Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- codet5+/q90cce/checkpoint-16161/model.safetensors +3 -0
- codet5+/q90cce/checkpoint-16161/optimizer.pt +3 -0
- codet5+/q90cce/checkpoint-16161/rng_state.pth +3 -0
- codet5+/q90cce/checkpoint-16161/scheduler.pt +3 -0
- codet5+/q90cce/checkpoint-16161/training_args.bin +3 -0
- codet5+/q90cce/final_checkpoint/model.safetensors +3 -0
- codet5+/q90useseq/checkpoint-16161/model.safetensors +3 -0
- codet5+/q90useseq/checkpoint-16161/optimizer.pt +3 -0
- codet5+/q90useseq/checkpoint-16161/rng_state.pth +3 -0
- codet5+/q90useseq/checkpoint-16161/scheduler.pt +3 -0
- codet5+/q90useseq/checkpoint-16161/training_args.bin +3 -0
- codet5+/q90useseq/events.out.tfevents.1712092321.nublar.444200.0 +3 -0
- codet5+/q90useseq/final_checkpoint/model.safetensors +3 -0
- gpt2/cgpt/out-cgpt-e18-cce/ckpt.pt +3 -0
- gpt2/cgpt/out-cgpt-e18-use-seq-0.6/ckpt.pt +3 -0
- gpt2/cgpt/out-cgpt-e18-use-seq-0.8/ckpt.pt +3 -0
- gpt2/cgpt/out-cgpt-e18-use-seq-1.0/ckpt.pt +3 -0
- gpt2/cgpt/out-cgpt-e18-use-seq-1.2/ckpt.pt +3 -0
- gpt2/cgpt/out-cgpt-e18-use-seq-ablate-1.0/ckpt.pt +3 -0
- gpt2/q90/out-funcom-gpt2-e18-cce/ckpt.pt +3 -0
- gpt2/q90/out-funcom-gpt2-e18-use-seq-0.6/ckpt.pt +3 -0
- gpt2/q90/out-funcom-gpt2-e18-use-seq-0.8/ckpt.pt +3 -0
- gpt2/q90/out-funcom-gpt2-e18-use-seq-1.0/ckpt.pt +3 -0
- gpt2/q90/out-funcom-gpt2-e18-use-seq-1.2/ckpt.pt +3 -0
- gpt2/q90/out-funcom-gpt2-e18-use-seq-ablate-1.0/ckpt.pt +3 -0
- llama/lora-alpaca-q90-cce/adapter_config.json +18 -0
- llama/lora-alpaca-q90-cce/adapter_model.bin +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-1000/optimizer.pt +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-1000/pytorch_model.bin +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-1000/rng_state.pth +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-1000/scaler.pt +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-1000/scheduler.pt +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-1000/trainer_state.json +356 -0
- llama/lora-alpaca-q90-cce/checkpoint-1000/training_args.bin +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-1200/optimizer.pt +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-1200/pytorch_model.bin +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-1200/rng_state.pth +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-1200/scaler.pt +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-1200/scheduler.pt +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-1200/trainer_state.json +424 -0
- llama/lora-alpaca-q90-cce/checkpoint-1200/training_args.bin +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-800/optimizer.pt +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-800/pytorch_model.bin +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-800/rng_state.pth +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-800/scaler.pt +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-800/scheduler.pt +3 -0
- llama/lora-alpaca-q90-cce/checkpoint-800/trainer_state.json +288 -0
- llama/lora-alpaca-q90-cce/checkpoint-800/training_args.bin +3 -0
- llama/lora-alpaca-q90-use-seq/adapter_config.json +19 -0
- llama/lora-alpaca-q90-use-seq/adapter_model.bin +3 -0
codet5+/q90cce/checkpoint-16161/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bac365536c3abbcd19ea10781413295f880335e19e5faacc2a80cf87f759c4f3
|
| 3 |
+
size 891558696
|
codet5+/q90cce/checkpoint-16161/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e947fc1a62608cdbd2e727ebf1b77ab2441741b82c210915feaa31490f802d2
|
| 3 |
+
size 1783272762
|
codet5+/q90cce/checkpoint-16161/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da7ab3d70319eedee0e20df99e3337c596300cf85c06a0ff43a497dc735bacc1
|
| 3 |
+
size 14244
|
codet5+/q90cce/checkpoint-16161/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc6074681aa311442c0e33cfb9d6fdc6bf20b16d03df5498cbd742101c5b5b60
|
| 3 |
+
size 1064
|
codet5+/q90cce/checkpoint-16161/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bba5554b9a249566c939cc47d94f0779adfb4a53f5215181d0d81754796270a0
|
| 3 |
+
size 4856
|
codet5+/q90cce/final_checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bac365536c3abbcd19ea10781413295f880335e19e5faacc2a80cf87f759c4f3
|
| 3 |
+
size 891558696
|
codet5+/q90useseq/checkpoint-16161/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ef3dc2c3b199d6303258dcf37018964d5bdbc6ee10174a0a2c22597cee9f407
|
| 3 |
+
size 891558696
|
codet5+/q90useseq/checkpoint-16161/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac9866e8e98bd91dbfa964a33d1bb24d4f288b67351da114cf008c1f2a0a2a0f
|
| 3 |
+
size 1783272762
|
codet5+/q90useseq/checkpoint-16161/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb2897a897fea1e576d8200facf0fd7c6684a305f296fe30fe6c438815665c88
|
| 3 |
+
size 14244
|
codet5+/q90useseq/checkpoint-16161/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cc6074681aa311442c0e33cfb9d6fdc6bf20b16d03df5498cbd742101c5b5b60
|
| 3 |
+
size 1064
|
codet5+/q90useseq/checkpoint-16161/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9310a6cee128577aa0bc565fc71ba9d56a1ecc0f3386594477591138294a4c
|
| 3 |
+
size 4856
|
codet5+/q90useseq/events.out.tfevents.1712092321.nublar.444200.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:64f61fc9afd31fc598f005fd9849bed2e87e11e4bc8944bf58e45f462a482386
