Model save

README.md

@@ -0,0 +1,67 @@
+---
+library_name: transformers
+license: llama3.1
+base_model: meta-llama/Meta-Llama-3.1-8B
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: llama3-1_8b_oh_dcft_v1_wo_camel_chemistry_gpt-4o-mini
+  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. -->
+
+# llama3-1_8b_oh_dcft_v1_wo_camel_chemistry_gpt-4o-mini
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3.1-8B](https://huggingface.co/meta-llama/Meta-Llama-3.1-8B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.5453
+
+## 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: 5e-06
+- train_batch_size: 16
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 32
+- total_train_batch_size: 512
+- total_eval_batch_size: 256
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.1
+- lr_scheduler_warmup_steps: 1738
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.5859        | 1.0   | 389  | 0.5778          |
+| 0.5297        | 2.0   | 778  | 0.5520          |
+| 0.4908        | 3.0   | 1167 | 0.5453          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.0
+- Datasets 2.21.0
+- Tokenizers 0.19.1

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50a1b21aabea5268cd3ac16974f315ee3db56c86563ecbf2fd1575c57e10fd20
+oid sha256:65426b720fc704c3d3f869c5a482177571b40363c145333cfe1ad0756ded3a38
 size 4976698672

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:472ba41c999747e7ee26f92805828d748ce924ab0562a12d9a8e8205bbedff8d
+oid sha256:a5d0c977ab068dc84a20bf4e21a9d94b6356165084b85b98de47a43d606ebe92
 size 4999802720

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4968182b2eb09b8f8a8795ef6feb173e381d6802b2c125e1a45409eaff03c85e
+oid sha256:c8d32a5f6289ceb88d3d97e83c61b4b29e9a56c84d99f08ea08f1722ae965612
 size 4915916176

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:454c63db601b9275d8965b5a6538330f0cb81b48a965a448ef12e41aca901d78
+oid sha256:0eb45effbdab094c5c4a322221e45d4ae83dd1c60123cf41906721861f564368
 size 1168138808

