Model save

README.md

@@ -0,0 +1,58 @@
+---
+library_name: transformers
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: swesmith-stack-reason
+  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-stack-reason
+
+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 sha256:0046655427449842b6178310dee1432111e03520a5c1b66aafcb398a426b878d
+oid sha256:d40b405cfeb7b84be0cc350a6bf07adada36cbba5330f83e928029e60bfc2f0b
 size 4902257696

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23a43c2521ef7747ac6dd404874c88514485bfb6f34ed22e3c31d4159ea380cd
+oid sha256:6b3f6530521c364cb1fafcdc8334b0c714778b8a0b911e8c0137328b68471e0c
 size 4915960368

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded39634aed615d1e2161e3e397b4e6942338471fefe129f834fb44c1f027b08
+oid sha256:7dcc31cdea60bdb1e2a1ebcf3269bee75b0ac2421e4a215381ade2084d0a0526
 size 4983068496

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a473c085e4194795bf775e27646cce6030e60f436fd97cfe827471710cf4e35
+oid sha256:f6a21073d4ee9bdbb778b3cfaa385301e812596d65635fc01fc3fbb20bf6bdc0
 size 1580230264

trainer_log.jsonl

@@ -1321,3 +1321,23 @@
 {"current_steps": 6605, "total_steps": 6713, "loss": 0.1785, "lr": 3.212319823834298e-08, "epoch": 6.888888888888889, "percentage": 98.39, "elapsed_time": "1 day, 13:00:11", "remaining_time": "0:36:18"}
 {"current_steps": 6610, "total_steps": 6713, "loss": 0.1673, "lr": 2.9244411421049946e-08, "epoch": 6.894105372978612, "percentage": 98.47, "elapsed_time": "1 day, 13:03:01", "remaining_time": "0:34:38"}
 {"current_steps": 6615, "total_steps": 6713, "loss": 0.1669, "lr": 2.6500650271759077e-08, "epoch": 6.899321857068336, "percentage": 98.54, "elapsed_time": "1 day, 13:05:44", "remaining_time": "0:32:58"}
+{"current_steps": 6620, "total_steps": 6713, "loss": 0.1593, "lr": 2.3891933341506636e-08, "epoch": 6.90453834115806, "percentage": 98.61, "elapsed_time": "1 day, 13:08:37", "remaining_time": "0:31:18"}
+{"current_steps": 6625, "total_steps": 6713, "loss": 0.1746, "lr": 2.1418278268270365e-08, "epoch": 6.9097548252477825, "percentage": 98.69, "elapsed_time": "1 day, 13:11:11", "remaining_time": "0:29:38"}
+{"current_steps": 6630, "total_steps": 6713, "loss": 0.1678, "lr": 1.907970177684737e-08, "epoch": 6.914971309337506, "percentage": 98.76, "elapsed_time": "1 day, 13:13:57", "remaining_time": "0:27:57"}
+{"current_steps": 6635, "total_steps": 6713, "loss": 0.1792, "lr": 1.687621967875863e-08, "epoch": 6.92018779342723, "percentage": 98.84, "elapsed_time": "1 day, 13:16:39", "remaining_time": "0:26:17"}
+{"current_steps": 6640, "total_steps": 6713, "loss": 0.1761, "lr": 1.4807846872113563e-08, "epoch": 6.925404277516954, "percentage": 98.91, "elapsed_time": "1 day, 13:19:15", "remaining_time": "0:24:37"}
+{"current_steps": 6645, "total_steps": 6713, "loss": 0.1716, "lr": 1.2874597341534512e-08, "epoch": 6.9306207616066775, "percentage": 98.99, "elapsed_time": "1 day, 13:21:50", "remaining_time": "0:22:56"}
+{"current_steps": 6650, "total_steps": 6713, "loss": 0.1653, "lr": 1.1076484158047962e-08, "epoch": 6.9358372456964, "percentage": 99.06, "elapsed_time": "1 day, 13:24:28", "remaining_time": "0:21:15"}
+{"current_steps": 6655, "total_steps": 6713, "loss": 0.1697, "lr": 9.413519479004596e-09, "epoch": 6.941053729786124, "percentage": 99.14, "elapsed_time": "1 day, 13:27:10", "remaining_time": "0:19:35"}
+{"current_steps": 6660, "total_steps": 6713, "loss": 0.1732, "lr": 7.885714547990475e-09, "epoch": 6.946270213875848, "percentage": 99.21, "elapsed_time": "1 day, 13:29:53", "remaining_time": "0:17:54"}
+{"current_steps": 6665, "total_steps": 6713, "loss": 0.1772, "lr": 6.493079694753768e-09, "epoch": 6.951486697965571, "percentage": 99.28, "elapsed_time": "1 day, 13:32:23", "remaining_time": "0:16:13"}
+{"current_steps": 6670, "total_steps": 6713, "loss": 0.17, "lr": 5.235624335133693e-09, "epoch": 6.9567031820552945, "percentage": 99.36, "elapsed_time": "1 day, 13:35:08", "remaining_time": "0:14:32"}
+{"current_steps": 6675, "total_steps": 6713, "loss": 0.1552, "lr": 4.113356971002791e-09, "epoch": 6.961919666145018, "percentage": 99.43, "elapsed_time": "1 day, 13:37:55", "remaining_time": "0:12:51"}
+{"current_steps": 6680, "total_steps": 6713, "loss": 0.1602, "lr": 3.126285190195866e-09, "epoch": 6.967136150234742, "percentage": 99.51, "elapsed_time": "1 day, 13:40:48", "remaining_time": "0:11:10"}
+{"current_steps": 6685, "total_steps": 6713, "loss": 0.1675, "lr": 2.2744156664766813e-09, "epoch": 6.972352634324466, "percentage": 99.58, "elapsed_time": "1 day, 13:43:36", "remaining_time": "0:09:28"}
+{"current_steps": 6690, "total_steps": 6713, "loss": 0.1663, "lr": 1.5577541594802293e-09, "epoch": 6.977569118414189, "percentage": 99.66, "elapsed_time": "1 day, 13:46:24", "remaining_time": "0:07:47"}
+{"current_steps": 6695, "total_steps": 6713, "loss": 0.1704, "lr": 9.7630551467498e-10, "epoch": 6.982785602503912, "percentage": 99.73, "elapsed_time": "1 day, 13:49:07", "remaining_time": "0:06:06"}
+{"current_steps": 6700, "total_steps": 6713, "loss": 0.1686, "lr": 5.300736633317982e-10, "epoch": 6.988002086593636, "percentage": 99.81, "elapsed_time": "1 day, 13:51:48", "remaining_time": "0:04:24"}
+{"current_steps": 6705, "total_steps": 6713, "loss": 0.1629, "lr": 2.1906162250395768e-10, "epoch": 6.993218570683359, "percentage": 99.88, "elapsed_time": "1 day, 13:54:41", "remaining_time": "0:02:42"}
+{"current_steps": 6710, "total_steps": 6713, "loss": 0.1818, "lr": 4.3271494996055544e-11, "epoch": 6.998435054773083, "percentage": 99.96, "elapsed_time": "1 day, 13:57:18", "remaining_time": "0:01:01"}
+{"current_steps": 6712, "total_steps": 6713, "epoch": 7.0, "percentage": 99.99, "elapsed_time": "1 day, 13:58:08", "remaining_time": "0:00:20"}