|
| 3 |
+
size 346166
|
codet5+/q90useseq/final_checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ef3dc2c3b199d6303258dcf37018964d5bdbc6ee10174a0a2c22597cee9f407
|
| 3 |
+
size 891558696
|
gpt2/cgpt/out-cgpt-e18-cce/ckpt.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84f04aedf6ad2067a3e0f3c07e6baeb77fd44f054169d95b8f137bce69c24ad7
|
| 3 |
+
size 1493434662
|
gpt2/cgpt/out-cgpt-e18-use-seq-0.6/ckpt.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f1d6639eacd08e3920acd816dbf496bbb2c9c6db0b7fb296a014302dbb5daca
|
| 3 |
+
size 1493434662
|
gpt2/cgpt/out-cgpt-e18-use-seq-0.8/ckpt.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb6ae0ea207a5c0e6d630c087f01005a79aefb174ca9d212dbd5378d46bd0c8a
|
| 3 |
+
size 1493434662
|
gpt2/cgpt/out-cgpt-e18-use-seq-1.0/ckpt.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bb276b90c587531cdb723c99cab892a84e8246d8e2969fe78a6c42ca1fd9b41
|
| 3 |
+
size 1493434662
|
gpt2/cgpt/out-cgpt-e18-use-seq-1.2/ckpt.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7ebc9fb2d7be656a0be6c0a9fa495df645a474e87cd93320a15feaee58e94d6
|
| 3 |
+
size 1493434662
|
gpt2/cgpt/out-cgpt-e18-use-seq-ablate-1.0/ckpt.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03044a2681785ab3eef0d4ec81fc7a0ef0776ef063a4f0ace861f1125e0facc4
|
| 3 |
+
size 1493434662
|
gpt2/q90/out-funcom-gpt2-e18-cce/ckpt.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d34914d55af32caaa2156640abe6500732a9311532335588ebae1a81144baddb
|
| 3 |
+
size 1493434662
|
gpt2/q90/out-funcom-gpt2-e18-use-seq-0.6/ckpt.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae52b73e6cc1472bdbe76caa18f81cf5ce5338c3c8c46a1666f67813265aa206
|
| 3 |
+
size 1493434662
|
gpt2/q90/out-funcom-gpt2-e18-use-seq-0.8/ckpt.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e3bcd657d03fe534fd37a5ab0b82eae3a513c01b1ac1988209b7c0718b3bb2e0
|
| 3 |
+
size 1493434662
|
gpt2/q90/out-funcom-gpt2-e18-use-seq-1.0/ckpt.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd5b45fd34b07dd6666f92d28f7b029d9e49e99ee2c825a4d0e5464e95575b33
|
| 3 |
+
size 1493434662
|
gpt2/q90/out-funcom-gpt2-e18-use-seq-1.2/ckpt.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb141dd6e585b610594151369d078577c29a0d3d41957a359d3b37f4b7325e91
|
| 3 |
+
size 1493434662
|
gpt2/q90/out-funcom-gpt2-e18-use-seq-ablate-1.0/ckpt.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cadab6f190a1293e6788681102e59de873048abf202fa6739448e96929ce432e
|
| 3 |
+
size 1493434726
|
llama/lora-alpaca-q90-cce/adapter_config.json
ADDED
|
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "decapoda-research/llama-7b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"enable_lora": null,
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"lora_alpha": 16,
|
| 8 |
+
"lora_dropout": 0.05,
|
| 9 |
+
"merge_weights": false,
|
| 10 |
+
"modules_to_save": null,
|
| 11 |
+
"peft_type": "LORA",
|
| 12 |
+
"r": 8,
|
| 13 |
+
"target_modules": [
|
| 14 |
+
"q_proj",
|
| 15 |
+
"v_proj"
|
| 16 |
+
],
|
| 17 |
+
"task_type": "CAUSAL_LM"
|
| 18 |
+
}
|
llama/lora-alpaca-q90-cce/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:85db8e950ef5d0f478d9511111d467d336e9f3b1a5951e1504bc0b097f42afa9
|
| 3 |
+
size 16822989
|
llama/lora-alpaca-q90-cce/checkpoint-1000/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:08448be733fb5513f2235cc506bbf6d8a3eed82d58e562bcd403a3187fb7d9a7
|
| 3 |
+
size 33629893
|
llama/lora-alpaca-q90-cce/checkpoint-1000/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5b1f8b85708871cade3d0285562fbb25d1ebe8040017504c66c30426c67e847
|
| 3 |
+
size 16822989
|
llama/lora-alpaca-q90-cce/checkpoint-1000/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:716b9e826437be7256498ff03ae610de855359aa3dcbc686fe327448af3b47ce
|
| 3 |
+
size 14575
|
llama/lora-alpaca-q90-cce/checkpoint-1000/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68cff80b680ddf6e7abbef98b5f336b97f9b5963e2209307f639383870e8cc71
|
| 3 |
+
size 557
|
llama/lora-alpaca-q90-cce/checkpoint-1000/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a69c02d22e7ba13517e1bdfd0b1c3ab7029bb5e809777e0aaafead5cf2bf0531
|
| 3 |
+
size 627
|
llama/lora-alpaca-q90-cce/checkpoint-1000/trainer_state.json
ADDED
|
@@ -0,0 +1,356 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6784626245498657,
|
| 3 |
+
"best_model_checkpoint": "lora-alpaca/checkpoint-1000",
|
| 4 |
+
"epoch": 0.7511913425197775,
|
| 5 |
+
"global_step": 1000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 13 |
+
"loss": 2.2234,
|
| 14 |
+
"step": 20
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 0.00011999999999999999,
|
| 19 |
+
"loss": 1.6986,
|
| 20 |
+
"step": 40
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.05,
|
| 24 |
+
"learning_rate": 0.00017999999999999998,
|
| 25 |
+
"loss": 1.0108,
|
| 26 |
+
"step": 60
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.06,
|
| 30 |
+
"learning_rate": 0.00023999999999999998,
|
| 31 |
+
"loss": 0.8498,
|
| 32 |
+
"step": 80
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.08,
|
| 36 |
+
"learning_rate": 0.0003,
|
| 37 |
+
"loss": 0.7975,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09,
|
| 42 |
+
"learning_rate": 0.00029512591389114535,
