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: b2_science_fasttext_neg_all
+  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. -->
+
+# b2_science_fasttext_neg_all
+
+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/b2_science_fasttext_neg_all 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: 32
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 256
+- optimizer: Use OptimizerNames.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 2.6.0a0+ecf3bae40a.nv25.01
+- Datasets 3.5.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1.1404623141058642e+18,
+    "train_loss": 0.39826868520936504,
+    "train_runtime": 17206.7809,
+    "train_samples_per_second": 9.182,
+    "train_steps_per_second": 0.072
+}

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:b622dd7a8fff5937095bcfa0625364d8c7cfe9c951a984f1d784e99bc76c0b9b
+oid sha256:486a87d58eb37eec6d5e175bcb60c8036b626618606cef199996688dbe570b3b
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eacc29c5b6fcd9ba29f11b83deb241078236810d4803d51dfbad7612d19a3c4d
+oid sha256:605b7323354e4518b413c62fe4353834f082e6396cb63cf13b66175941e97506
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9c409a8692209f597643eb27eb0f35b362135fd2e0169e16621bba2b9647b13
+oid sha256:61f2f64b36970519ddc124bf8223e5ec56244a9ab99bf9571c35374958b8349b
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39288bddbdae8271476ec5614b9d87effd8a080b8e9c836620853d1d8b035c54
+oid sha256:ffb1f2786a6cd1f62d2e04375ad3e9ee3abdac7a089d07cb80fb675405765555
 size 1089994880

runs/Apr24_14-25-29_jpbot-001-34.jupiter.internal/events.out.tfevents.1745497577.jpbot-001-34.jupiter.internal.943066.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36dd9c7185fecac636d4ccef22ffe7b8c9d48a7f30efcf48175253f5c256cd8b
+size 265989

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-04-24 14:25:29", "end_time": "2025-04-24 19:13:10"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "total_flos": 1.1404623141058642e+18,
+    "train_loss": 0.39826868520936504,
+    "train_runtime": 17206.7809,
+    "train_samples_per_second": 9.182,
+    "train_steps_per_second": 0.072
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f324ecce1c8bae6327c5feaabec0f9980a89848dfaa5cf88746e175c4bbf1a0
-size 7288
+oid sha256:d9193ae167ab6c96d684d347afa2dce3ccbfabfc25d0e37eecb8416fba921833
+size 7352