Model save

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: swesmith-stackseq
+  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. -->
+
+# swesmith-stackseq
+
+This model was trained from scratch on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 4e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.98) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 7.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.56.1
+- Pytorch 2.9.1+cu128
+- Datasets 4.4.1
+- Tokenizers 0.22.1

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.56.1"
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec72f45c15ccc06edc9344333cfeefb0b4a14d5cbf94c2300b7f30e55bcf802
+oid sha256:3ed5f25a24de16c4b76e33c107633b5ff3773560d426dc2217edccb89e94e967
 size 4902257696

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1fc5f072b8a86d51745e69d9f490f4d1155831aa8f4d951c3f85fcd15dd59c8c
+oid sha256:11800a7d44af841b55582f1b032b0d9a93a85cdcabbd4848346cca0905017f2c
 size 4915960368

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56fc9f2598355a4c26c3c4ee3110b314bc20ac486c103e39277b48ee6f975079
+oid sha256:9ec6a172b2f60a288dd35356b12752cd1d3737b6a20a840e031a8b58745bf90a
 size 4983068496

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b25f6c3ed3e0ba5e3014a0a844371d7f1bed9429d88d638fb298601c2c822df
+oid sha256:2f067182115d1b2df5c343dcbc6bb5152bf5744678e4dc5dd354c7f165e18ebb
 size 1580230264