|
| 43 |
+
"loss": 0.7621,
|
| 44 |
+
"step": 120
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.11,
|
| 48 |
+
"learning_rate": 0.0002902518277822908,
|
| 49 |
+
"loss": 0.7465,
|
| 50 |
+
"step": 140
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.12,
|
| 54 |
+
"learning_rate": 0.0002853777416734362,
|
| 55 |
+
"loss": 0.7367,
|
| 56 |
+
"step": 160
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.14,
|
| 60 |
+
"learning_rate": 0.0002805036555645816,
|
| 61 |
+
"loss": 0.732,
|
| 62 |
+
"step": 180
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.15,
|
| 66 |
+
"learning_rate": 0.00027562956945572704,
|
| 67 |
+
"loss": 0.7253,
|
| 68 |
+
"step": 200
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.15,
|
| 72 |
+
"eval_loss": 0.7244793176651001,
|
| 73 |
+
"eval_runtime": 129.0223,
|
| 74 |
+
"eval_samples_per_second": 15.501,
|
| 75 |
+
"eval_steps_per_second": 1.938,
|
| 76 |
+
"step": 200
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.17,
|
| 80 |
+
"learning_rate": 0.0002707554833468724,
|
| 81 |
+
"loss": 0.7226,
|
| 82 |
+
"step": 220
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.18,
|
| 86 |
+
"learning_rate": 0.00026588139723801785,
|
| 87 |
+
"loss": 0.716,
|
| 88 |
+
"step": 240
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.2,
|
| 92 |
+
"learning_rate": 0.00026100731112916323,
|
| 93 |
+
"loss": 0.7182,
|
| 94 |
+
"step": 260
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.21,
|
| 98 |
+
"learning_rate": 0.00025613322502030867,
|
| 99 |
+
"loss": 0.7026,
|
| 100 |
+
"step": 280
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.23,
|
| 104 |
+
"learning_rate": 0.0002512591389114541,
|
| 105 |
+
"loss": 0.7139,
|
| 106 |
+
"step": 300
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.24,
|
| 110 |
+
"learning_rate": 0.0002463850528025995,
|
| 111 |
+
"loss": 0.7156,
|
| 112 |
+
"step": 320
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.26,
|
| 116 |
+
"learning_rate": 0.00024151096669374492,
|
| 117 |
+
"loss": 0.7069,
|
| 118 |
+
"step": 340
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.27,
|
| 122 |
+
"learning_rate": 0.0002366368805848903,
|
| 123 |
+
"loss": 0.6998,
|
| 124 |
+
"step": 360
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.29,
|
| 128 |
+
"learning_rate": 0.0002317627944760357,
|
| 129 |
+
"loss": 0.7058,
|
| 130 |
+
"step": 380
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.3,
|
| 134 |
+
"learning_rate": 0.00022688870836718114,
|
| 135 |
+
"loss": 0.7004,
|
| 136 |
+
"step": 400
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3,
|
| 140 |
+
"eval_loss": 0.6993061900138855,
|
| 141 |
+
"eval_runtime": 129.0376,
|
| 142 |
+
"eval_samples_per_second": 15.499,
|
| 143 |
+
"eval_steps_per_second": 1.937,
|
| 144 |
+
"step": 400
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.32,
|
| 148 |
+
"learning_rate": 0.00022201462225832652,
|
| 149 |
+
"loss": 0.6933,
|
| 150 |
+
"step": 420
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.33,
|
| 154 |
+
"learning_rate": 0.00021714053614947196,
|
| 155 |
+
"loss": 0.6868,
|
| 156 |
+
"step": 440
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.35,
|
| 160 |
+
"learning_rate": 0.00021226645004061737,
|
| 161 |
+
"loss": 0.6955,
|
| 162 |
+
"step": 460
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.36,
|
| 166 |
+
"learning_rate": 0.00020739236393176277,
|
| 167 |
+
"loss": 0.6878,
|
| 168 |
+
"step": 480
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.38,
|
| 172 |
+
"learning_rate": 0.00020251827782290818,
|
| 173 |
+
"loss": 0.6891,
|
| 174 |
+
"step": 500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.39,
|
| 178 |
+
"learning_rate": 0.0001976441917140536,
|
| 179 |
+
"loss": 0.686,
|
| 180 |
+
"step": 520
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.41,
|
| 184 |
+
"learning_rate": 0.00019277010560519902,
|
| 185 |
+
"loss": 0.6977,
|
| 186 |
+
"step": 540
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.42,
|
| 190 |
+
"learning_rate": 0.00018789601949634443,
|
| 191 |
+
"loss": 0.688,
|
| 192 |
+
"step": 560
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.44,
|
| 196 |
+
"learning_rate": 0.0001830219333874898,
|
| 197 |
+
"loss": 0.6838,
|
| 198 |
+
"step": 580
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.45,
|
| 202 |
+
"learning_rate": 0.00017814784727863525,
|
| 203 |
+
"loss": 0.682,
|
| 204 |
+
"step": 600
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.45,
|
| 208 |
+
"eval_loss": 0.6886340379714966,
|
| 209 |
+
"eval_runtime": 128.9722,
|
| 210 |
+
"eval_samples_per_second": 15.507,
|
| 211 |
+
"eval_steps_per_second": 1.938,
|
| 212 |
+
"step": 600
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.47,
|
| 216 |
+
"learning_rate": 0.00017327376116978065,
|
| 217 |
+
"loss": 0.6879,
|
| 218 |
+
"step": 620
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.48,
|
| 222 |
+
"learning_rate": 0.0001683996750609261,
|
| 223 |
+
"loss": 0.6871,
|
| 224 |
+
"step": 640
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.5,
|
| 228 |
+
"learning_rate": 0.00016352558895207147,
|
| 229 |
+
"loss": 0.6823,
|
| 230 |
+
"step": 660
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.51,
|
| 234 |
+