trainer_log.jsonl

@@ -80,3 +80,41 @@
 {"current_steps": 780, "total_steps": 1167, "loss": 0.5175, "learning_rate": 5e-06, "epoch": 2.005141388174807, "percentage": 66.84, "elapsed_time": "1:30:44", "remaining_time": "0:45:01"}
 {"current_steps": 790, "total_steps": 1167, "loss": 0.4906, "learning_rate": 5e-06, "epoch": 2.030848329048843, "percentage": 67.69, "elapsed_time": "1:31:46", "remaining_time": "0:43:47"}
 {"current_steps": 800, "total_steps": 1167, "loss": 0.4893, "learning_rate": 5e-06, "epoch": 2.056555269922879, "percentage": 68.55, "elapsed_time": "1:32:48", "remaining_time": "0:42:34"}
+{"current_steps": 810, "total_steps": 1167, "loss": 0.4989, "learning_rate": 5e-06, "epoch": 2.082262210796915, "percentage": 69.41, "elapsed_time": "1:33:51", "remaining_time": "0:41:21"}
+{"current_steps": 820, "total_steps": 1167, "loss": 0.4874, "learning_rate": 5e-06, "epoch": 2.107969151670951, "percentage": 70.27, "elapsed_time": "1:34:53", "remaining_time": "0:40:09"}
+{"current_steps": 830, "total_steps": 1167, "loss": 0.4944, "learning_rate": 5e-06, "epoch": 2.133676092544987, "percentage": 71.12, "elapsed_time": "1:35:56", "remaining_time": "0:38:57"}
+{"current_steps": 840, "total_steps": 1167, "loss": 0.4871, "learning_rate": 5e-06, "epoch": 2.159383033419023, "percentage": 71.98, "elapsed_time": "1:36:58", "remaining_time": "0:37:45"}
+{"current_steps": 850, "total_steps": 1167, "loss": 0.4928, "learning_rate": 5e-06, "epoch": 2.185089974293059, "percentage": 72.84, "elapsed_time": "1:38:00", "remaining_time": "0:36:33"}
+{"current_steps": 860, "total_steps": 1167, "loss": 0.4909, "learning_rate": 5e-06, "epoch": 2.210796915167095, "percentage": 73.69, "elapsed_time": "1:39:03", "remaining_time": "0:35:21"}
+{"current_steps": 870, "total_steps": 1167, "loss": 0.489, "learning_rate": 5e-06, "epoch": 2.236503856041131, "percentage": 74.55, "elapsed_time": "1:40:05", "remaining_time": "0:34:10"}
+{"current_steps": 880, "total_steps": 1167, "loss": 0.4838, "learning_rate": 5e-06, "epoch": 2.2622107969151672, "percentage": 75.41, "elapsed_time": "1:41:08", "remaining_time": "0:32:59"}
+{"current_steps": 890, "total_steps": 1167, "loss": 0.4892, "learning_rate": 5e-06, "epoch": 2.2879177377892033, "percentage": 76.26, "elapsed_time": "1:42:10", "remaining_time": "0:31:48"}
+{"current_steps": 900, "total_steps": 1167, "loss": 0.4958, "learning_rate": 5e-06, "epoch": 2.3136246786632393, "percentage": 77.12, "elapsed_time": "1:43:13", "remaining_time": "0:30:37"}
+{"current_steps": 910, "total_steps": 1167, "loss": 0.4904, "learning_rate": 5e-06, "epoch": 2.3393316195372753, "percentage": 77.98, "elapsed_time": "1:44:15", "remaining_time": "0:29:26"}
+{"current_steps": 920, "total_steps": 1167, "loss": 0.4949, "learning_rate": 5e-06, "epoch": 2.365038560411311, "percentage": 78.83, "elapsed_time": "1:45:18", "remaining_time": "0:28:16"}
+{"current_steps": 930, "total_steps": 1167, "loss": 0.4941, "learning_rate": 5e-06, "epoch": 2.390745501285347, "percentage": 79.69, "elapsed_time": "1:46:20", "remaining_time": "0:27:06"}
+{"current_steps": 940, "total_steps": 1167, "loss": 0.4943, "learning_rate": 5e-06, "epoch": 2.416452442159383, "percentage": 80.55, "elapsed_time": "1:47:23", "remaining_time": "0:25:56"}
+{"current_steps": 950, "total_steps": 1167, "loss": 0.4924, "learning_rate": 5e-06, "epoch": 2.442159383033419, "percentage": 81.41, "elapsed_time": "1:48:26", "remaining_time": "0:24:46"}
+{"current_steps": 960, "total_steps": 1167, "loss": 0.486, "learning_rate": 5e-06, "epoch": 2.467866323907455, "percentage": 82.26, "elapsed_time": "1:49:29", "remaining_time": "0:23:36"}
+{"current_steps": 970, "total_steps": 1167, "loss": 0.4907, "learning_rate": 5e-06, "epoch": 2.493573264781491, "percentage": 83.12, "elapsed_time": "1:50:31", "remaining_time": "0:22:26"}
