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: am_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. -->
+
+# am_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/am_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": 4.989094874591058,
+    "total_flos": 1.517527475894721e+19,
+    "train_loss": 0.18812398983721149,
+    "train_runtime": 53023.3041,
+    "train_samples_per_second": 5.533,
+    "train_steps_per_second": 0.011
+}

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:eda6cabeba77cc43015a179bfac36fa3175635f9f551ddd302e455d07b3b7765
+oid sha256:b725862e1a49961467e9500eb9ad0869a5e391d7951c76b0fe6a7e0eac6ff3d4
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:22e5a4925d18fcfae863de4f54e62d07a0027ae113753408e73f645998014083
+oid sha256:bf3dd50ff5510d4bc0a08a8086e09258a270d3ba53387afb2a52374131d279dd
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0091c17eeaef1ec3c2fb76a9933c6451c3aa8332a414073dd47fe2b336741f17
+oid sha256:8aead2f630164a16566219369a66e47c3298a31133c013b7402b9988e51aca05
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06eb52757de476425798c5bd5f9ae9a1b26fde8a4bc6ebcefa5e84ef9c77e187
+oid sha256:254ac2adea5d8c42bb4e1e4eb9d3b11abe5260317d0f7662f96b366314d4e69a
 size 1089994880

runs/May09_23-11-32_jrc0929/events.out.tfevents.1746825268.jrc0929.2178476.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1dbfe850ca34492952eb15ecb5fdd6dcfa41d3008d68bcf94e460368ac0f6509
+size 5664

runs/May09_23-26-27_jrc0932/events.out.tfevents.1746826152.jrc0932.2137577.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff9c0cf8d1269c6731c7af55e9696f8bf17b67e8801f16c707e6f0aea163a13
+size 82808

runs/May10_23-29-46_jrc0936/events.out.tfevents.1746912747.jrc0936.2314569.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0980a53972ac0af48fa6dd6d9d97db249aabd01a4743c1babce38ad84dc490a7
+size 53762

start_end.json

@@ -0,0 +1 @@
+{"start_time": "2025-05-10 23:29:46", "end_time": "2025-05-11 14:16:22"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.989094874591058,
+    "total_flos": 1.517527475894721e+19,
+    "train_loss": 0.18812398983721149,
+    "train_runtime": 53023.3041,
+    "train_samples_per_second": 5.533,
+    "train_steps_per_second": 0.011
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e27c7eeccc0a1d9ead0facd6dd9466bfb4d9868c32eaa398bbcd8bf9fce147f5
-size 7288
+oid sha256:36e7c90be2d76bc5ff25e2f26216103892088d22325c079224b6a0eea8e2deea
+size 7352