"learning_rate": 0.00015865150284321688,
|
| 235 |
+
"loss": 0.6732,
|
| 236 |
+
"step": 680
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.53,
|
| 240 |
+
"learning_rate": 0.0001537774167343623,
|
| 241 |
+
"loss": 0.6832,
|
| 242 |
+
"step": 700
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.54,
|
| 246 |
+
"learning_rate": 0.0001489033306255077,
|
| 247 |
+
"loss": 0.6795,
|
| 248 |
+
"step": 720
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.56,
|
| 252 |
+
"learning_rate": 0.00014402924451665313,
|
| 253 |
+
"loss": 0.686,
|
| 254 |
+
"step": 740
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.57,
|
| 258 |
+
"learning_rate": 0.00013915515840779853,
|
| 259 |
+
"loss": 0.6799,
|
| 260 |
+
"step": 760
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.59,
|
| 264 |
+
"learning_rate": 0.00013428107229894394,
|
| 265 |
+
"loss": 0.6738,
|
| 266 |
+
"step": 780
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.6,
|
| 270 |
+
"learning_rate": 0.00012940698619008935,
|
| 271 |
+
"loss": 0.6801,
|
| 272 |
+
"step": 800
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.6,
|
| 276 |
+
"eval_loss": 0.6822482943534851,
|
| 277 |
+
"eval_runtime": 128.9861,
|
| 278 |
+
"eval_samples_per_second": 15.506,
|
| 279 |
+
"eval_steps_per_second": 1.938,
|
| 280 |
+
"step": 800
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.62,
|
| 284 |
+
"learning_rate": 0.00012453290008123476,
|
| 285 |
+
"loss": 0.6803,
|
| 286 |
+
"step": 820
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.63,
|
| 290 |
+
"learning_rate": 0.00011965881397238017,
|
| 291 |
+
"loss": 0.6647,
|
| 292 |
+
"step": 840
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.65,
|
| 296 |
+
"learning_rate": 0.00011478472786352559,
|
| 297 |
+
"loss": 0.6838,
|
| 298 |
+
"step": 860
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.66,
|
| 302 |
+
"learning_rate": 0.000109910641754671,
|
| 303 |
+
"loss": 0.6793,
|
| 304 |
+
"step": 880
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.68,
|
| 308 |
+
"learning_rate": 0.0001050365556458164,
|
| 309 |
+
"loss": 0.6882,
|
| 310 |
+
"step": 900
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.69,
|
| 314 |
+
"learning_rate": 0.00010016246953696181,
|
| 315 |
+
"loss": 0.6733,
|
| 316 |
+
"step": 920
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.71,
|
| 320 |
+
"learning_rate": 9.528838342810722e-05,
|
| 321 |
+
"loss": 0.6786,
|
| 322 |
+
"step": 940
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.72,
|
| 326 |
+
"learning_rate": 9.041429731925264e-05,
|
| 327 |
+
"loss": 0.682,
|
| 328 |
+
"step": 960
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.74,
|
| 332 |
+
"learning_rate": 8.554021121039803e-05,
|
| 333 |
+
"loss": 0.6737,
|
| 334 |
+
"step": 980
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.75,
|
| 338 |
+
"learning_rate": 8.066612510154345e-05,
|
| 339 |
+
"loss": 0.6681,
|
| 340 |
+
"step": 1000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.75,
|
| 344 |
+
"eval_loss": 0.6784626245498657,
|
| 345 |
+
"eval_runtime": 129.063,
|
| 346 |
+
"eval_samples_per_second": 15.496,
|
| 347 |
+
"eval_steps_per_second": 1.937,
|
| 348 |
+
"step": 1000
|
| 349 |
+
}
|
| 350 |
+
],
|
| 351 |
+
"max_steps": 1331,
|
| 352 |
+
"num_train_epochs": 1,
|
| 353 |
+
"total_flos": 1.29988124737536e+18,
|
| 354 |
+
"trial_name": null,
|
| 355 |
+
"trial_params": null
|
| 356 |
+
}
|
llama/lora-alpaca-q90-cce/checkpoint-1000/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fac929355b6e3b85d753318e1aa77cfc30f00e526d22857f9fad037d422dcc46
|
| 3 |
+
size 3515
|
llama/lora-alpaca-q90-cce/checkpoint-1200/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33c49815930ea90b0dac6ef1171f469dc470d3cdcb9c57f454da076b9a4f9ab8
|
| 3 |
+
size 33629893
|
llama/lora-alpaca-q90-cce/checkpoint-1200/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ba9f60fb87ca30385c9a4917ba3ebeedc71c97e0a283b0324e79a1b8ce328ba7
|
| 3 |
+
size 16822989
|
llama/lora-alpaca-q90-cce/checkpoint-1200/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4d98aaa8ee8a726667d1326e2de60a7ee06aaece6c618bc7ce732b91f5e2f50
|
| 3 |
+
size 14575
|
llama/lora-alpaca-q90-cce/checkpoint-1200/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:741cefeca9ef427f92406d2d10b81996655e2a9d50eb7aaa9614e6fdd1c9f529
|
| 3 |
+
size 557
|
llama/lora-alpaca-q90-cce/checkpoint-1200/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d90a20c54899e27f19a89e3464bfe4b304595c9ee6541365c21acdedbea9c09
|
| 3 |
+
size 627
|
llama/lora-alpaca-q90-cce/checkpoint-1200/trainer_state.json
ADDED
|
@@ -0,0 +1,424 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6754332184791565,
|
| 3 |
+
"best_model_checkpoint": "lora-alpaca/checkpoint-1200",
|
| 4 |
+
"epoch": 0.901429611023733,
|
| 5 |
+
"global_step": 1200,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 13 |
+
"loss": 2.2234,
|
| 14 |
+
"step": 20
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 0.00011999999999999999,
|
| 19 |
+
"loss": 1.6986,
|
| 20 |
+
"step": 40
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.05,
|
| 24 |
+
"learning_rate": 0.00017999999999999998,
|
| 25 |
+
"loss": 1.0108,
|
| 26 |
+
"step": 60
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.06,
