "elapsed_time": "0:19:29", "remaining_time": "8:03:54"}
+{"current_steps": 600, "total_steps": 15490, "loss": null, "eval_loss": 0.14366257190704346, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.39, "percentage": 3.87, "elapsed_time": "0:19:29", "remaining_time": "8:03:54"}
+{"current_steps": 610, "total_steps": 15490, "loss": 0.1899, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.964153765698083e-05, "epoch": 0.39, "percentage": 3.94, "elapsed_time": "0:20:41", "remaining_time": "8:24:40"}
+{"current_steps": 620, "total_steps": 15490, "loss": 0.1342, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.962929857863215e-05, "epoch": 0.4, "percentage": 4.0, "elapsed_time": "0:20:48", "remaining_time": "8:19:15"}
+{"current_steps": 630, "total_steps": 15490, "loss": 0.1417, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.961685482890901e-05, "epoch": 0.41, "percentage": 4.07, "elapsed_time": "0:20:56", "remaining_time": "8:13:56"}
+{"current_steps": 640, "total_steps": 15490, "loss": 0.1421, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.960420645912949e-05, "epoch": 0.41, "percentage": 4.13, "elapsed_time": "0:21:03", "remaining_time": "8:08:43"}
+{"current_steps": 650, "total_steps": 15490, "loss": 0.1082, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.959135352145552e-05, "epoch": 0.42, "percentage": 4.2, "elapsed_time": "0:21:11", "remaining_time": "8:03:50"}
+{"current_steps": 650, "total_steps": 15490, "loss": null, "eval_loss": 0.14832669496536255, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.42, "percentage": 4.2, "elapsed_time": "0:21:11", "remaining_time": "8:03:50"}
+{"current_steps": 650, "total_steps": 15490, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.42, "percentage": 4.2, "elapsed_time": "0:21:11", "remaining_time": "8:03:50"}
+{"current_steps": 274, "total_steps": 274, "loss": null, "eval_loss": 0.1412981152534485, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 0.42, "percentage": 100.0, "elapsed_time": "0:23:33", "remaining_time": "0:00:00"}

llama2_13b_peft/vitaminc_fact_verification/trainer_state.json

@@ -0,0 +1,589 @@
+{
+  "best_metric": 0.1412981152534485,
+  "best_model_checkpoint": "ckpt/llama2_13b_fuze15_no_sys/vitaminc_fact_verification_no_sys/checkpoint-500",
+  "epoch": 0.4196255648805681,
+  "eval_steps": 50,
+  "global_step": 650,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01,
+      "grad_norm": 10.859735488891602,
+      "learning_rate": 5e-05,
+      "loss": 7.5989,
+      "step": 10
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 18.92371368408203,
+      "learning_rate": 0.0001,
+      "loss": 1.8506,
+      "step": 20
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 4.927052974700928,
+      "learning_rate": 9.99998968999259e-05,
+      "loss": 0.5371,
+      "step": 30
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.9307419657707214,
+      "learning_rate": 9.99995876001288e-05,
+      "loss": 0.4742,
+      "step": 40
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 1.7804088592529297,
+      "learning_rate": 9.999907210188424e-05,
+      "loss": 0.4369,
+      "step": 50
+    },
+    {
+      "epoch": 0.03,
+      "eval_loss": 0.3792226016521454,
+      "eval_runtime": 64.0364,
+      "eval_samples_per_second": 102.457,
+      "eval_steps_per_second": 4.279,
+      "step": 50
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 1.2824290990829468,
+      "learning_rate": 9.999835040731813e-05,
+      "loss": 0.3655,
+      "step": 60
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 2.9581339359283447,
+      "learning_rate": 9.999742251940676e-05,
+      "loss": 0.2957,
+      "step": 70
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 1.5681889057159424,
+      "learning_rate": 9.999628844197672e-05,
+      "loss": 0.3023,
+      "step": 80
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 2.3982322216033936,
+      "learning_rate": 9.999494817970498e-05,
+      "loss": 0.2589,
+      "step": 90
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 1.3965446949005127,
+      "learning_rate": 9.999340173811875e-05,
+      "loss": 0.2145,
+      "step": 100
+    },
+    {
+      "epoch": 0.06,
+      "eval_loss": 0.22720637917518616,
+      "eval_runtime": 64.0931,
+      "eval_samples_per_second": 102.367,
+      "eval_steps_per_second": 4.275,
+      "step": 100
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 2.2436370849609375,
+      "learning_rate": 9.999164912359557e-05,
+      "loss": 0.2288,
+      "step": 110
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.4689403772354126,
+      "learning_rate": 9.998969034336327e-05,
+      "loss": 0.2672,
+      "step": 120
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 1.8660027980804443,
+      "learning_rate": 9.99875254054998e-05,
+      "loss": 0.2312,
+      "step": 130
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 2.51678729057312,
+      "learning_rate": 9.99851543189334e-05,
+      "loss": 0.1959,
+      "step": 140
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.6088509559631348,
+      "learning_rate": 9.998257709344246e-05,
+      "loss": 0.2037,
+      "step": 150
+    },
+    {
+      "epoch": 0.1,
+      "eval_loss": 0.1836628019809723,
+      "eval_runtime": 64.108,
+      "eval_samples_per_second": 102.343,
+      "eval_steps_per_second": 4.274,
+      "step": 150
