Hugging Face's logo

DCAgent
/
a1-magicoder

Text Generation
Transformers
Safetensors
qwen3
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Model card Files
xet
 Community
EtashGuha commited on
Commit
7114d11
·
verified ·
1 Parent(s): f436e9b

Upload folder using huggingface_hub

Browse files
Files changed (8) hide show
  1. all_results.json +9 -9
  2. model-00001-of-00004.safetensors +1 -1
  3. model-00002-of-00004.safetensors +1 -1
  4. model-00003-of-00004.safetensors +1 -1
  5. model-00004-of-00004.safetensors +1 -1
  6. train_results.json +9 -9
  7. trainer_log.jsonl +0 -0
  8. training_loss.png +0 -0
all_results.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "achieved_tflops_per_gpu": 0.002110187398451811,
3
- "achieved_tflops_per_gpu_theoretical": 650.4776760620482,
4
  "epoch": 7.0,
5
  "loss_nan_ranks": 0,
6
- "loss_rank_avg": 0.2384590357542038,
7
- "mfu_percent": 0.00014912985148069337,
8
- "mfu_percent_theoretical": 45.97015378530376,
9
  "total_flos": 688651439570944.0,
10
- "train_loss": 0.26049303336732077,
11
- "train_runtime": 20396.6316,
12
- "train_samples_per_second": 3.064,
13
- "train_steps_per_second": 0.192,
14
  "valid_targets_mean": 4082.4,
15
  "valid_targets_min": 866
16
  }
 
1
  {
2
+ "achieved_tflops_per_gpu": 0.002083037344637663,
3
+ "achieved_tflops_per_gpu_theoretical": 640.3139623735788,
4
  "epoch": 7.0,
5
  "loss_nan_ranks": 0,
6
+ "loss_rank_avg": 0.2396668791770935,
7
+ "mfu_percent": 0.000147211119762379,
8
+ "mfu_percent_theoretical": 45.25187013240839,
9
  "total_flos": 688651439570944.0,
10
+ "train_loss": 0.26112440031201767,
11
+ "train_runtime": 20662.4788,
12
+ "train_samples_per_second": 3.025,
13
+ "train_steps_per_second": 0.189,
14
  "valid_targets_mean": 4082.4,
15
  "valid_targets_min": 866
16
  }
model-00001-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:daffa32e7444e736a1c517d62c2a55d9f96260371213ac37e97ac9827b55b478
3
  size 4902257696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47f3aa434710f7fda3f3fa23057b2e062a6aa19ca2d59a9b13e40fdd97429883
3
  size 4902257696
model-00002-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dfe4bb96e03e07782586ca63884f59543a475c5932ac4ccf440848b3736ff540
3
  size 4915960368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1a0fd930bff3c69df9149615c3cf4e670eed5c7a0c04e8c233a8bab64be4fac
3
  size 4915960368
model-00003-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc931313941b618ca7de44a63927fa3a1e43ed4b723a103c01493d683889d17b
3
  size 4983068496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dca3424fb65168ebb5b237c408c5676171d377664a4284a3e8789d97f07f9644
3
  size 4983068496
model-00004-of-00004.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7ab55fd4c4fd1cdb8d41f5aee283940231d28eba52cc99ebf70cf3cbf11b598d
3
  size 1580230264
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ee02a580f9fe64b849fa281316175c784a52a8823b4120b1f3a7330abd09598
3
  size 1580230264
train_results.json CHANGED
@@ -1,16 +1,16 @@
1
  {
2
- "achieved_tflops_per_gpu": 0.002110187398451811,
3
- "achieved_tflops_per_gpu_theoretical": 650.4776760620482,
4
  "epoch": 7.0,
5
  "loss_nan_ranks": 0,
6
- "loss_rank_avg": 0.2384590357542038,
7
- "mfu_percent": 0.00014912985148069337,
8
- "mfu_percent_theoretical": 45.97015378530376,
9
  "total_flos": 688651439570944.0,
10
- "train_loss": 0.26049303336732077,
11
- "train_runtime": 20396.6316,
12
- "train_samples_per_second": 3.064,
13
- "train_steps_per_second": 0.192,
14
  "valid_targets_mean": 4082.4,
15
  "valid_targets_min": 866
16
  }
 
1
  {
2
+ "achieved_tflops_per_gpu": 0.002083037344637663,
3
+ "achieved_tflops_per_gpu_theoretical": 640.3139623735788,
4
  "epoch": 7.0,
5
  "loss_nan_ranks": 0,
6
+ "loss_rank_avg": 0.2396668791770935,
7
+ "mfu_percent": 0.000147211119762379,
8
+ "mfu_percent_theoretical": 45.25187013240839,
9
  "total_flos": 688651439570944.0,
10
+ "train_loss": 0.26112440031201767,
11
+ "train_runtime": 20662.4788,
12
+ "train_samples_per_second": 3.025,
13
+ "train_steps_per_second": 0.189,
14
  "valid_targets_mean": 4082.4,
15
  "valid_targets_min": 866
16
  }
trainer_log.jsonl CHANGED
The diff for this file is too large to render. See raw diff
 
training_loss.png CHANGED