Upload model

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: openmathreasoning_300k
+  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. -->
+
+# openmathreasoning_300k
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct) on the mlfoundations-dev/openmathreasoning_300k 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: 8e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 512
+- total_eval_batch_size: 128
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.5.0a0+b465a5843b.nv24.09
+- Datasets 3.5.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.997262581596125,
+    "total_flos": 3.94117975967185e+19,
+    "train_loss": 0.06913654437741718,
+    "train_runtime": 69116.03,
+    "train_samples_per_second": 10.993,
+    "train_steps_per_second": 0.021
+}

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "_name_or_path": "/p/data1/mmlaion/dcft/hub/models--Qwen--Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
   "architectures": [
     "Qwen2ForCausalLM"
   ],

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1f5931ccb930ed9f6d6a5eddd29d1f6b974101538ad080489ae08f69e984530
+oid sha256:7729e8bf7075a3fc8449a74f328e04d036daca696abd2b1efab91efc2f5c6761
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34924893d7b1bf6866440eaa72fac0bd949b30984ce63502230728c3d059408a
+oid sha256:c86598bce672e7ae057bcf229fc403332e9012fbf4782b2d3c9d9f8262d3545d
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa2a22daaf7720b488f8a81663e34505ddfb6ffae4bb7d2d302b4b1d17fce08e
+oid sha256:3bc1f25ed52554ff971c11ad2da5e016c4bcc7015d290a1557cdc36002dbbe3e
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3183111a7d7a8bb7e7ff2d219361a454324196ff5f6f152452c6fd52ff47d91
+oid sha256:b86141c7e4974e09df7168b7a7d7df836b19eab1ea90a96d9d4e7b17f3910612
 size 1089994880

runs/May16_00-51-56_jrc0917/events.out.tfevents.1747349858.jrc0917.1676126.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa3254dd594aa99d33b0cfb8370da510836e28d530d7fcb2fc20ef916cc42ab
+size 79281

runs/May17_00-55-10_jrc0912/events.out.tfevents.1747436468.jrc0912.4192221.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bad14101dd60129fc49f216e6fae88e3048d4f581d00f0bc6abf91388d703364
+size 83234

runs/May18_00-58-14_jrc0912/events.out.tfevents.1747523040.jrc0912.220060.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cb67965d545a8f86af4f0eac1bb2cf3a9090ec5a40ac120ea9290e0dec84899
+size 83234

runs/May19_01-01-22_jrc0911/events.out.tfevents.1747609625.jrc0911.1223953.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ba9959299f3d911d3301ba45732507ee9b2a21a5d500831c90841fdaeea5705
+size 83234

runs/May20_01-04-39_jrc0911/events.out.tfevents.1747696231.jrc0911.1444783.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:659a06d75be5989c831f5d2bc27a16e142472e53e7e331a15b3f458202638437
+size 68397

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-05-20 01:04:39", "end_time": "2025-05-20 20:22:38"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.997262581596125,
+    "total_flos": 3.94117975967185e+19,
+    "train_loss": 0.06913654437741718,
+    "train_runtime": 69116.03,
+    "train_samples_per_second": 10.993,
+    "train_steps_per_second": 0.021
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af75f5d80d8bdadd56ce7171ee5ae3a928dced0fbe2601c188cf10b0c3eaf5a
-size 7160
+oid sha256:9e85b7d6e66644a292bc8c34c46e7e1229adfd0c39d2717e7b32a279b5fca98a
+size 7416