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 1.2034131288528442,
+      "learning_rate": 9.997979373965541e-05,
+      "loss": 0.2029,
+      "step": 160
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 1.6140587329864502,
+      "learning_rate": 9.997680426905086e-05,
+      "loss": 0.1685,
+      "step": 170
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 0.7357319593429565,
+      "learning_rate": 9.997360869395738e-05,
+      "loss": 0.2626,
+      "step": 180
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 1.1027621030807495,
+      "learning_rate": 9.997020702755353e-05,
+      "loss": 0.2029,
+      "step": 190
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 2.1580281257629395,
+      "learning_rate": 9.996659928386778e-05,
+      "loss": 0.1913,
+      "step": 200
+    },
+    {
+      "epoch": 0.13,
+      "eval_loss": 0.27072426676750183,
+      "eval_runtime": 64.1275,
+      "eval_samples_per_second": 102.312,
+      "eval_steps_per_second": 4.273,
+      "step": 200
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 0.9698787927627563,
+      "learning_rate": 9.996278547777851e-05,
+      "loss": 0.225,
+      "step": 210
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.197509765625,
+      "learning_rate": 9.995876562501383e-05,
+      "loss": 0.2244,
+      "step": 220
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 1.7454187870025635,
+      "learning_rate": 9.995453974215163e-05,
+      "loss": 0.1903,
+      "step": 230
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.8432933688163757,
+      "learning_rate": 9.995010784661948e-05,
+      "loss": 0.1813,
+      "step": 240
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.7707247138023376,
+      "learning_rate": 9.994546995669454e-05,
+      "loss": 0.1781,
+      "step": 250
+    },
+    {
+      "epoch": 0.16,
+      "eval_loss": 0.17831701040267944,
+      "eval_runtime": 64.1171,
+      "eval_samples_per_second": 102.328,
+      "eval_steps_per_second": 4.273,
+      "step": 250
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 0.5202718377113342,
+      "learning_rate": 9.994062609150345e-05,
+      "loss": 0.194,
+      "step": 260
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 1.0719162225723267,
+      "learning_rate": 9.993557627102234e-05,
+      "loss": 0.2086,
+      "step": 270
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.8697193264961243,
+      "learning_rate": 9.993032051607669e-05,
+      "loss": 0.1526,
+      "step": 280
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 1.0092685222625732,
+      "learning_rate": 9.992485884834124e-05,
+      "loss": 0.1478,
+      "step": 290
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 2.2846994400024414,
+      "learning_rate": 9.991919129033994e-05,
+      "loss": 0.2087,
+      "step": 300
+    },
+    {
+      "epoch": 0.19,
+      "eval_loss": 0.2066759169101715,
+      "eval_runtime": 64.114,
+      "eval_samples_per_second": 102.333,
+      "eval_steps_per_second": 4.274,
+      "step": 300
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 0.825279176235199,
+      "learning_rate": 9.991331786544577e-05,
+      "loss": 0.1824,
+      "step": 310
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.030802845954895,
+      "learning_rate": 9.990723859788081e-05,
+      "loss": 0.1129,
+      "step": 320
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 1.1893362998962402,
+      "learning_rate": 9.990095351271594e-05,
+      "loss": 0.1886,
+      "step": 330
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 1.1142666339874268,
+      "learning_rate": 9.98944626358709e-05,
+      "loss": 0.1969,
+      "step": 340
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.058111310005188,
+      "learning_rate": 9.988776599411405e-05,
+      "loss": 0.2029,
+      "step": 350
+    },
+    {
+      "epoch": 0.23,
+      "eval_loss": 0.15160420536994934,
+      "eval_runtime": 64.19,
+      "eval_samples_per_second": 102.212,
+      "eval_steps_per_second": 4.269,
+      "step": 350
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 1.1944071054458618,
+      "learning_rate": 9.98808636150624e-05,
+      "loss": 0.1585,
+      "step": 360
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.920417845249176,
+      "learning_rate": 9.987375552718133e-05,
+      "loss": 0.108,
+      "step": 370
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.9066952466964722,
+      "learning_rate": 9.986644175978466e-05,
+      "loss": 0.135,
+      "step": 380
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.9051805138587952,
+      "learning_rate": 9.985892234303438e-05,
+      "loss": 0.1606,
+      "step": 390
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.7989512085914612,
+      "learning_rate": 9.985119730794056e-05,
+      "loss": 0.1081,
+      "step": 400
+    },
+    {
+      "epoch": 0.26,
+      "eval_loss": 0.15552477538585663,
+      "eval_runtime": 64.1478,
+      "eval_samples_per_second": 102.279,
+      "eval_steps_per_second": 4.271,
+      "step": 400
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.9340474009513855,
+      "learning_rate": 9.984326668636131e-05,
+      "loss": 0.1763,
+      "step": 410
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 2.8541486263275146,
+      "learning_rate": 9.98351305110025e-05,
+      "loss": 0.1041,
+      "step": 420
