Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- Area/checkpoint-400/adapter_model.safetensors +3 -0
- Area/checkpoint-450/rng_state_0.pth +3 -0
- Area/checkpoint-450/scheduler.pt +3 -0
- Area/checkpoint-500/rng_state_1.pth +3 -0
- Area/checkpoint-500/rng_state_2.pth +3 -0
- Area/checkpoint-500/rng_state_3.pth +3 -0
- Area/checkpoint-500/rng_state_4.pth +3 -0
- Area/checkpoint-500/rng_state_5.pth +3 -0
- Area/checkpoint-500/rng_state_6.pth +3 -0
- Area/checkpoint-500/rng_state_7.pth +3 -0
- Power/dpo/adapter_model.safetensors +3 -0
- Power/dpo/checkpoint-200/adapter_model.safetensors +3 -0
- Power_Area/checkpoint-300/tokenizer.json +0 -0
- Power_Area/checkpoint-300/trainer_state.json +483 -0
- Power_Area/checkpoint-350/README.md +202 -0
- Power_Area/checkpoint-350/adapter_config.json +34 -0
- Power_Area/checkpoint-350/special_tokens_map.json +23 -0
- Power_Area/checkpoint-350/tokenizer.json +0 -0
- Power_Area/checkpoint-350/tokenizer_config.json +196 -0
- Power_Area/checkpoint-350/trainer_state.json +558 -0
- Power_Area/checkpoint-400/README.md +202 -0
- Power_Area/checkpoint-400/adapter_config.json +34 -0
- Power_Area/checkpoint-400/special_tokens_map.json +23 -0
- Power_Area/checkpoint-400/tokenizer.json +0 -0
- Power_Area/checkpoint-400/tokenizer_config.json +196 -0
- Power_Area/checkpoint-400/trainer_state.json +633 -0
- Power_Area/checkpoint-450/README.md +202 -0
- Power_Area/checkpoint-450/adapter_config.json +34 -0
- Power_Area/checkpoint-450/special_tokens_map.json +23 -0
- Power_Area/checkpoint-450/tokenizer.json +0 -0
- Power_Area/checkpoint-450/tokenizer_config.json +196 -0
- Power_Area/checkpoint-450/trainer_state.json +708 -0
- Power_Area/checkpoint-500/README.md +202 -0
- Power_Area/checkpoint-500/adapter_config.json +34 -0
- Power_Area/checkpoint-500/special_tokens_map.json +23 -0
- Power_Area/checkpoint-500/tokenizer.json +0 -0
- Power_Area/checkpoint-500/tokenizer_config.json +196 -0
- Power_Area/checkpoint-500/trainer_state.json +783 -0
- Power_Area/checkpoint-550/README.md +202 -0
- Power_Area/checkpoint-550/adapter_config.json +34 -0
- Power_Area/checkpoint-550/special_tokens_map.json +23 -0
- Power_Area/checkpoint-550/tokenizer.json +0 -0
- Power_Area/checkpoint-550/tokenizer_config.json +196 -0
- Power_Area/checkpoint-550/trainer_state.json +858 -0
- Power_Area/checkpoint-580/README.md +202 -0
- Power_Area/checkpoint-580/adapter_config.json +34 -0
- Power_Area/checkpoint-580/special_tokens_map.json +23 -0
- Power_Area/checkpoint-580/tokenizer.json +0 -0
- Power_Area/checkpoint-580/tokenizer_config.json +196 -0
- Power_Area/checkpoint-580/trainer_state.json +903 -0
Area/checkpoint-400/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6b63b4238bbd2be9d2b5a623ba1238cfda12d20d9a5117fbba28ef52806c187
|
| 3 |
+
size 80013120
|
Area/checkpoint-450/rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bb7c3bc1248de8b4739437317b988d953fd64a5de9736606d74f9c8277f1b485
|
| 3 |
+
size 15984
|
Area/checkpoint-450/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ed4c5e628e583a77ca3203830f548741cdaa4a7e269de094fcbf300dd38da54b
|
| 3 |
+
size 1064
|
Area/checkpoint-500/rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:03e36a570d6158fc25d1cf5d9f8f450fc64c5a7683330277f89ff76d5f2fc6cd
|
| 3 |
+
size 15984
|
Area/checkpoint-500/rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b4f619cbef4b74f1680d667c8788285a602392e63bdf3760ef3a59ec8864d483
|
| 3 |
+
size 15984
|
Area/checkpoint-500/rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fc037fba93ace1bf7ce01b1a5f7d785698d47b4cc2cedf2300bbf7a41ebf05c
|
| 3 |
+
size 15984
|
Area/checkpoint-500/rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ab728c2461d6d1c64f04d7cbfdfcbfa7bd7ad0ef6e19d52458501ee81b27128
|
| 3 |
+
size 15984
|
Area/checkpoint-500/rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27530e653ebf5997ae3159cdcde264607e6a6f86b7e3c7a1b3a1e8301cd43d03
|
| 3 |
+
size 15984
|
Area/checkpoint-500/rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c1fddaeb1257697bd7c0101abf1ab23f2925d0d9165cd8bddfbd22f8444db2b7
|
| 3 |
+
size 15984
|
Area/checkpoint-500/rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:942af3734a320fe12a3205a47ca1cdc7d1f0996bfde86c020a35545ccd2fd418
|
| 3 |
+
size 15984
|
Power/dpo/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71476e35b886d7dc9cdaa60a313c5cb8c41b2ad8c9039f387bcddb2afa0383cd
|
| 3 |
+
size 80013120
|
Power/dpo/checkpoint-200/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:05ac5b8f56cc98b060ab7dc726d328fd7049e1816f0e503f28b78a8f86b79fb0
|
| 3 |
+
size 80013120
|
Power_Area/checkpoint-300/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Power_Area/checkpoint-300/trainer_state.json
