Model save
Browse files- README.md +1 -1
- model-00001-of-00004.safetensors +1 -1
- model-00002-of-00004.safetensors +1 -1
- model-00003-of-00004.safetensors +1 -1
- model-00004-of-00004.safetensors +1 -1
- run_summary.json +2 -2
- trainer_log.jsonl +17 -29
- training_args.bin +1 -1
README.md
CHANGED
|
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 16 |
|
| 17 |
# freelancer-projects-1k-traces
|
| 18 |
|
| 19 |
-
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
|
|
|
| 16 |
|
| 17 |
# freelancer-projects-1k-traces
|
| 18 |
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on an unknown dataset.
|
| 20 |
|
| 21 |
## Model description
|
| 22 |
|
model-00001-of-00004.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 4902257696
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac1b735b21cd640610eb2f1d9abd268a4b91df5440a1864b1a813cdd466a1521
|
| 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:
|
| 3 |
size 4915960368
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:39b32c80a2e204b38cd666c0c8b88217e8d70eee4922085a4f1107a14f3bdb64
|
| 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:
|
| 3 |
size 4983068496
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8eca6ac7b42b6dbdaa3da672ab91e2ffacf70f3b56f04f5290b56454366c65c7
|
| 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:
|
| 3 |
size 1580230264
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf6ac415391039b2ada07a72842e590ebc80e12ba95e2363032e1b70bd529550
|
| 3 |
size 1580230264
|
run_summary.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"agent_name": null,
|
| 3 |
-
"training_start":
|
| 4 |
"training_end": null,
|
| 5 |
"created_by": "DCAgent",
|
| 6 |
"base_model_name": "Qwen/Qwen3-8B",
|
| 7 |
"dataset_name": "DCAgent/freelancer-projects-1k-traces",
|
| 8 |
"training_type": "SFT",
|
| 9 |
"training_parameters": "https://huggingface.co/DCAgent/freelancer-projects-1k-traces/blob/main/config.json",
|
| 10 |
-
"wandb_link": "https://wandb.ai/
|
| 11 |
"traces_location_s3": null
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"agent_name": null,
|
| 3 |
+
"training_start": "2025-10-21T08:04:10Z",
|
| 4 |
"training_end": null,
|
| 5 |
"created_by": "DCAgent",
|
| 6 |
"base_model_name": "Qwen/Qwen3-8B",
|
| 7 |
"dataset_name": "DCAgent/freelancer-projects-1k-traces",
|
| 8 |
"training_type": "SFT",
|
| 9 |
"training_parameters": "https://huggingface.co/DCAgent/freelancer-projects-1k-traces/blob/main/config.json",
|
| 10 |
+
"wandb_link": "https://wandb.ai/dogml/dc-agent/runs/freelancer-projects-1k-traces",
|
| 11 |
"traces_location_s3": null
|
| 12 |
}
|
trainer_log.jsonl
CHANGED
|
@@ -1,29 +1,17 @@
|
|
| 1 |
-
{"current_steps":
|
| 2 |
-
{"current_steps":
|
| 3 |
-
{"current_steps":
|
| 4 |
-
{"current_steps":
|
| 5 |
-
{"current_steps":
|
| 6 |
-
{"current_steps":
|
| 7 |
-
{"current_steps":
|
| 8 |
-
{"current_steps":
|
| 9 |
-
{"current_steps":
|
| 10 |
-
{"current_steps":
|
| 11 |
-
{"current_steps": 55, "total_steps": 80, "loss": 0.5323, "lr": 1.1547634765186016e-05, "epoch": 3.448, "percentage": 68.75, "elapsed_time": "
|
| 12 |
-
{"current_steps":
|
| 13 |
-
{"current_steps":
|
| 14 |
-
{"current_steps":
|
| 15 |
-
{"current_steps":
|
| 16 |
-
{"current_steps":
|
| 17 |
-
{"current_steps":
|
| 18 |
-
{"current_steps": 45, "total_steps": 80, "loss": 0.5482, "lr": 2e-05, "epoch": 2.832, "percentage": 56.25, "elapsed_time": "0:49:21", "remaining_time": "0:38:23"}
|
| 19 |
-
{"current_steps": 75, "total_steps": 80, "loss": 0.5152, "lr": 6.814834742186361e-07, "epoch": 4.704, "percentage": 93.75, "elapsed_time": "1:20:34", "remaining_time": "0:05:22"}
|
| 20 |
-
{"current_steps": 50, "total_steps": 80, "loss": 0.5278, "lr": 1.5671207721237945e-05, "epoch": 3.128, "percentage": 62.5, "elapsed_time": "0:54:27", "remaining_time": "0:32:40"}
|
| 21 |
-
{"current_steps": 80, "total_steps": 80, "loss": 0.5091, "lr": 1.9035568362844037e-08, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:25:52", "remaining_time": "0:00:00"}
|
| 22 |
-
{"current_steps": 80, "total_steps": 80, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:25:52", "remaining_time": "0:00:00"}
|
| 23 |
-
{"current_steps": 55, "total_steps": 80, "loss": 0.5317, "lr": 1.1547634765186016e-05, "epoch": 3.448, "percentage": 68.75, "elapsed_time": "1:00:02", "remaining_time": "0:27:17"}
|
| 24 |
-