trainer_log.jsonl

@@ -1342,3 +1342,25 @@
 {"current_steps": 6595, "total_steps": 6713, "loss": 0.1975, "lr": 3.8285770108272836e-08, "epoch": 6.878455920709442, "percentage": 98.24, "elapsed_time": "1 day, 3:02:01", "remaining_time": "0:29:01"}
 {"current_steps": 6600, "total_steps": 6713, "loss": 0.1922, "lr": 3.5136991259672183e-08, "epoch": 6.8836724047991655, "percentage": 98.32, "elapsed_time": "1 day, 3:03:43", "remaining_time": "0:27:48"}
 {"current_steps": 6605, "total_steps": 6713, "loss": 0.1966, "lr": 3.212319823834298e-08, "epoch": 6.888888888888889, "percentage": 98.39, "elapsed_time": "1 day, 3:06:45", "remaining_time": "0:26:35"}
+{"current_steps": 6610, "total_steps": 6713, "loss": 0.1904, "lr": 2.9244411421049946e-08, "epoch": 6.894105372978612, "percentage": 98.47, "elapsed_time": "1 day, 3:08:25", "remaining_time": "0:25:22"}
+{"current_steps": 6615, "total_steps": 6713, "loss": 0.1933, "lr": 2.6500650271759077e-08, "epoch": 6.899321857068336, "percentage": 98.54, "elapsed_time": "1 day, 3:10:01", "remaining_time": "0:24:08"}
+{"current_steps": 6620, "total_steps": 6713, "loss": 0.1954, "lr": 2.3891933341506636e-08, "epoch": 6.90453834115806, "percentage": 98.61, "elapsed_time": "1 day, 3:11:50", "remaining_time": "0:22:55"}
+{"current_steps": 6625, "total_steps": 6713, "loss": 0.1853, "lr": 2.1418278268270365e-08, "epoch": 6.9097548252477825, "percentage": 98.69, "elapsed_time": "1 day, 3:13:40", "remaining_time": "0:21:42"}
+{"current_steps": 6630, "total_steps": 6713, "loss": 0.1855, "lr": 1.907970177684737e-08, "epoch": 6.914971309337506, "percentage": 98.76, "elapsed_time": "1 day, 3:15:22", "remaining_time": "0:20:28"}
+{"current_steps": 6635, "total_steps": 6713, "loss": 0.1884, "lr": 1.687621967875863e-08, "epoch": 6.92018779342723, "percentage": 98.84, "elapsed_time": "1 day, 3:17:06", "remaining_time": "0:19:14"}
+{"current_steps": 6640, "total_steps": 6713, "loss": 0.1862, "lr": 1.4807846872113563e-08, "epoch": 6.925404277516954, "percentage": 98.91, "elapsed_time": "1 day, 3:18:46", "remaining_time": "0:18:01"}
+{"current_steps": 6645, "total_steps": 6713, "loss": 0.18, "lr": 1.2874597341534512e-08, "epoch": 6.9306207616066775, "percentage": 98.99, "elapsed_time": "1 day, 3:20:30", "remaining_time": "0:16:47"}
+{"current_steps": 6650, "total_steps": 6713, "loss": 0.1762, "lr": 1.1076484158047962e-08, "epoch": 6.9358372456964, "percentage": 99.06, "elapsed_time": "1 day, 3:22:07", "remaining_time": "0:15:33"}
+{"current_steps": 6655, "total_steps": 6713, "loss": 0.1863, "lr": 9.413519479004596e-09, "epoch": 6.941053729786124, "percentage": 99.14, "elapsed_time": "1 day, 3:23:44", "remaining_time": "0:14:19"}
+{"current_steps": 6660, "total_steps": 6713, "loss": 0.186, "lr": 7.885714547990475e-09, "epoch": 6.946270213875848, "percentage": 99.21, "elapsed_time": "1 day, 3:25:26", "remaining_time": "0:13:05"}
+{"current_steps": 6665, "total_steps": 6713, "loss": 0.2063, "lr": 6.493079694753768e-09, "epoch": 6.951486697965571, "percentage": 99.28, "elapsed_time": "1 day, 3:27:03", "remaining_time": "0:11:51"}
+{"current_steps": 6670, "total_steps": 6713, "loss": 0.185, "lr": 5.235624335133693e-09, "epoch": 6.9567031820552945, "percentage": 99.36, "elapsed_time": "1 day, 3:28:42", "remaining_time": "0:10:37"}
+{"current_steps": 6675, "total_steps": 6713, "loss": 0.1817, "lr": 4.113356971002791e-09, "epoch": 6.961919666145018, "percentage": 99.43, "elapsed_time": "1 day, 3:30:24", "remaining_time": "0:09:23"}
+{"current_steps": 6680, "total_steps": 6713, "loss": 0.1833, "lr": 3.126285190195866e-09, "epoch": 6.967136150234742, "percentage": 99.51, "elapsed_time": "1 day, 3:32:03", "remaining_time": "0:08:09"}
+{"current_steps": 6685, "total_steps": 6713, "loss": 0.1934, "lr": 2.2744156664766813e-09, "epoch": 6.972352634324466, "percentage": 99.58, "elapsed_time": "1 day, 3:33:43", "remaining_time": "0:06:55"}
+{"current_steps": 6690, "total_steps": 6713, "loss": 0.1925, "lr": 1.5577541594802293e-09, "epoch": 6.977569118414189, "percentage": 99.66, "elapsed_time": "1 day, 3:35:24", "remaining_time": "0:05:41"}
+{"current_steps": 6695, "total_steps": 6713, "loss": 0.1903, "lr": 9.7630551467498e-10, "epoch": 6.982785602503912, "percentage": 99.73, "elapsed_time": "1 day, 3:37:07", "remaining_time": "0:04:27"}
+{"current_steps": 6700, "total_steps": 6713, "loss": 0.1954, "lr": 5.300736633317982e-10, "epoch": 6.988002086593636, "percentage": 99.81, "elapsed_time": "1 day, 3:38:48", "remaining_time": "0:03:13"}
+{"current_steps": 6705, "total_steps": 6713, "loss": 0.1875, "lr": 2.1906162250395768e-10, "epoch": 6.993218570683359, "percentage": 99.88, "elapsed_time": "1 day, 3:40:28", "remaining_time": "0:01:58"}
+{"current_steps": 6710, "total_steps": 6713, "loss": 0.1902, "lr": 4.3271494996055544e-11, "epoch": 6.998435054773083, "percentage": 99.96, "elapsed_time": "1 day, 3:42:11", "remaining_time": "0:00:44"}
+{"current_steps": 6712, "total_steps": 6713, "epoch": 7.0, "percentage": 99.99, "elapsed_time": "1 day, 3:42:52", "remaining_time": "0:00:14"}