ADDED
|
@@ -0,0 +1,483 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 10.147679324894515,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 300,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33755274261603374,
|
| 13 |
+
"grad_norm": 0.4396141469478607,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": 1.6453087329864502,
|
| 16 |
+
"logits/rejected": 1.694819450378418,
|
| 17 |
+
"logps/chosen": -74.5937728881836,
|
| 18 |
+
"logps/rejected": -83.19783782958984,
|
| 19 |
+
"loss": 0.6928,
|
| 20 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 21 |
+
"rewards/chosen": 0.003385844174772501,
|
| 22 |
+
"rewards/margins": 0.004794469103217125,
|
| 23 |
+
"rewards/rejected": -0.0014086246956139803,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6751054852320675,
|
| 28 |
+
"grad_norm": 3.18404483795166,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": 1.7945035696029663,
|
| 31 |
+
"logits/rejected": 1.8347476720809937,
|
| 32 |
+
"logps/chosen": -95.46636199951172,
|
| 33 |
+
"logps/rejected": -101.22709655761719,
|
| 34 |
+
"loss": 0.6933,
|
| 35 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 36 |
+
"rewards/chosen": -0.0005593777750618756,
|
| 37 |
+
"rewards/margins": -0.002013001125305891,
|
| 38 |
+
"rewards/rejected": 0.0014536241069436073,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0126582278481013,
|
| 43 |
+
"grad_norm": 0.48596081137657166,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": 1.774155616760254,
|
| 46 |
+
"logits/rejected": 1.8374344110488892,
|
| 47 |
+
"logps/chosen": -82.01265716552734,
|
| 48 |
+
"logps/rejected": -84.23635864257812,
|
| 49 |
+
"loss": 0.6948,
|
| 50 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 51 |
+
"rewards/chosen": -0.0031326995231211185,
|
| 52 |
+
"rewards/margins": -0.00463916826993227,
|
| 53 |
+
"rewards/rejected": 0.0015064675826579332,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.350210970464135,
|
| 58 |
+
"grad_norm": 0.5144609808921814,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": 1.838865876197815,
|
| 61 |
+
"logits/rejected": 1.9505430459976196,
|
| 62 |
+
"logps/chosen": -73.50071716308594,
|
| 63 |
+
"logps/rejected": -88.8648452758789,
|
| 64 |
+
"loss": 0.6928,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.0035957477521151304,
|
| 67 |
+
"rewards/margins": -0.008830643258988857,
|
| 68 |
+
"rewards/rejected": 0.005234894808381796,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6877637130801688,
|
| 73 |
+
"grad_norm": 0.48295095562934875,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": 1.8197529315948486,
|
| 76 |
+
"logits/rejected": 1.8459796905517578,
|
| 77 |
+
"logps/chosen": -83.36590576171875,
|
| 78 |
+
"logps/rejected": -70.26930236816406,
|
| 79 |
+
"loss": 0.6929,
|
| 80 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 81 |
+
"rewards/chosen": -0.0030026868917047977,
|
| 82 |
+
"rewards/margins": -0.006082554347813129,
|
| 83 |
+
"rewards/rejected": 0.003079867223277688,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.0464135021097047,
|
| 88 |
+
"grad_norm": 0.5616092085838318,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": 1.7525272369384766,
|
| 91 |
+
"logits/rejected": 1.8092533349990845,
|
| 92 |
+
"logps/chosen": -82.01802062988281,
|
| 93 |
+
"logps/rejected": -78.39723205566406,
|
| 94 |
+
"loss": 0.6949,
|
| 95 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 96 |
+
"rewards/chosen": -0.0010920714121311903,
|
| 97 |
+
"rewards/margins": -0.0016235255170613527,
|
| 98 |
+
"rewards/rejected": 0.0005314538720995188,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3839662447257384,
|
| 103 |
+
"grad_norm": 0.5237122774124146,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": 1.754880666732788,
|
| 106 |
+
"logits/rejected": 1.8100305795669556,
|
| 107 |
+
"logps/chosen": -89.62864685058594,
|
| 108 |
+
"logps/rejected": -88.30036926269531,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5,
|
| 111 |
+
"rewards/chosen": -0.002314353361725807,
|
| 112 |
+
"rewards/margins": -0.001038494287058711,
|
| 113 |
+
"rewards/rejected": -0.0012758590746670961,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.721518987341772,
|
| 118 |
+
"grad_norm": 0.507128119468689,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": 1.7501789331436157,
|
| 121 |
+
"logits/rejected": 1.6666221618652344,
|
| 122 |
+
"logps/chosen": -94.74919128417969,
|
| 123 |
+
"logps/rejected": -74.9794692993164,
|
| 124 |
+
"loss": 0.6922,
|
| 125 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 126 |
+