{"current_steps": 60, "total_steps": 80, "loss": 0.5294, "lr": 7.824771419825588e-06, "epoch": 3.768, "percentage": 75.0, "elapsed_time": "1:05:23", "remaining_time": "0:21:47"}
|
| 25 |
-
{"current_steps": 65, "total_steps": 80, "loss": 0.5094, "lr": 4.679111137620442e-06, "epoch": 4.064, "percentage": 81.25, "elapsed_time": "1:10:26", "remaining_time": "0:16:15"}
|
| 26 |
-
{"current_steps": 70, "total_steps": 80, "loss": 0.5321, "lr": 2.259783336435566e-06, "epoch": 4.384, "percentage": 87.5, "elapsed_time": "1:15:44", "remaining_time": "0:10:49"}
|
| 27 |
-
{"current_steps": 75, "total_steps": 80, "loss": 0.5144, "lr": 6.814834742186361e-07, "epoch": 4.704, "percentage": 93.75, "elapsed_time": "1:21:10", "remaining_time": "0:05:24"}
|
| 28 |
-
{"current_steps": 80, "total_steps": 80, "loss": 0.5083, "lr": 1.9035568362844037e-08, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:26:29", "remaining_time": "0:00:00"}
|
| 29 |
-
{"current_steps": 80, "total_steps": 80, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "1:26:29", "remaining_time": "0:00:00"}
|
|
|
|
| 1 |
+
{"current_steps": 5, "total_steps": 80, "loss": 0.7923, "lr": 2e-05, "epoch": 0.32, "percentage": 6.25, "elapsed_time": "0:11:42", "remaining_time": "2:55:38"}
|
| 2 |
+
{"current_steps": 10, "total_steps": 80, "loss": 0.6915, "lr": 3.998096443163716e-05, "epoch": 0.64, "percentage": 12.5, "elapsed_time": "0:23:23", "remaining_time": "2:43:42"}
|
| 3 |
+
{"current_steps": 15, "total_steps": 80, "loss": 0.6339, "lr": 3.931851652578137e-05, "epoch": 0.96, "percentage": 18.75, "elapsed_time": "0:35:02", "remaining_time": "2:31:48"}
|
| 4 |
+
{"current_steps": 20, "total_steps": 80, "loss": 0.5937, "lr": 3.774021666356444e-05, "epoch": 1.256, "percentage": 25.0, "elapsed_time": "0:45:40", "remaining_time": "2:17:00"}
|
| 5 |
+
{"current_steps": 25, "total_steps": 80, "loss": 0.5791, "lr": 3.532088886237956e-05, "epoch": 1.576, "percentage": 31.25, "elapsed_time": "0:56:37", "remaining_time": "2:04:35"}
|
| 6 |
+
{"current_steps": 30, "total_steps": 80, "loss": 0.5804, "lr": 3.217522858017442e-05, "epoch": 1.896, "percentage": 37.5, "elapsed_time": "1:08:05", "remaining_time": "1:53:29"}
|
| 7 |
+
{"current_steps": 35, "total_steps": 80, "loss": 0.569, "lr": 2.8452365234813992e-05, "epoch": 2.192, "percentage": 43.75, "elapsed_time": "1:18:03", "remaining_time": "1:40:21"}
|
| 8 |
+
{"current_steps": 40, "total_steps": 80, "loss": 0.5312, "lr": 2.4328792278762058e-05, "epoch": 2.512, "percentage": 50.0, "elapsed_time": "1:29:10", "remaining_time": "1:29:10"}
|
| 9 |
+
{"current_steps": 45, "total_steps": 80, "loss": 0.5487, "lr": 2e-05, "epoch": 2.832, "percentage": 56.25, "elapsed_time": "1:40:15", "remaining_time": "1:17:58"}
|
| 10 |
+
{"current_steps": 50, "total_steps": 80, "loss": 0.5284, "lr": 1.5671207721237945e-05, "epoch": 3.128, "percentage": 62.5, "elapsed_time": "1:50:37", "remaining_time": "1:06:22"}
|
| 11 |
+
{"current_steps": 55, "total_steps": 80, "loss": 0.5323, "lr": 1.1547634765186016e-05, "epoch": 3.448, "percentage": 68.75, "elapsed_time": "2:02:01", "remaining_time": "0:55:27"}
|
| 12 |
+
{"current_steps": 60, "total_steps": 80, "loss": 0.5299, "lr": 7.824771419825588e-06, "epoch": 3.768, "percentage": 75.0, "elapsed_time": "2:12:55", "remaining_time": "0:44:18"}
|
| 13 |
+
{"current_steps": 65, "total_steps": 80, "loss": 0.5101, "lr": 4.679111137620442e-06, "epoch": 4.064, "percentage": 81.25, "elapsed_time": "2:23:15", "remaining_time": "0:33:03"}
|
| 14 |
+
{"current_steps": 70, "total_steps": 80, "loss": 0.5329, "lr": 2.259783336435566e-06, "epoch": 4.384, "percentage": 87.5, "elapsed_time": "2:34:05", "remaining_time": "0:22:00"}
|
| 15 |
+
{"current_steps": 75, "total_steps": 80, "loss": 0.5152, "lr": 6.814834742186361e-07, "epoch": 4.704, "percentage": 93.75, "elapsed_time": "2:45:09", "remaining_time": "0:11:00"}
|
| 16 |
+
{"current_steps": 80, "total_steps": 80, "loss": 0.509, "lr": 1.9035568362844037e-08, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "2:55:57", "remaining_time": "0:00:00"}
|
| 17 |
+
{"current_steps": 80, "total_steps": 80, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "2:55:57", "remaining_time": "0:00:00"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
training_args.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8529
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a3d5acc6be183b311833c52531e4262d356e274cd56c5e80799d43b10001b97
|
| 3 |
size 8529
|