|
| 30 |
+
"learning_rate": 0.00023999999999999998,
|
| 31 |
+
"loss": 0.8498,
|
| 32 |
+
"step": 80
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.08,
|
| 36 |
+
"learning_rate": 0.0003,
|
| 37 |
+
"loss": 0.7975,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09,
|
| 42 |
+
"learning_rate": 0.00029512591389114535,
|
| 43 |
+
"loss": 0.7621,
|
| 44 |
+
"step": 120
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.11,
|
| 48 |
+
"learning_rate": 0.0002902518277822908,
|
| 49 |
+
"loss": 0.7465,
|
| 50 |
+
"step": 140
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.12,
|
| 54 |
+
"learning_rate": 0.0002853777416734362,
|
| 55 |
+
"loss": 0.7367,
|
| 56 |
+
"step": 160
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.14,
|
| 60 |
+
"learning_rate": 0.0002805036555645816,
|
| 61 |
+
"loss": 0.732,
|
| 62 |
+
"step": 180
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.15,
|
| 66 |
+
"learning_rate": 0.00027562956945572704,
|
| 67 |
+
"loss": 0.7253,
|
| 68 |
+
"step": 200
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.15,
|
| 72 |
+
"eval_loss": 0.7244793176651001,
|
| 73 |
+
"eval_runtime": 129.0223,
|
| 74 |
+
"eval_samples_per_second": 15.501,
|
| 75 |
+
"eval_steps_per_second": 1.938,
|
| 76 |
+
"step": 200
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.17,
|
| 80 |
+
"learning_rate": 0.0002707554833468724,
|
| 81 |
+
"loss": 0.7226,
|
| 82 |
+
"step": 220
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.18,
|
| 86 |
+
"learning_rate": 0.00026588139723801785,
|
| 87 |
+
"loss": 0.716,
|
| 88 |
+
"step": 240
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.2,
|
| 92 |
+
"learning_rate": 0.00026100731112916323,
|
| 93 |
+
"loss": 0.7182,
|
| 94 |
+
"step": 260
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.21,
|
| 98 |
+
"learning_rate": 0.00025613322502030867,
|
| 99 |
+
"loss": 0.7026,
|
| 100 |
+
"step": 280
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.23,
|
| 104 |
+
"learning_rate": 0.0002512591389114541,
|
| 105 |
+
"loss": 0.7139,
|
| 106 |
+
"step": 300
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.24,
|
| 110 |
+
"learning_rate": 0.0002463850528025995,
|
| 111 |
+
"loss": 0.7156,
|
| 112 |
+
"step": 320
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.26,
|
| 116 |
+
"learning_rate": 0.00024151096669374492,
|
| 117 |
+
"loss": 0.7069,
|
| 118 |
+
"step": 340
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.27,
|
| 122 |
+
"learning_rate": 0.0002366368805848903,
|
| 123 |
+
"loss": 0.6998,
|
| 124 |
+
"step": 360
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.29,
|
| 128 |
+
"learning_rate": 0.0002317627944760357,
|
| 129 |
+
"loss": 0.7058,
|
| 130 |
+
"step": 380
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.3,
|
| 134 |
+
"learning_rate": 0.00022688870836718114,
|
| 135 |
+
"loss": 0.7004,
|
| 136 |
+
"step": 400
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3,
|
| 140 |
+
"eval_loss": 0.6993061900138855,
|
| 141 |
+
"eval_runtime": 129.0376,
|
| 142 |
+
"eval_samples_per_second": 15.499,
|
| 143 |
+
"eval_steps_per_second": 1.937,
|
| 144 |
+
"step": 400
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.32,
|
| 148 |
+
"learning_rate": 0.00022201462225832652,
|
| 149 |
+
"loss": 0.6933,
|
| 150 |
+
"step": 420
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.33,
|
| 154 |
+
"learning_rate": 0.00021714053614947196,
|
| 155 |
+
"loss": 0.6868,
|
| 156 |
+
"step": 440
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.35,
|
| 160 |
+
"learning_rate": 0.00021226645004061737,
|
| 161 |
+
"loss": 0.6955,
|
| 162 |
+
"step": 460
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.36,
|
| 166 |
+
"learning_rate": 0.00020739236393176277,
|
| 167 |
+
"loss": 0.6878,
|
| 168 |
+
"step": 480
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.38,
|
| 172 |
+
"learning_rate": 0.00020251827782290818,
|
| 173 |
+
"loss": 0.6891,
|
| 174 |
+
"step": 500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.39,
|
| 178 |
+
"learning_rate": 0.0001976441917140536,
|
| 179 |
+
"loss": 0.686,
|
| 180 |
+
"step": 520
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.41,
|
| 184 |
+
"learning_rate": 0.00019277010560519902,
|
| 185 |
+
"loss": 0.6977,
|
| 186 |
+
"step": 540
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.42,
|
| 190 |
+
"learning_rate": 0.00018789601949634443,
|
| 191 |
+
"loss": 0.688,
|
| 192 |
+
"step": 560
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.44,
|
| 196 |
+
"learning_rate": 0.0001830219333874898,
|
| 197 |
+
"loss": 0.6838,
|
| 198 |
+
"step": 580
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.45,
|
| 202 |
+
"learning_rate": 0.00017814784727863525,
|
| 203 |
+
"loss": 0.682,
|
| 204 |
+
"step": 600
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.45,
|
| 208 |
+
"eval_loss": 0.6886340379714966,
|
| 209 |
+
"eval_runtime": 128.9722,
|
| 210 |
+
"eval_samples_per_second": 15.507,
|
| 211 |
+
"eval_steps_per_second": 1.938,
|
| 212 |
+
"step": 600
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.47,
|
| 216 |
+
"learning_rate": 0.00017327376116978065,
|
| 217 |
+
"loss": 0.6879,
|
| 218 |
+
"step": 620
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.48,
|
| 222 |