+{"current_steps": 980, "total_steps": 1167, "loss": 0.496, "learning_rate": 5e-06, "epoch": 2.519280205655527, "percentage": 83.98, "elapsed_time": "1:51:34", "remaining_time": "0:21:17"}
+{"current_steps": 990, "total_steps": 1167, "loss": 0.4927, "learning_rate": 5e-06, "epoch": 2.544987146529563, "percentage": 84.83, "elapsed_time": "1:52:36", "remaining_time": "0:20:07"}
+{"current_steps": 1000, "total_steps": 1167, "loss": 0.4859, "learning_rate": 5e-06, "epoch": 2.570694087403599, "percentage": 85.69, "elapsed_time": "1:53:39", "remaining_time": "0:18:58"}
+{"current_steps": 1010, "total_steps": 1167, "loss": 0.4908, "learning_rate": 5e-06, "epoch": 2.596401028277635, "percentage": 86.55, "elapsed_time": "1:54:42", "remaining_time": "0:17:49"}
+{"current_steps": 1020, "total_steps": 1167, "loss": 0.4894, "learning_rate": 5e-06, "epoch": 2.622107969151671, "percentage": 87.4, "elapsed_time": "1:55:44", "remaining_time": "0:16:40"}
+{"current_steps": 1030, "total_steps": 1167, "loss": 0.4913, "learning_rate": 5e-06, "epoch": 2.6478149100257067, "percentage": 88.26, "elapsed_time": "1:56:47", "remaining_time": "0:15:32"}
+{"current_steps": 1040, "total_steps": 1167, "loss": 0.4883, "learning_rate": 5e-06, "epoch": 2.6735218508997427, "percentage": 89.12, "elapsed_time": "1:57:50", "remaining_time": "0:14:23"}
+{"current_steps": 1050, "total_steps": 1167, "loss": 0.4852, "learning_rate": 5e-06, "epoch": 2.6992287917737787, "percentage": 89.97, "elapsed_time": "1:58:52", "remaining_time": "0:13:14"}
+{"current_steps": 1060, "total_steps": 1167, "loss": 0.4875, "learning_rate": 5e-06, "epoch": 2.7249357326478147, "percentage": 90.83, "elapsed_time": "1:59:55", "remaining_time": "0:12:06"}
+{"current_steps": 1070, "total_steps": 1167, "loss": 0.4862, "learning_rate": 5e-06, "epoch": 2.7506426735218508, "percentage": 91.69, "elapsed_time": "2:00:57", "remaining_time": "0:10:57"}
+{"current_steps": 1080, "total_steps": 1167, "loss": 0.4866, "learning_rate": 5e-06, "epoch": 2.776349614395887, "percentage": 92.54, "elapsed_time": "2:02:00", "remaining_time": "0:09:49"}
+{"current_steps": 1090, "total_steps": 1167, "loss": 0.4882, "learning_rate": 5e-06, "epoch": 2.802056555269923, "percentage": 93.4, "elapsed_time": "2:03:02", "remaining_time": "0:08:41"}
+{"current_steps": 1100, "total_steps": 1167, "loss": 0.4857, "learning_rate": 5e-06, "epoch": 2.827763496143959, "percentage": 94.26, "elapsed_time": "2:04:05", "remaining_time": "0:07:33"}
+{"current_steps": 1110, "total_steps": 1167, "loss": 0.4844, "learning_rate": 5e-06, "epoch": 2.853470437017995, "percentage": 95.12, "elapsed_time": "2:05:07", "remaining_time": "0:06:25"}
+{"current_steps": 1120, "total_steps": 1167, "loss": 0.4877, "learning_rate": 5e-06, "epoch": 2.879177377892031, "percentage": 95.97, "elapsed_time": "2:06:10", "remaining_time": "0:05:17"}
+{"current_steps": 1130, "total_steps": 1167, "loss": 0.4853, "learning_rate": 5e-06, "epoch": 2.904884318766067, "percentage": 96.83, "elapsed_time": "2:07:12", "remaining_time": "0:04:09"}
+{"current_steps": 1140, "total_steps": 1167, "loss": 0.4856, "learning_rate": 5e-06, "epoch": 2.930591259640103, "percentage": 97.69, "elapsed_time": "2:08:15", "remaining_time": "0:03:02"}
+{"current_steps": 1150, "total_steps": 1167, "loss": 0.4866, "learning_rate": 5e-06, "epoch": 2.956298200514139, "percentage": 98.54, "elapsed_time": "2:09:17", "remaining_time": "0:01:54"}
+{"current_steps": 1160, "total_steps": 1167, "loss": 0.4908, "learning_rate": 5e-06, "epoch": 2.982005141388175, "percentage": 99.4, "elapsed_time": "2:10:20", "remaining_time": "0:00:47"}
+{"current_steps": 1167, "total_steps": 1167, "eval_loss": 0.5453311800956726, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:15:53", "remaining_time": "0:00:00"}
+{"current_steps": 1167, "total_steps": 1167, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:19:43", "remaining_time": "0:00:00"}