"rewards/chosen": 0.00475720502436161,
|
| 127 |
+
"rewards/margins": 0.01054429542273283,
|
| 128 |
+
"rewards/rejected": -0.005787090864032507,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.059071729957806,
|
| 133 |
+
"grad_norm": 0.8151038885116577,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": 1.7203710079193115,
|
| 136 |
+
"logits/rejected": 1.7376699447631836,
|
| 137 |
+
"logps/chosen": -76.8824691772461,
|
| 138 |
+
"logps/rejected": -84.74555206298828,
|
| 139 |
+
"loss": 0.6925,
|
| 140 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 141 |
+
"rewards/chosen": 0.01064519863575697,
|
| 142 |
+
"rewards/margins": 0.012716365046799183,
|
| 143 |
+
"rewards/rejected": -0.0020711664110422134,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3966244725738397,
|
| 148 |
+
"grad_norm": 0.5476706027984619,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": 1.7857105731964111,
|
| 151 |
+
"logits/rejected": 1.7341340780258179,
|
| 152 |
+
"logps/chosen": -88.39775085449219,
|
| 153 |
+
"logps/rejected": -80.00445556640625,
|
| 154 |
+
"loss": 0.6893,
|
| 155 |
+
"rewards/accuracies": 0.612500011920929,
|
| 156 |
+
"rewards/chosen": 0.0052363635040819645,
|
| 157 |
+
"rewards/margins": 0.016881367191672325,
|
| 158 |
+
"rewards/rejected": -0.011645001359283924,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.7341772151898733,
|
| 163 |
+
"grad_norm": 0.6562405824661255,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": 1.737647294998169,
|
| 166 |
+
"logits/rejected": 1.7781591415405273,
|
| 167 |
+
"logps/chosen": -92.72380065917969,
|
| 168 |
+
"logps/rejected": -85.51634216308594,
|
| 169 |
+
"loss": 0.6899,
|
| 170 |
+
"rewards/accuracies": 0.512499988079071,
|
| 171 |
+
"rewards/chosen": -0.010819707065820694,
|
| 172 |
+
"rewards/margins": -0.0005886269500479102,
|
| 173 |
+
"rewards/rejected": -0.010231079533696175,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.071729957805907,
|
| 178 |
+
"grad_norm": 0.6393210291862488,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": 1.7890704870224,
|
| 181 |
+
"logits/rejected": 1.8340994119644165,
|
| 182 |
+
"logps/chosen": -87.615478515625,
|
| 183 |
+
"logps/rejected": -108.13908386230469,
|
| 184 |
+
"loss": 0.6872,
|
| 185 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 186 |
+
"rewards/chosen": 0.002250433200970292,
|
| 187 |
+
"rewards/margins": 0.012117428705096245,
|
| 188 |
+
"rewards/rejected": -0.009866995736956596,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.409282700421941,
|
| 193 |
+
"grad_norm": 0.7390326261520386,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": 1.7916072607040405,
|
| 196 |
+
"logits/rejected": 1.787153959274292,
|
| 197 |
+
"logps/chosen": -84.11034393310547,
|
| 198 |
+
"logps/rejected": -76.81166076660156,
|
| 199 |
+
"loss": 0.6844,
|
| 200 |
+
"rewards/accuracies": 0.5625,
|
| 201 |
+
"rewards/chosen": -0.003190569579601288,
|
| 202 |
+
"rewards/margins": 0.015628555789589882,
|
| 203 |
+
"rewards/rejected": -0.01881912164390087,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.746835443037975,
|
| 208 |
+
"grad_norm": 0.7888330817222595,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": 1.8455331325531006,
|
| 211 |
+
"logits/rejected": 1.8137515783309937,
|
| 212 |
+
"logps/chosen": -78.94912719726562,
|
| 213 |
+
"logps/rejected": -76.1368637084961,
|
| 214 |
+
"loss": 0.6819,
|
| 215 |
+
"rewards/accuracies": 0.625,
|
| 216 |
+
"rewards/chosen": -0.012986091896891594,
|
| 217 |
+
"rewards/margins": 0.015167826786637306,
|
| 218 |
+
"rewards/rejected": -0.02815392054617405,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.084388185654008,
|
| 223 |
+
"grad_norm": 0.7248090505599976,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": 1.6686553955078125,
|
| 226 |
+
"logits/rejected": 1.6654260158538818,
|
| 227 |
+
"logps/chosen": -78.25769805908203,
|
| 228 |
+
"logps/rejected": -71.3498306274414,
|
| 229 |
+
"loss": 0.677,
|
| 230 |
+
"rewards/accuracies": 0.612500011920929,
|
| 231 |
+
"rewards/chosen": -0.0182911679148674,
|
| 232 |
+
"rewards/margins": 0.02633112668991089,
|
| 233 |
+
"rewards/rejected": -0.04462229460477829,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.421940928270042,
|
| 238 |
+
"grad_norm": 0.7906918525695801,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": 1.8054498434066772,
|
| 241 |
+
"logits/rejected": 1.751422643661499,
|
| 242 |
+
"logps/chosen": -91.65776824951172,
|
| 243 |
+
"logps/rejected": -68.41027069091797,
|
| 244 |
+
"loss": 0.6741,
|
| 245 |
+
"rewards/accuracies": 0.574999988079071,
|
| 246 |
+
"rewards/chosen": -0.04313550516963005,
|