+
"learning_rate": 0.0001683996750609261,
|
| 223 |
+
"loss": 0.6871,
|
| 224 |
+
"step": 640
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.5,
|
| 228 |
+
"learning_rate": 0.00016352558895207147,
|
| 229 |
+
"loss": 0.6823,
|
| 230 |
+
"step": 660
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.51,
|
| 234 |
+
"learning_rate": 0.00015865150284321688,
|
| 235 |
+
"loss": 0.6732,
|
| 236 |
+
"step": 680
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.53,
|
| 240 |
+
"learning_rate": 0.0001537774167343623,
|
| 241 |
+
"loss": 0.6832,
|
| 242 |
+
"step": 700
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.54,
|
| 246 |
+
"learning_rate": 0.0001489033306255077,
|
| 247 |
+
"loss": 0.6795,
|
| 248 |
+
"step": 720
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.56,
|
| 252 |
+
"learning_rate": 0.00014402924451665313,
|
| 253 |
+
"loss": 0.686,
|
| 254 |
+
"step": 740
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.57,
|
| 258 |
+
"learning_rate": 0.00013915515840779853,
|
| 259 |
+
"loss": 0.6799,
|
| 260 |
+
"step": 760
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.59,
|
| 264 |
+
"learning_rate": 0.00013428107229894394,
|
| 265 |
+
"loss": 0.6738,
|
| 266 |
+
"step": 780
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.6,
|
| 270 |
+
"learning_rate": 0.00012940698619008935,
|
| 271 |
+
"loss": 0.6801,
|
| 272 |
+
"step": 800
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.6,
|
| 276 |
+
"eval_loss": 0.6822482943534851,
|
| 277 |
+
"eval_runtime": 128.9861,
|
| 278 |
+
"eval_samples_per_second": 15.506,
|
| 279 |
+
"eval_steps_per_second": 1.938,
|
| 280 |
+
"step": 800
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"epoch": 0.62,
|
| 284 |
+
"learning_rate": 0.00012453290008123476,
|
| 285 |
+
"loss": 0.6803,
|
| 286 |
+
"step": 820
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.63,
|
| 290 |
+
"learning_rate": 0.00011965881397238017,
|
| 291 |
+
"loss": 0.6647,
|
| 292 |
+
"step": 840
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"epoch": 0.65,
|
| 296 |
+
"learning_rate": 0.00011478472786352559,
|
| 297 |
+
"loss": 0.6838,
|
| 298 |
+
"step": 860
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.66,
|
| 302 |
+
"learning_rate": 0.000109910641754671,
|
| 303 |
+
"loss": 0.6793,
|
| 304 |
+
"step": 880
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.68,
|
| 308 |
+
"learning_rate": 0.0001050365556458164,
|
| 309 |
+
"loss": 0.6882,
|
| 310 |
+
"step": 900
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.69,
|
| 314 |
+
"learning_rate": 0.00010016246953696181,
|
| 315 |
+
"loss": 0.6733,
|
| 316 |
+
"step": 920
|
| 317 |
+
},
|
| 318 |
+
{
|
| 319 |
+
"epoch": 0.71,
|
| 320 |
+
"learning_rate": 9.528838342810722e-05,
|
| 321 |
+
"loss": 0.6786,
|
| 322 |
+
"step": 940
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.72,
|
| 326 |
+
"learning_rate": 9.041429731925264e-05,
|
| 327 |
+
"loss": 0.682,
|
| 328 |
+
"step": 960
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.74,
|
| 332 |
+
"learning_rate": 8.554021121039803e-05,
|
| 333 |
+
"loss": 0.6737,
|
| 334 |
+
"step": 980
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.75,
|
| 338 |
+
"learning_rate": 8.066612510154345e-05,
|
| 339 |
+
"loss": 0.6681,
|
| 340 |
+
"step": 1000
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.75,
|
| 344 |
+
"eval_loss": 0.6784626245498657,
|
| 345 |
+
"eval_runtime": 129.063,
|
| 346 |
+
"eval_samples_per_second": 15.496,
|
| 347 |
+
"eval_steps_per_second": 1.937,
|
| 348 |
+
"step": 1000
|
| 349 |
+
},
|
| 350 |
+
{
|
| 351 |
+
"epoch": 0.77,
|
| 352 |
+
"learning_rate": 7.579203899268886e-05,
|
| 353 |
+
"loss": 0.678,
|
| 354 |
+
"step": 1020
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.78,
|
| 358 |
+
"learning_rate": 7.091795288383428e-05,
|
| 359 |
+
"loss": 0.6692,
|
| 360 |
+
"step": 1040
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.8,
|
| 364 |
+
"learning_rate": 6.604386677497969e-05,
|
| 365 |
+
"loss": 0.6767,
|
| 366 |
+
"step": 1060
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.81,
|
| 370 |
+
"learning_rate": 6.11697806661251e-05,
|
| 371 |
+
"loss": 0.6699,
|
| 372 |
+
"step": 1080
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.83,
|
| 376 |
+
"learning_rate": 5.6295694557270505e-05,
|
| 377 |
+
"loss": 0.678,
|
| 378 |
+
"step": 1100
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.84,
|
| 382 |
+
"learning_rate": 5.142160844841592e-05,
|
| 383 |
+
"loss": 0.6802,
|
| 384 |
+
"step": 1120
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.86,
|
| 388 |
+
"learning_rate": 4.654752233956133e-05,
|
| 389 |
+
"loss": 0.6773,
|
| 390 |
+
"step": 1140
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"epoch": 0.87,
|
| 394 |
+
"learning_rate": 4.167343623070674e-05,
|
| 395 |
+
"loss": 0.6719,
|
| 396 |
+
"step": 1160
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.89,
|
| 400 |
+
"learning_rate": 3.679935012185215e-05,
|
| 401 |
+
"loss": 0.6764,
|
| 402 |
+
"step": 1180
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.9,
|
| 406 |
+
"learning_rate": 3.192526401299756e-05,
|
| 407 |
+
"loss": 0.6745,
|
| 408 |
+
"step": 1200
|
| 409 |
+
},
|
| 410 |
+
{
|
| 411 |
+
"epoch": 0.9,
|
| 412 |
