Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +29 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-10744/adapter_model.safetensors +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-10744/optimizer.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-10744/rng_state.pth +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-10744/scheduler.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-10744/tokenizer.json +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-10744/training_args.bin +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-13430/adapter_model.safetensors +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-13430/optimizer.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-13430/rng_state.pth +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-13430/scheduler.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-13430/tokenizer.json +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-13430/training_args.bin +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-16116/adapter_model.safetensors +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-16116/optimizer.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-16116/rng_state.pth +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-16116/scheduler.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-16116/tokenizer.json +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-16116/training_args.bin +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-18802/adapter_model.safetensors +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-18802/optimizer.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-18802/rng_state.pth +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-18802/scheduler.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-18802/tokenizer.json +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-18802/training_args.bin +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-21488/adapter_model.safetensors +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-21488/optimizer.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-21488/rng_state.pth +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-21488/scheduler.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-21488/tokenizer.json +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-21488/training_args.bin +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-24174/adapter_model.safetensors +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-24174/optimizer.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-24174/rng_state.pth +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-24174/scheduler.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-24174/tokenizer.json +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-24174/training_args.bin +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-2686/adapter_model.safetensors +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-2686/optimizer.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-2686/rng_state.pth +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-2686/scheduler.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-2686/tokenizer.json +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-2686/training_args.bin +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-26860/adapter_model.safetensors +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-26860/optimizer.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-26860/rng_state.pth +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-26860/scheduler.pt +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-26860/tokenizer.json +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-26860/training_args.bin +3 -0
- sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-29546/adapter_model.safetensors +3 -0
.gitattributes
CHANGED
|
@@ -402,3 +402,32 @@ sft/20250419_012050_sftqwen2a-full-resume-goodcpkt-loraopt-5e-16bs-0.0002/checkp
|
|
| 402 |
sft/20250419_012050_sftqwen2a-full-resume-goodcpkt-loraopt-5e-16bs-0.0002/checkpoint-9339/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 403 |
sft/20250419_012050_sftqwen2a-full-resume-goodcpkt-loraopt-5e-16bs-0.0002/checkpoint-12452/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 404 |
sft/20250419_012050_sftqwen2a-full-resume-goodcpkt-loraopt-5e-16bs-0.0002/checkpoint-40469/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 402 |
sft/20250419_012050_sftqwen2a-full-resume-goodcpkt-loraopt-5e-16bs-0.0002/checkpoint-9339/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 403 |
sft/20250419_012050_sftqwen2a-full-resume-goodcpkt-loraopt-5e-16bs-0.0002/checkpoint-12452/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 404 |
sft/20250419_012050_sftqwen2a-full-resume-goodcpkt-loraopt-5e-16bs-0.0002/checkpoint-40469/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 405 |
+
sft/20250418_145854_sftqwen2a-full-semantic-loraopt-5e-24bs-0.0002/checkpoint-4150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 406 |
+
sft/20250418_161400_sftqwen2a-full-semantic-loraopt-5e-24bs-0.0002/checkpoint-6225/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 407 |
+
sft/20250418_161400_sftqwen2a-full-semantic-loraopt-5e-24bs-0.0002/checkpoint-8300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 408 |
+
sft/20250418_161400_sftqwen2a-full-semantic-loraopt-5e-24bs-0.0002/checkpoint-14525/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 409 |
+
sft/20250418_161400_sftqwen2a-full-semantic-loraopt-5e-24bs-0.0002/checkpoint-2075/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 410 |
+
sft/20250418_161400_sftqwen2a-full-semantic-loraopt-5e-24bs-0.0002/checkpoint-10375/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 411 |
+
sft/20250418_161400_sftqwen2a-full-semantic-loraopt-5e-24bs-0.0002/checkpoint-12450/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 412 |
+