| 247 |
+
"rewards/margins": 0.017568334937095642,
|
| 248 |
+
"rewards/rejected": -0.060703836381435394,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.759493670886076,
|
| 253 |
+
"grad_norm": 0.8152453303337097,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": 1.742419958114624,
|
| 256 |
+
"logits/rejected": 1.9456249475479126,
|
| 257 |
+
"logps/chosen": -80.52605438232422,
|
| 258 |
+
"logps/rejected": -117.02473449707031,
|
| 259 |
+
"loss": 0.67,
|
| 260 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 261 |
+
"rewards/chosen": -0.030041133984923363,
|
| 262 |
+
"rewards/margins": 0.03393586724996567,
|
| 263 |
+
"rewards/rejected": -0.06397700309753418,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.09704641350211,
|
| 268 |
+
"grad_norm": 0.7848192453384399,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": 1.836090087890625,
|
| 271 |
+
"logits/rejected": 2.0285377502441406,
|
| 272 |
+
"logps/chosen": -72.87449645996094,
|
| 273 |
+
"logps/rejected": -101.46552276611328,
|
| 274 |
+
"loss": 0.6659,
|
| 275 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 276 |
+
"rewards/chosen": -0.04543738812208176,
|
| 277 |
+
"rewards/margins": 0.0431094653904438,
|
| 278 |
+
"rewards/rejected": -0.08854684978723526,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.434599156118144,
|
| 283 |
+
"grad_norm": 0.8349910378456116,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": 1.7459189891815186,
|
| 286 |
+
"logits/rejected": 1.8324615955352783,
|
| 287 |
+
"logps/chosen": -72.0348892211914,
|
| 288 |
+
"logps/rejected": -86.13719940185547,
|
| 289 |
+
"loss": 0.6555,
|
| 290 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 291 |
+
"rewards/chosen": -0.04952271655201912,
|
| 292 |
+
"rewards/margins": 0.07018387317657471,
|
| 293 |
+
"rewards/rejected": -0.11970658600330353,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.772151898734177,
|
| 298 |
+
"grad_norm": 0.9766960144042969,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": 1.7785131931304932,
|
| 301 |
+
"logits/rejected": 1.8624244928359985,
|
| 302 |
+
"logps/chosen": -91.82891845703125,
|
| 303 |
+
"logps/rejected": -102.28694915771484,
|
| 304 |
+
"loss": 0.6465,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.04159725084900856,
|
| 307 |
+
"rewards/margins": 0.09511855244636536,
|
| 308 |
+
"rewards/rejected": -0.1367158144712448,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.109704641350211,
|
| 313 |
+
"grad_norm": 0.9714512228965759,
|
| 314 |
+
"learning_rate": 4.024886035802432e-06,
|
| 315 |
+
"logits/chosen": 1.756864309310913,
|
| 316 |
+
"logits/rejected": 1.7497355937957764,
|
| 317 |
+
"logps/chosen": -82.28770446777344,
|
| 318 |
+
"logps/rejected": -72.7796859741211,
|
| 319 |
+
"loss": 0.6498,
|
| 320 |
+
"rewards/accuracies": 0.8125,
|
| 321 |
+
"rewards/chosen": -0.0668434351682663,
|
| 322 |
+
"rewards/margins": 0.1403656005859375,
|
| 323 |
+
"rewards/rejected": -0.2072090357542038,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.447257383966245,
|
| 328 |
+
"grad_norm": 0.9135355949401855,
|
| 329 |
+
"learning_rate": 3.9029676634059565e-06,
|
| 330 |
+
"logits/chosen": 1.677150011062622,
|
| 331 |
+
"logits/rejected": 1.7840830087661743,
|
| 332 |
+
"logps/chosen": -78.84297180175781,
|
| 333 |
+
"logps/rejected": -102.04107666015625,
|
| 334 |
+
"loss": 0.6438,
|
| 335 |
+
"rewards/accuracies": 0.75,
|
| 336 |
+
"rewards/chosen": -0.10343215614557266,
|
| 337 |
+
"rewards/margins": 0.15733790397644043,
|
| 338 |
+
"rewards/rejected": -0.2607700526714325,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.784810126582278,
|
| 343 |
+
"grad_norm": 0.8835084438323975,
|
| 344 |
+
"learning_rate": 3.7759691553595214e-06,
|
| 345 |
+
"logits/chosen": 1.8346344232559204,
|
| 346 |
+
"logits/rejected": 1.838543176651001,
|
| 347 |
+
"logps/chosen": -109.93656921386719,
|
| 348 |
+
"logps/rejected": -73.76078033447266,
|
| 349 |
+
"loss": 0.6279,
|
| 350 |
+
"rewards/accuracies": 0.75,
|
| 351 |
+
"rewards/chosen": -0.08149126917123795,
|
| 352 |
+
"rewards/margins": 0.17928050458431244,
|
| 353 |
+
"rewards/rejected": -0.26077181100845337,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.122362869198312,
|
| 358 |
+
"grad_norm": 0.9854581952095032,
|
| 359 |
+
"learning_rate": 3.6443503723320837e-06,
|
| 360 |
+
"logits/chosen": 1.7367273569107056,
|
| 361 |
+
"logits/rejected": 1.723976492881775,
|
| 362 |
+
"logps/chosen": -80.76436614990234,
|
| 363 |
+
"logps/rejected": -75.7645034790039,
|
| 364 |
+
"loss": 0.6309,
|
| 365 |
+
"rewards/accuracies": 0.762499988079071,
|
| 366 |
+
"rewards/chosen": -0.12716726958751678,