+
"eval_loss": 0.6754332184791565,
|
| 413 |
+
"eval_runtime": 128.9887,
|
| 414 |
+
"eval_samples_per_second": 15.505,
|
| 415 |
+
"eval_steps_per_second": 1.938,
|
| 416 |
+
"step": 1200
|
| 417 |
+
}
|
| 418 |
+
],
|
| 419 |
+
"max_steps": 1331,
|
| 420 |
+
"num_train_epochs": 1,
|
| 421 |
+
"total_flos": 1.559857496850432e+18,
|
| 422 |
+
"trial_name": null,
|
| 423 |
+
"trial_params": null
|
| 424 |
+
}
|
llama/lora-alpaca-q90-cce/checkpoint-1200/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fac929355b6e3b85d753318e1aa77cfc30f00e526d22857f9fad037d422dcc46
|
| 3 |
+
size 3515
|
llama/lora-alpaca-q90-cce/checkpoint-800/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d4dae287198f854ec748229003488aa7600420a32ba91d46f4d84bd52120b57
|
| 3 |
+
size 33629893
|
llama/lora-alpaca-q90-cce/checkpoint-800/pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:acd23c87bf974e5147bc9a152a9262c3efffaa61b736daf495c3cf4da9f237d6
|
| 3 |
+
size 16822989
|
llama/lora-alpaca-q90-cce/checkpoint-800/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f1a4cc8c5baf51f3cd71e0d56a3c0b65204e606c6f5eb0adc2d7ae2c7e900fbf
|
| 3 |
+
size 14575
|
llama/lora-alpaca-q90-cce/checkpoint-800/scaler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27ec07a12731ae6f9765d05fe7c8495505f1d0f90b4cc6255a0853fec3970808
|
| 3 |
+
size 557
|
llama/lora-alpaca-q90-cce/checkpoint-800/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:616a7b1df89e3ef38b6fa5a5f381236e37a81295f1e5fe4260a5014a64e9a421
|
| 3 |
+
size 627
|
llama/lora-alpaca-q90-cce/checkpoint-800/trainer_state.json
ADDED
|
@@ -0,0 +1,288 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": 0.6822482943534851,
|
| 3 |
+
"best_model_checkpoint": "lora-alpaca/checkpoint-800",
|
| 4 |
+
"epoch": 0.600953074015822,
|
| 5 |
+
"global_step": 800,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.02,
|
| 12 |
+
"learning_rate": 5.9999999999999995e-05,
|
| 13 |
+
"loss": 2.2234,
|
| 14 |
+
"step": 20
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.03,
|
| 18 |
+
"learning_rate": 0.00011999999999999999,
|
| 19 |
+
"loss": 1.6986,
|
| 20 |
+
"step": 40
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.05,
|
| 24 |
+
"learning_rate": 0.00017999999999999998,
|
| 25 |
+
"loss": 1.0108,
|
| 26 |
+
"step": 60
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.06,
|
| 30 |
+
"learning_rate": 0.00023999999999999998,
|
| 31 |
+
"loss": 0.8498,
|
| 32 |
+
"step": 80
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.08,
|
| 36 |
+
"learning_rate": 0.0003,
|
| 37 |
+
"loss": 0.7975,
|
| 38 |
+
"step": 100
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.09,
|
| 42 |
+
"learning_rate": 0.00029512591389114535,
|
| 43 |
+
"loss": 0.7621,
|
| 44 |
+
"step": 120
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.11,
|
| 48 |
+
"learning_rate": 0.0002902518277822908,
|
| 49 |
+
"loss": 0.7465,
|
| 50 |
+
"step": 140
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"epoch": 0.12,
|
| 54 |
+
"learning_rate": 0.0002853777416734362,
|
| 55 |
+
"loss": 0.7367,
|
| 56 |
+
"step": 160
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 0.14,
|
| 60 |
+
"learning_rate": 0.0002805036555645816,
|
| 61 |
+
"loss": 0.732,
|
| 62 |
+
"step": 180
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 0.15,
|
| 66 |
+
"learning_rate": 0.00027562956945572704,
|
| 67 |
+
"loss": 0.7253,
|
| 68 |
+
"step": 200
|
| 69 |
+
},
|
| 70 |
+
{
|
| 71 |
+
"epoch": 0.15,
|
| 72 |
+
"eval_loss": 0.7244793176651001,
|
| 73 |
+
"eval_runtime": 129.0223,
|
| 74 |
+
"eval_samples_per_second": 15.501,
|
| 75 |
+
"eval_steps_per_second": 1.938,
|
| 76 |
+
"step": 200
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"epoch": 0.17,
|
| 80 |
+
"learning_rate": 0.0002707554833468724,
|
| 81 |
+
"loss": 0.7226,
|
| 82 |
+
"step": 220
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.18,
|
| 86 |
+
"learning_rate": 0.00026588139723801785,
|
| 87 |
+
"loss": 0.716,
|
| 88 |
+
"step": 240
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.2,
|
| 92 |
+
"learning_rate": 0.00026100731112916323,
|
| 93 |
+
"loss": 0.7182,
|
| 94 |
+
"step": 260
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.21,
|
| 98 |
+
"learning_rate": 0.00025613322502030867,
|
| 99 |
+
"loss": 0.7026,
|
| 100 |
+
"step": 280
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"epoch": 0.23,
|
| 104 |
+
"learning_rate": 0.0002512591389114541,
|
| 105 |
+
"loss": 0.7139,
|
| 106 |
+
"step": 300
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.24,
|
| 110 |
+
"learning_rate": 0.0002463850528025995,
|
| 111 |
+
"loss": 0.7156,
|
| 112 |
+
"step": 320
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"epoch": 0.26,
|
| 116 |
+
"learning_rate": 0.00024151096669374492,
|
| 117 |
+
"loss": 0.7069,
|
| 118 |
+
"step": 340
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.27,
|
| 122 |
+
"learning_rate": 0.0002366368805848903,
|
| 123 |
+
"loss": 0.6998,
|
| 124 |
+
"step": 360
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.29,
|
| 128 |
+
"learning_rate": 0.0002317627944760357,
|
| 129 |
+
"loss": 0.7058,
|
| 130 |
+
"step": 380
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.3,
|
| 134 |
+
"learning_rate": 0.00022688870836718114,
|
| 135 |
+