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.9724450707435608,
+      "learning_rate": 9.982678881541776e-05,
+      "loss": 0.145,
+      "step": 430
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 0.9071981906890869,
+      "learning_rate": 9.981824163400827e-05,
+      "loss": 0.1629,
+      "step": 440
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 1.0815389156341553,
+      "learning_rate": 9.980948900202262e-05,
+      "loss": 0.1619,
+      "step": 450
+    },
+    {
+      "epoch": 0.29,
+      "eval_loss": 0.14458192884922028,
+      "eval_runtime": 64.1153,
+      "eval_samples_per_second": 102.331,
+      "eval_steps_per_second": 4.274,
+      "step": 450
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 1.084578275680542,
+      "learning_rate": 9.98005309555567e-05,
+      "loss": 0.136,
+      "step": 460
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 0.9090166091918945,
+      "learning_rate": 9.979136753155351e-05,
+      "loss": 0.1194,
+      "step": 470
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 1.7761623859405518,
+      "learning_rate": 9.978199876780304e-05,
+      "loss": 0.1498,
+      "step": 480
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.8033456206321716,
+      "learning_rate": 9.977242470294212e-05,
+      "loss": 0.1561,
+      "step": 490
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.4055212438106537,
+      "learning_rate": 9.97626453764542e-05,
+      "loss": 0.111,
+      "step": 500
+    },
+    {
+      "epoch": 0.32,
+      "eval_loss": 0.1412981152534485,
+      "eval_runtime": 64.1229,
+      "eval_samples_per_second": 102.319,
+      "eval_steps_per_second": 4.273,
+      "step": 500
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 2.6774351596832275,
+      "learning_rate": 9.975266082866923e-05,
+      "loss": 0.1407,
+      "step": 510
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.5348044037818909,
+      "learning_rate": 9.974247110076355e-05,
+      "loss": 0.1087,
+      "step": 520
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.6100921034812927,
+      "learning_rate": 9.973207623475965e-05,
+      "loss": 0.1808,
+      "step": 530
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 0.5292113423347473,
+      "learning_rate": 9.972147627352592e-05,
+      "loss": 0.1508,
+      "step": 540
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.4681833982467651,
+      "learning_rate": 9.971067126077669e-05,
+      "loss": 0.1546,
+      "step": 550
+    },
+    {
+      "epoch": 0.36,
+      "eval_loss": 0.14756999909877777,
+      "eval_runtime": 64.1644,
+      "eval_samples_per_second": 102.253,
+      "eval_steps_per_second": 4.27,
+      "step": 550
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.851148247718811,
+      "learning_rate": 9.969966124107183e-05,
+      "loss": 0.1303,
+      "step": 560
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.9203129410743713,
+      "learning_rate": 9.968844625981672e-05,
+      "loss": 0.1683,
+      "step": 570
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 1.1840310096740723,
+      "learning_rate": 9.967702636326194e-05,
+      "loss": 0.1199,
+      "step": 580
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 0.7599567770957947,
+      "learning_rate": 9.966540159850323e-05,
+      "loss": 0.1296,
+      "step": 590
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 1.0713849067687988,
+      "learning_rate": 9.965357201348111e-05,
+      "loss": 0.14,
+      "step": 600
+    },
+    {
+      "epoch": 0.39,
+      "eval_loss": 0.14366257190704346,
+      "eval_runtime": 64.1436,
+      "eval_samples_per_second": 102.286,
+      "eval_steps_per_second": 4.272,
+      "step": 600
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.8163577914237976,
+      "learning_rate": 9.964153765698083e-05,
+      "loss": 0.1899,
+      "step": 610
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.6260606050491333,
+      "learning_rate": 9.962929857863215e-05,
+      "loss": 0.1342,
+      "step": 620
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 1.3450220823287964,
+      "learning_rate": 9.961685482890901e-05,
+      "loss": 0.1417,
+      "step": 630
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 2.8518264293670654,
+      "learning_rate": 9.960420645912949e-05,
+      "loss": 0.1421,
+      "step": 640
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.3831160366535187,
+      "learning_rate": 9.959135352145552e-05,
+      "loss": 0.1082,
+      "step": 650
+    },
+    {
+      "epoch": 0.42,
+      "eval_loss": 0.14832669496536255,
+      "eval_runtime": 64.1294,
+      "eval_samples_per_second": 102.309,
+      "eval_steps_per_second": 4.273,
+      "step": 650
+    },
+    {
+      "epoch": 0.42,
+      "step": 650,
+      "total_flos": 2.307321824972636e+17,
+      "train_loss": 0.3310180792441735,
+      "train_runtime": 1340.7166,
+      "train_samples_per_second": 277.27,
+      "train_steps_per_second": 11.554
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 15490,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 2.307321824972636e+17,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

llama2_13b_peft/vitaminc_fact_verification/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8d870d151be3e535cf16486ceecb60cffba0b4d073161e08569bec709eb0934
+size 5112