End of training
Browse files- README.md +4 -1
- all_results.json +16 -0
- train_results.json +16 -0
- trainer_state.json +0 -0
- training_loss.png +0 -0
README.md
CHANGED
|
@@ -1,7 +1,10 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
|
|
|
|
|
|
| 3 |
tags:
|
| 4 |
- llama-factory
|
|
|
|
| 5 |
- generated_from_trainer
|
| 6 |
model-index:
|
| 7 |
- name: r2egym-nl2bash-stack-bugsseq-fixthink-again
|
|
@@ -13,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 13 |
|
| 14 |
# r2egym-nl2bash-stack-bugsseq-fixthink-again
|
| 15 |
|
| 16 |
-
This model
|
| 17 |
|
| 18 |
## Model description
|
| 19 |
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: Qwen/Qwen3-8B
|
| 5 |
tags:
|
| 6 |
- llama-factory
|
| 7 |
+
- full
|
| 8 |
- generated_from_trainer
|
| 9 |
model-index:
|
| 10 |
- name: r2egym-nl2bash-stack-bugsseq-fixthink-again
|
|
|
|
| 16 |
|
| 17 |
# r2egym-nl2bash-stack-bugsseq-fixthink-again
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--glm-4.6-r2egym-32ep-32k/snapshots/1b98f51e65d71b6dc9702529884355b93b8b8685_thinking_preprocessed, the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--GLM-4.6-nl2bash-verified-32eps-32k/snapshots/61e17458d760f1419c4447abbab4fc93118563dd_thinking_preprocessed, the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k/snapshots/1c13e68d92fc88775a6a593c5ca93a4a4bae0a38_thinking_preprocessed and the /data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--GLM-4.6-inferredbugs-32eps-65k/snapshots/60d83f48605156a6b9182f9b54c6da2d4dffc061_thinking_preprocessed datasets.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
all_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"achieved_tflops_per_gpu": 5.961135004994871,
|
| 3 |
+
"achieved_tflops_per_gpu_theoretical": 528.5131118004142,
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"loss_nan_ranks": 0,
|
| 6 |
+
"loss_rank_avg": 0.04253735765814781,
|
| 7 |
+
"mfu_percent": 0.6027436809903812,
|
| 8 |
+
"mfu_percent_theoretical": 53.439141739172314,
|
| 9 |
+
"total_flos": 3.879727127867687e+18,
|
| 10 |
+
"train_loss": 0.18411178431570632,
|
| 11 |
+
"train_runtime": 81354.623,
|
| 12 |
+
"train_samples_per_second": 2.497,
|
| 13 |
+
"train_steps_per_second": 0.156,
|
| 14 |
+
"valid_targets_mean": 4458.2,
|
| 15 |
+
"valid_targets_min": 1268
|
| 16 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"achieved_tflops_per_gpu": 5.961135004994871,
|
| 3 |
+
"achieved_tflops_per_gpu_theoretical": 528.5131118004142,
|
| 4 |
+
"epoch": 7.0,
|
| 5 |
+
"loss_nan_ranks": 0,
|
| 6 |
+
"loss_rank_avg": 0.04253735765814781,
|
| 7 |
+
"mfu_percent": 0.6027436809903812,
|
| 8 |
+
"mfu_percent_theoretical": 53.439141739172314,
|
| 9 |
+
"total_flos": 3.879727127867687e+18,
|
| 10 |
+
"train_loss": 0.18411178431570632,
|
| 11 |
+
"train_runtime": 81354.623,
|
| 12 |
+
"train_samples_per_second": 2.497,
|
| 13 |
+
"train_steps_per_second": 0.156,
|
| 14 |
+
"valid_targets_mean": 4458.2,
|
| 15 |
+
"valid_targets_min": 1268
|
| 16 |
+
}
|
trainer_state.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_loss.png
ADDED
|