"loss": 0.7004,
|
| 136 |
+
"step": 400
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.3,
|
| 140 |
+
"eval_loss": 0.6993061900138855,
|
| 141 |
+
"eval_runtime": 129.0376,
|
| 142 |
+
"eval_samples_per_second": 15.499,
|
| 143 |
+
"eval_steps_per_second": 1.937,
|
| 144 |
+
"step": 400
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 0.32,
|
| 148 |
+
"learning_rate": 0.00022201462225832652,
|
| 149 |
+
"loss": 0.6933,
|
| 150 |
+
"step": 420
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.33,
|
| 154 |
+
"learning_rate": 0.00021714053614947196,
|
| 155 |
+
"loss": 0.6868,
|
| 156 |
+
"step": 440
|
| 157 |
+
},
|
| 158 |
+
{
|
| 159 |
+
"epoch": 0.35,
|
| 160 |
+
"learning_rate": 0.00021226645004061737,
|
| 161 |
+
"loss": 0.6955,
|
| 162 |
+
"step": 460
|
| 163 |
+
},
|
| 164 |
+
{
|
| 165 |
+
"epoch": 0.36,
|
| 166 |
+
"learning_rate": 0.00020739236393176277,
|
| 167 |
+
"loss": 0.6878,
|
| 168 |
+
"step": 480
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.38,
|
| 172 |
+
"learning_rate": 0.00020251827782290818,
|
| 173 |
+
"loss": 0.6891,
|
| 174 |
+
"step": 500
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.39,
|
| 178 |
+
"learning_rate": 0.0001976441917140536,
|
| 179 |
+
"loss": 0.686,
|
| 180 |
+
"step": 520
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.41,
|
| 184 |
+
"learning_rate": 0.00019277010560519902,
|
| 185 |
+
"loss": 0.6977,
|
| 186 |
+
"step": 540
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.42,
|
| 190 |
+
"learning_rate": 0.00018789601949634443,
|
| 191 |
+
"loss": 0.688,
|
| 192 |
+
"step": 560
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.44,
|
| 196 |
+
"learning_rate": 0.0001830219333874898,
|
| 197 |
+
"loss": 0.6838,
|
| 198 |
+
"step": 580
|
| 199 |
+
},
|
| 200 |
+
{
|
| 201 |
+
"epoch": 0.45,
|
| 202 |
+
"learning_rate": 0.00017814784727863525,
|
| 203 |
+
"loss": 0.682,
|
| 204 |
+
"step": 600
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 0.45,
|
| 208 |
+
"eval_loss": 0.6886340379714966,
|
| 209 |
+
"eval_runtime": 128.9722,
|
| 210 |
+
"eval_samples_per_second": 15.507,
|
| 211 |
+
"eval_steps_per_second": 1.938,
|
| 212 |
+
"step": 600
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.47,
|
| 216 |
+
"learning_rate": 0.00017327376116978065,
|
| 217 |
+
"loss": 0.6879,
|
| 218 |
+
"step": 620
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.48,
|
| 222 |
+
"learning_rate": 0.0001683996750609261,
|
| 223 |
+
"loss": 0.6871,
|
| 224 |
+
"step": 640
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.5,
|
| 228 |
+
"learning_rate": 0.00016352558895207147,
|
| 229 |
+
"loss": 0.6823,
|
| 230 |
+
"step": 660
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"epoch": 0.51,
|
| 234 |
+
"learning_rate": 0.00015865150284321688,
|
| 235 |
+
"loss": 0.6732,
|
| 236 |
+
"step": 680
|
| 237 |
+
},
|
| 238 |
+
{
|
| 239 |
+
"epoch": 0.53,
|
| 240 |
+
"learning_rate": 0.0001537774167343623,
|
| 241 |
+
"loss": 0.6832,
|
| 242 |
+
"step": 700
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"epoch": 0.54,
|
| 246 |
+
"learning_rate": 0.0001489033306255077,
|
| 247 |
+
"loss": 0.6795,
|
| 248 |
+
"step": 720
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.56,
|
| 252 |
+
"learning_rate": 0.00014402924451665313,
|
| 253 |
+
"loss": 0.686,
|
| 254 |
+
"step": 740
|
| 255 |
+
},
|
| 256 |
+
{
|
| 257 |
+
"epoch": 0.57,
|
| 258 |
+
"learning_rate": 0.00013915515840779853,
|
| 259 |
+
"loss": 0.6799,
|
| 260 |
+
"step": 760
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.59,
|
| 264 |
+
"learning_rate": 0.00013428107229894394,
|
| 265 |
+
"loss": 0.6738,
|
| 266 |
+
"step": 780
|
| 267 |
+
},
|
| 268 |
+
{
|
| 269 |
+
"epoch": 0.6,
|
| 270 |
+
"learning_rate": 0.00012940698619008935,
|
| 271 |
+
"loss": 0.6801,
|
| 272 |
+
"step": 800
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"epoch": 0.6,
|
| 276 |
+
"eval_loss": 0.6822482943534851,
|
| 277 |
+
"eval_runtime": 128.9861,
|
| 278 |
+
"eval_samples_per_second": 15.506,
|
| 279 |
+
"eval_steps_per_second": 1.938,
|
| 280 |
+
"step": 800
|
| 281 |
+
}
|
| 282 |
+
],
|
| 283 |
+
"max_steps": 1331,
|
| 284 |
+
"num_train_epochs": 1,
|
| 285 |
+
"total_flos": 1.039904997900288e+18,
|
| 286 |
+
"trial_name": null,
|
| 287 |
+
"trial_params": null
|
| 288 |
+
}
|
llama/lora-alpaca-q90-cce/checkpoint-800/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fac929355b6e3b85d753318e1aa77cfc30f00e526d22857f9fad037d422dcc46
|
| 3 |
+
size 3515
|
llama/lora-alpaca-q90-use-seq/adapter_config.json
ADDED
|
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"base_model_name_or_path": "decapoda-research/llama-7b-hf",
|
| 3 |
+
"bias": "none",
|
| 4 |
+
"enable_lora": null,
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"lora_alpha": 16,
|
| 9 |
+
"lora_dropout": 0.05,
|
| 10 |
+
"merge_weights": false,
|
| 11 |
+
"modules_to_save": null,
|
| 12 |
+
"peft_type": "LORA",
|
| 13 |
+
"r": 8,
|
| 14 |
+
"target_modules": [
|
| 15 |
+
"q_proj",
|
| 16 |
+
"v_proj"
|
| 17 |
+
],
|
| 18 |
+
"task_type": "CAUSAL_LM"
|
| 19 |
+
}
|
llama/lora-alpaca-q90-use-seq/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d4f45e8904cd0ecec21041e4968cee3f330f05b89c3aa425e3eb7d9a3251ec4
|
| 3 |
+
size 16822989
|