|
| 367 |
+
"rewards/margins": 0.15734827518463135,
|
| 368 |
+
"rewards/rejected": -0.2845155596733093,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 8.459915611814345,
|
| 373 |
+
"grad_norm": 0.9569210410118103,
|
| 374 |
+
"learning_rate": 3.508587904974522e-06,
|
| 375 |
+
"logits/chosen": 1.711611032485962,
|
| 376 |
+
"logits/rejected": 1.820723295211792,
|
| 377 |
+
"logps/chosen": -81.62940979003906,
|
| 378 |
+
"logps/rejected": -104.07059478759766,
|
| 379 |
+
"loss": 0.6206,
|
| 380 |
+
"rewards/accuracies": 0.800000011920929,
|
| 381 |
+
"rewards/chosen": -0.12964895367622375,
|
| 382 |
+
"rewards/margins": 0.2236514836549759,
|
| 383 |
+
"rewards/rejected": -0.35330042243003845,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.79746835443038,
|
| 388 |
+
"grad_norm": 0.9199231863021851,
|
| 389 |
+
"learning_rate": 3.3691733481883693e-06,
|
| 390 |
+
"logits/chosen": 1.860053300857544,
|
| 391 |
+
"logits/rejected": 1.8826453685760498,
|
| 392 |
+
"logps/chosen": -89.85298919677734,
|
| 393 |
+
"logps/rejected": -90.7202377319336,
|
| 394 |
+
"loss": 0.6129,
|
| 395 |
+
"rewards/accuracies": 0.75,
|
| 396 |
+
"rewards/chosen": -0.1632840931415558,
|
| 397 |
+
"rewards/margins": 0.22734332084655762,
|
| 398 |
+
"rewards/rejected": -0.3906274437904358,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.135021097046414,
|
| 403 |
+
"grad_norm": 0.996032178401947,
|
| 404 |
+
"learning_rate": 3.226611521064278e-06,
|
| 405 |
+
"logits/chosen": 1.8121602535247803,
|
| 406 |
+
"logits/rejected": 1.7851508855819702,
|
| 407 |
+
"logps/chosen": -76.85626220703125,
|
| 408 |
+
"logps/rejected": -77.3901138305664,
|
| 409 |
+
"loss": 0.6155,
|
| 410 |
+
"rewards/accuracies": 0.75,
|
| 411 |
+
"rewards/chosen": -0.16423651576042175,
|
| 412 |
+
"rewards/margins": 0.2163097858428955,
|
| 413 |
+
"rewards/rejected": -0.38054633140563965,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 9.472573839662447,
|
| 418 |
+
"grad_norm": 0.96324622631073,
|
| 419 |
+
"learning_rate": 3.0814186389357765e-06,
|
| 420 |
+
"logits/chosen": 1.7609102725982666,
|
| 421 |
+
"logits/rejected": 1.782065749168396,
|
| 422 |
+
"logps/chosen": -78.853271484375,
|
| 423 |
+
"logps/rejected": -81.43799591064453,
|
| 424 |
+
"loss": 0.5991,
|
| 425 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 426 |
+
"rewards/chosen": -0.19906465709209442,
|
| 427 |
+
"rewards/margins": 0.2417418658733368,
|
| 428 |
+
"rewards/rejected": -0.4408065378665924,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 9.810126582278482,
|
| 433 |
+
"grad_norm": 0.9327431917190552,
|
| 434 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 435 |
+
"logits/chosen": 1.7485430240631104,
|
| 436 |
+
"logits/rejected": 1.7885955572128296,
|
| 437 |
+
"logps/chosen": -81.84668731689453,
|
| 438 |
+
"logps/rejected": -84.5110855102539,
|
| 439 |
+
"loss": 0.6035,
|
| 440 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 441 |
+
"rewards/chosen": -0.24916405975818634,
|
| 442 |
+
"rewards/margins": 0.22875118255615234,
|
| 443 |
+
"rewards/rejected": -0.47791528701782227,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.147679324894515,
|
| 448 |
+
"grad_norm": 1.1683701276779175,
|
| 449 |
+
"learning_rate": 2.785250302445062e-06,
|
| 450 |
+
"logits/chosen": 1.8126602172851562,
|
| 451 |
+
"logits/rejected": 1.8814666271209717,
|
| 452 |
+
"logps/chosen": -105.7123031616211,
|
| 453 |
+
"logps/rejected": -92.78335571289062,
|
| 454 |
+
"loss": 0.5916,
|
| 455 |
+
"rewards/accuracies": 0.800000011920929,
|
| 456 |
+
"rewards/chosen": -0.257813036441803,
|
| 457 |
+
"rewards/margins": 0.28732481598854065,
|
| 458 |
+
"rewards/rejected": -0.5451378226280212,
|
| 459 |
+
"step": 300
|
| 460 |
+
}
|
| 461 |
+
],
|
| 462 |
+
"logging_steps": 10,
|
| 463 |
+
"max_steps": 580,
|
| 464 |
+
"num_input_tokens_seen": 0,
|
| 465 |
+
"num_train_epochs": 20,
|
| 466 |
+
"save_steps": 50,
|
| 467 |
+
"stateful_callbacks": {
|
| 468 |
+
"TrainerControl": {
|
| 469 |
+
"args": {
|
| 470 |
+
"should_epoch_stop": false,
|
| 471 |
+
"should_evaluate": false,
|
| 472 |
+
"should_log": false,
|
| 473 |
+
"should_save": true,
|
| 474 |
+
"should_training_stop": false
|
| 475 |
+
},
|
| 476 |
+
"attributes": {}
|
| 477 |
+
}
|
| 478 |
+
},
|
| 479 |
+
"total_flos": 1.0293313016661279e+18,
|
| 480 |
+
"train_batch_size": 1,
|
| 481 |
+
"trial_name": null,
|
| 482 |
+
"trial_params": null
|
| 483 |
+
}
|