sft/20250418_161400_sftqwen2a-full-semantic-loraopt-5e-24bs-0.0002/checkpoint-4150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 413 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-29546/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 414 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-5372/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 415 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-26860/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 416 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-37604/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 417 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-51034/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 418 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-16116/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 419 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-53739/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 420 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-53720/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 421 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-2686/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 422 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-18802/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 423 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-42976/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 424 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-10744/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 425 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-24174/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 426 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-13430/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 427 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-32232/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 428 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-45662/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 429 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-21488/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 430 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-40290/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 431 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-48348/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 432 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-34918/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 433 |
+
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-8058/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-10744/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64f902c738272e23a32134c9d5cf8b1727395bf91245b7d227dd36a328b002e8
|
| 3 |
+
size 22056664
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-10744/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9d0e3fef8b2f9c4ea1db19e87e77f2519424fc4319a35abab4b6ef71160f8f42
|
| 3 |
+
size 44254970
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-10744/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26be2cccb586fc13e3757cca94d45eed5926556b42fe427c46d1fd06ac869e66
|
| 3 |
+
size 14244
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-10744/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9390b9e9db87e54d8e521ede424adf2a309a2322eef78fb32a1577e0a763a8e9
|
| 3 |
+
size 1064
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-10744/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
|
| 3 |
+
size 12030779
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-10744/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74a211a4d505615828f67a8675b15a75cb9fac8eb0a5e1a8f73f9ed1e9f52629
|
| 3 |
+
size 5944
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-13430/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b6eebd9120c5247d877d7add8ecbe040058ffbd5dc3aecd1bc0bab4f0848f51c
|
| 3 |
+
size 22056664
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-13430/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c89726261c0e5c8e8cfebc302d149f792122e4683e6992ec20c05b4cb4bd2604
|
| 3 |
+
size 44254970
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-13430/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c6fdeae615e6342575db1f40dde800655cfdac7f21aa3a2cfe6b146b90a2661
|
| 3 |
+
size 14244
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-13430/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad1e3f24d4934f23196be340c43ed5007466843344d424cfb13d50ed820dba18
|
| 3 |
+
size 1064
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-13430/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
|
| 3 |
+
size 12030779
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-13430/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74a211a4d505615828f67a8675b15a75cb9fac8eb0a5e1a8f73f9ed1e9f52629
|
| 3 |
+
size 5944
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-16116/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03d1a762f168ad22baad17f5f787011e0a209d93f8c12bb4741179d4bf8df8d0
|
| 3 |
+
size 22056664
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-16116/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:996029b98768b6ce37a727f2c2f9758b2222e015eda3f31ea7d4c279a605bb54
|
| 3 |
+
size 44254970
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-16116/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:82589919e5836277ce6c6998ebc9b5f40da5025f49943d1a18b108bdc299b863
|
| 3 |
+
size 14244
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-16116/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7219b3c3871149d953c49138c163644ad547dc27e30f0e7ea00ba5373b314bd7
|
| 3 |
+
size 1064
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-16116/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
|
| 3 |
+
size 12030779
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-16116/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74a211a4d505615828f67a8675b15a75cb9fac8eb0a5e1a8f73f9ed1e9f52629
|
| 3 |
+
size 5944