Power_Area/checkpoint-350/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Power_Area/checkpoint-350/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Power_Area/checkpoint-350/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Power_Area/checkpoint-350/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Power_Area/checkpoint-350/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Power_Area/checkpoint-350/trainer_state.json
ADDED
|
@@ -0,0 +1,558 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 11.835443037974684,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 350,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33755274261603374,
|
| 13 |
+
"grad_norm": 0.4396141469478607,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": 1.6453087329864502,
|
| 16 |
+
"logits/rejected": 1.694819450378418,
|
| 17 |
+
"logps/chosen": -74.5937728881836,
|
| 18 |
+
"logps/rejected": -83.19783782958984,
|
| 19 |
+
"loss": 0.6928,
|
| 20 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 21 |
+
"rewards/chosen": 0.003385844174772501,
|
| 22 |
+
"rewards/margins": 0.004794469103217125,
|
| 23 |
+
"rewards/rejected": -0.0014086246956139803,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6751054852320675,
|
| 28 |
+
"grad_norm": 3.18404483795166,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": 1.7945035696029663,
|
| 31 |
+
"logits/rejected": 1.8347476720809937,
|
| 32 |
+
"logps/chosen": -95.46636199951172,
|
| 33 |
+
"logps/rejected": -101.22709655761719,
|
| 34 |
+
"loss": 0.6933,
|
| 35 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 36 |
+
"rewards/chosen": -0.0005593777750618756,
|
| 37 |
+
"rewards/margins": -0.002013001125305891,
|
| 38 |
+
"rewards/rejected": 0.0014536241069436073,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0126582278481013,
|
| 43 |
+
"grad_norm": 0.48596081137657166,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": 1.774155616760254,
|
| 46 |
+
"logits/rejected": 1.8374344110488892,
|
| 47 |
+
"logps/chosen": -82.01265716552734,
|
| 48 |
+
"logps/rejected": -84.23635864257812,
|
| 49 |
+
"loss": 0.6948,
|
| 50 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 51 |
+
"rewards/chosen": -0.0031326995231211185,
|
| 52 |
+
"rewards/margins": -0.00463916826993227,
|
| 53 |
+
"rewards/rejected": 0.0015064675826579332,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.350210970464135,
|
| 58 |
+
"grad_norm": 0.5144609808921814,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": 1.838865876197815,
|
| 61 |
+
"logits/rejected": 1.9505430459976196,
|
| 62 |
+
"logps/chosen": -73.50071716308594,
|
| 63 |
+
"logps/rejected": -88.8648452758789,
|
| 64 |
+
"loss": 0.6928,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.0035957477521151304,
|
| 67 |
+
"rewards/margins": -0.008830643258988857,
|
| 68 |
+
"rewards/rejected": 0.005234894808381796,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6877637130801688,
|
| 73 |
+
"grad_norm": 0.48295095562934875,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": 1.8197529315948486,
|
| 76 |
+
"logits/rejected": 1.8459796905517578,
|
| 77 |
+
"logps/chosen": -83.36590576171875,
|
| 78 |
+
"logps/rejected": -70.26930236816406,
|
| 79 |
+
"loss": 0.6929,
|
| 80 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 81 |
+
"rewards/chosen": -0.0030026868917047977,
|
| 82 |
+
"rewards/margins": -0.006082554347813129,
|
| 83 |
+
"rewards/rejected": 0.003079867223277688,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.0464135021097047,
|
| 88 |
+
"grad_norm": 0.5616092085838318,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": 1.7525272369384766,
|
| 91 |
+
"logits/rejected": 1.8092533349990845,
|
| 92 |
+
"logps/chosen": -82.01802062988281,
|
| 93 |
+
"logps/rejected": -78.39723205566406,
|
| 94 |
+
"loss": 0.6949,
|
| 95 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 96 |
+
"rewards/chosen": -0.0010920714121311903,
|
| 97 |
+
"rewards/margins": -0.0016235255170613527,
|
| 98 |
+
"rewards/rejected": 0.0005314538720995188,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3839662447257384,
|
| 103 |
+
"grad_norm": 0.5237122774124146,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": 1.754880666732788,
|
| 106 |
+
"logits/rejected": 1.8100305795669556,
|
| 107 |
+
"logps/chosen": -89.62864685058594,
|
| 108 |
+
"logps/rejected": -88.30036926269531,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5,
|
| 111 |
+
"rewards/chosen": -0.002314353361725807,
|
| 112 |
+
"rewards/margins": -0.001038494287058711,
|
| 113 |
+
"rewards/rejected": -0.0012758590746670961,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.721518987341772,
|
| 118 |
+
"grad_norm": 0.507128119468689,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": 1.7501789331436157,
|
| 121 |
+
"logits/rejected": 1.6666221618652344,
|
| 122 |
+
"logps/chosen": -94.74919128417969,
|
| 123 |
+
"logps/rejected": -74.9794692993164,
|
| 124 |
+
"loss": 0.6922,
|
| 125 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 126 |
+
"rewards/chosen": 0.00475720502436161,
|
| 127 |
+
"rewards/margins": 0.01054429542273283,
|
| 128 |
+
"rewards/rejected": -0.005787090864032507,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.059071729957806,
|
| 133 |
+
"grad_norm": 0.8151038885116577,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": 1.7203710079193115,
|
| 136 |
+
"logits/rejected": 1.7376699447631836,
|
| 137 |
+
"logps/chosen": -76.8824691772461,
|
| 138 |
+
"logps/rejected": -84.74555206298828,
|
| 139 |
+
"loss": 0.6925,
|
| 140 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 141 |
+
"rewards/chosen": 0.01064519863575697,
|
| 142 |
+
"rewards/margins": 0.012716365046799183,
|
| 143 |
+
"rewards/rejected": -0.0020711664110422134,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3966244725738397,
|
| 148 |
+
"grad_norm": 0.5476706027984619,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": 1.7857105731964111,
|
| 151 |
+
"logits/rejected": 1.7341340780258179,
|
| 152 |
+
"logps/chosen": -88.39775085449219,
|
| 153 |
+
"logps/rejected": -80.00445556640625,
|
| 154 |
+
"loss": 0.6893,
|
| 155 |
+
"rewards/accuracies": 0.612500011920929,
|
| 156 |
+
"rewards/chosen": 0.0052363635040819645,
|
| 157 |
+
"rewards/margins": 0.016881367191672325,
|
| 158 |
+
"rewards/rejected": -0.011645001359283924,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.7341772151898733,
|
| 163 |
+
"grad_norm": 0.6562405824661255,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": 1.737647294998169,
|
| 166 |
+
"logits/rejected": 1.7781591415405273,
|
| 167 |
+
"logps/chosen": -92.72380065917969,
|
| 168 |
+
"logps/rejected": -85.51634216308594,
|
| 169 |
+
"loss": 0.6899,
|
| 170 |
+
"rewards/accuracies": 0.512499988079071,
|
| 171 |
+
"rewards/chosen": -0.010819707065820694,
|
| 172 |
+
"rewards/margins": -0.0005886269500479102,
|
| 173 |
+
"rewards/rejected": -0.010231079533696175,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.071729957805907,
|
| 178 |
+
"grad_norm": 0.6393210291862488,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": 1.7890704870224,
|
| 181 |
+
"logits/rejected": 1.8340994119644165,
|
| 182 |
+
"logps/chosen": -87.615478515625,
|
| 183 |
+
"logps/rejected": -108.13908386230469,
|
| 184 |
+
"loss": 0.6872,
|
| 185 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 186 |
+
"rewards/chosen": 0.002250433200970292,
|
| 187 |
+
"rewards/margins": 0.012117428705096245,
|
| 188 |
+
"rewards/rejected": -0.009866995736956596,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.409282700421941,
|
| 193 |
+
"grad_norm": 0.7390326261520386,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": 1.7916072607040405,
|
| 196 |
+
"logits/rejected": 1.787153959274292,
|
| 197 |
+
"logps/chosen": -84.11034393310547,
|
| 198 |
+
"logps/rejected": -76.81166076660156,
|
| 199 |
+
"loss": 0.6844,
|
| 200 |
+
"rewards/accuracies": 0.5625,
|
| 201 |
+
"rewards/chosen": -0.003190569579601288,
|
| 202 |
+
"rewards/margins": 0.015628555789589882,
|
| 203 |
+
"rewards/rejected": -0.01881912164390087,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.746835443037975,
|
| 208 |
+
"grad_norm": 0.7888330817222595,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": 1.8455331325531006,
|
| 211 |
+
"logits/rejected": 1.8137515783309937,
|
| 212 |
+
"logps/chosen": -78.94912719726562,
|
| 213 |
+
"logps/rejected": -76.1368637084961,
|
| 214 |
+
"loss": 0.6819,
|
| 215 |
+
"rewards/accuracies": 0.625,
|
| 216 |
+
"rewards/chosen": -0.012986091896891594,
|
| 217 |
+
"rewards/margins": 0.015167826786637306,
|
| 218 |
+
"rewards/rejected": -0.02815392054617405,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.084388185654008,
|
| 223 |
+
"grad_norm": 0.7248090505599976,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": 1.6686553955078125,
|
| 226 |
+
"logits/rejected": 1.6654260158538818,
|
| 227 |
+
"logps/chosen": -78.25769805908203,
|
| 228 |
+
"logps/rejected": -71.3498306274414,
|
| 229 |
+
"loss": 0.677,
|
| 230 |
+
"rewards/accuracies": 0.612500011920929,
|
| 231 |
+
"rewards/chosen": -0.0182911679148674,
|
| 232 |
+
"rewards/margins": 0.02633112668991089,
|
| 233 |
+
"rewards/rejected": -0.04462229460477829,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.421940928270042,
|
| 238 |
+
"grad_norm": 0.7906918525695801,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": 1.8054498434066772,
|
| 241 |
+
"logits/rejected": 1.751422643661499,
|
| 242 |
+
"logps/chosen": -91.65776824951172,