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-18802/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:19500295049324e68dd8ce48107138b570b119b5eec0037cca849433505ca456
|
| 3 |
+
size 22056664
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-18802/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eea9e00a70b2b02cad50fcd66f6ba7c60324b343f29575b772d045c6c360e126
|
| 3 |
+
size 44254970
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-18802/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:594416d2fa38e9051a40b895ad343e90d5db1868ac8adff09ac293e60e4ad337
|
| 3 |
+
size 14244
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-18802/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dd940c42ff107363306c4110ec5798c6272c344f54c3bbd003169ccb2577342
|
| 3 |
+
size 1064
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-18802/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
|
| 3 |
+
size 12030779
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-18802/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74a211a4d505615828f67a8675b15a75cb9fac8eb0a5e1a8f73f9ed1e9f52629
|
| 3 |
+
size 5944
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-21488/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1969e1aba6c22ed771eab1ce9beaf2a2f2e5da09c267ae76653a0fcc1e17f58
|
| 3 |
+
size 22056664
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-21488/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59f3ea874cb8c2d3ad042eddded63ee960899178edaa0a3a5ebddec8343b41f3
|
| 3 |
+
size 44254970
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-21488/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7fb52a50498dc8c601801234d9be5655b85071884d20a062ccff691d72c3c4cd
|
| 3 |
+
size 14244
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-21488/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c555d863e46352f24f39fa03c88fffab0c55ed5c3c024fdf74ec4deb94f2869
|
| 3 |
+
size 1064
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-21488/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
|
| 3 |
+
size 12030779
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-21488/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74a211a4d505615828f67a8675b15a75cb9fac8eb0a5e1a8f73f9ed1e9f52629
|
| 3 |
+
size 5944
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-24174/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:417384d304637c33b7707fe237843e4f6ea0d412d19236ce52d30195033c998a
|
| 3 |
+
size 22056664
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-24174/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f76b66c30489b237819d150100939eafd91d1e79134198ee5d960f124e2597b2
|
| 3 |
+
size 44254970
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-24174/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d70e6a6935ecd06a4e4f698efc077803dbf96adae01bfeb38e75cda130e751b8
|
| 3 |
+
size 14244
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-24174/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f2f5e6a843408d82d41270d63f8bab0bfb6b9fd12f3293b61024e51f8d2f1eb0
|
| 3 |
+
size 1064
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-24174/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
|
| 3 |
+
size 12030779
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-24174/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74a211a4d505615828f67a8675b15a75cb9fac8eb0a5e1a8f73f9ed1e9f52629
|
| 3 |
+
size 5944
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-2686/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a77770329e8ad9436cee725f20c0c4619edab3bbc01403f31ccba4c5bc15770d
|
| 3 |
+
size 22056664
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-2686/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:609d6ba7d1476e925de60b31382d3686e8ab5d63c5659a016d26cf8648b647ff
|
| 3 |
+
size 44254970
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-2686/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:533c61404d774d92999e249e3d2a6e6186f3c32af19973a17e954cb989161a08
|
| 3 |
+
size 14244
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-2686/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4b9bde912a15d35176ce89b4105b407cd5427678e97e1b702c4929f2698551a0
|
| 3 |
+
size 1064
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-2686/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
|
| 3 |
+
size 12030779
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-2686/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74a211a4d505615828f67a8675b15a75cb9fac8eb0a5e1a8f73f9ed1e9f52629
|
| 3 |
+
size 5944
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-26860/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6634bd70738ed94caeb989fc368b5343a881de8d102391854ccb0558d48a05e
|
| 3 |
+
size 22056664
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-26860/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b06f8ff6791f055d18e0307334687927e1ced13be8cb011ac0405f93e5a0e2c
|
| 3 |
+
size 44254970
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-26860/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:414ee90a47ab3707b88970094639a2e0a8b679d00390c9179c1bf52d898c99be
|
| 3 |
+
size 14244
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-26860/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5536994a280158c6388b8e8a9a17ee51d52cefc0f6a2087dd41cea97ac954f2b
|
| 3 |
+
size 1064
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-26860/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fecdb47d281073055efd605d080013e3114ed0f3c5d8af201e245b199864c9c7
|
| 3 |
+
size 12030779
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-26860/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74a211a4d505615828f67a8675b15a75cb9fac8eb0a5e1a8f73f9ed1e9f52629
|
| 3 |
+
size 5944
|
sft/20250404_031003_sfttraining_qwen2.5_simple-loraopt-2e-6bs-0.0002/checkpoint-29546/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fc543e8d8a2a697bbf33a37942b3487955bffca099df43a2cd81b92771c36057
|
| 3 |
+
size 22056664
|