|
| 243 |
+
"logps/rejected": -68.41027069091797,
|
| 244 |
+
"loss": 0.6741,
|
| 245 |
+
"rewards/accuracies": 0.574999988079071,
|
| 246 |
+
"rewards/chosen": -0.04313550516963005,
|
| 247 |
+
"rewards/margins": 0.017568334937095642,
|
| 248 |
+
"rewards/rejected": -0.060703836381435394,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.759493670886076,
|
| 253 |
+
"grad_norm": 0.8152453303337097,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": 1.742419958114624,
|
| 256 |
+
"logits/rejected": 1.9456249475479126,
|
| 257 |
+
"logps/chosen": -80.52605438232422,
|
| 258 |
+
"logps/rejected": -117.02473449707031,
|
| 259 |
+
"loss": 0.67,
|
| 260 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 261 |
+
"rewards/chosen": -0.030041133984923363,
|
| 262 |
+
"rewards/margins": 0.03393586724996567,
|
| 263 |
+
"rewards/rejected": -0.06397700309753418,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.09704641350211,
|
| 268 |
+
"grad_norm": 0.7848192453384399,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": 1.836090087890625,
|
| 271 |
+
"logits/rejected": 2.0285377502441406,
|
| 272 |
+
"logps/chosen": -72.87449645996094,
|
| 273 |
+
"logps/rejected": -101.46552276611328,
|
| 274 |
+
"loss": 0.6659,
|
| 275 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 276 |
+
"rewards/chosen": -0.04543738812208176,
|
| 277 |
+
"rewards/margins": 0.0431094653904438,
|
| 278 |
+
"rewards/rejected": -0.08854684978723526,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.434599156118144,
|
| 283 |
+
"grad_norm": 0.8349910378456116,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": 1.7459189891815186,
|
| 286 |
+
"logits/rejected": 1.8324615955352783,
|
| 287 |
+
"logps/chosen": -72.0348892211914,
|
| 288 |
+
"logps/rejected": -86.13719940185547,
|
| 289 |
+
"loss": 0.6555,
|
| 290 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 291 |
+
"rewards/chosen": -0.04952271655201912,
|
| 292 |
+
"rewards/margins": 0.07018387317657471,
|
| 293 |
+
"rewards/rejected": -0.11970658600330353,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.772151898734177,
|
| 298 |
+
"grad_norm": 0.9766960144042969,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": 1.7785131931304932,
|
| 301 |
+
"logits/rejected": 1.8624244928359985,
|
| 302 |
+
"logps/chosen": -91.82891845703125,
|
| 303 |
+
"logps/rejected": -102.28694915771484,
|
| 304 |
+
"loss": 0.6465,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.04159725084900856,
|
| 307 |
+
"rewards/margins": 0.09511855244636536,
|
| 308 |
+
"rewards/rejected": -0.1367158144712448,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.109704641350211,
|
| 313 |
+
"grad_norm": 0.9714512228965759,
|
| 314 |
+
"learning_rate": 4.024886035802432e-06,
|
| 315 |
+
"logits/chosen": 1.756864309310913,
|
| 316 |
+
"logits/rejected": 1.7497355937957764,
|
| 317 |
+
"logps/chosen": -82.28770446777344,
|
| 318 |
+
"logps/rejected": -72.7796859741211,
|
| 319 |
+
"loss": 0.6498,
|
| 320 |
+
"rewards/accuracies": 0.8125,
|
| 321 |
+
"rewards/chosen": -0.0668434351682663,
|
| 322 |
+
"rewards/margins": 0.1403656005859375,
|
| 323 |
+
"rewards/rejected": -0.2072090357542038,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.447257383966245,
|
| 328 |
+
"grad_norm": 0.9135355949401855,
|
| 329 |
+
"learning_rate": 3.9029676634059565e-06,
|
| 330 |
+
"logits/chosen": 1.677150011062622,
|
| 331 |
+
"logits/rejected": 1.7840830087661743,
|
| 332 |
+
"logps/chosen": -78.84297180175781,
|
| 333 |
+
"logps/rejected": -102.04107666015625,
|
| 334 |
+
"loss": 0.6438,
|
| 335 |
+
"rewards/accuracies": 0.75,
|
| 336 |
+
"rewards/chosen": -0.10343215614557266,
|
| 337 |
+
"rewards/margins": 0.15733790397644043,
|
| 338 |
+
"rewards/rejected": -0.2607700526714325,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.784810126582278,
|
| 343 |
+
"grad_norm": 0.8835084438323975,
|
| 344 |
+
"learning_rate": 3.7759691553595214e-06,
|
| 345 |
+
"logits/chosen": 1.8346344232559204,
|
| 346 |
+
"logits/rejected": 1.838543176651001,
|
| 347 |
+
"logps/chosen": -109.93656921386719,
|
| 348 |
+
"logps/rejected": -73.76078033447266,
|
| 349 |
+
"loss": 0.6279,
|
| 350 |
+
"rewards/accuracies": 0.75,
|
| 351 |
+
"rewards/chosen": -0.08149126917123795,
|
| 352 |
+
"rewards/margins": 0.17928050458431244,
|
| 353 |
+
"rewards/rejected": -0.26077181100845337,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.122362869198312,
|
| 358 |
+
"grad_norm": 0.9854581952095032,
|
| 359 |
+
"learning_rate": 3.6443503723320837e-06,
|
| 360 |
+
"logits/chosen": 1.7367273569107056,
|
| 361 |
+
"logits/rejected": 1.723976492881775,
|
| 362 |
+
"logps/chosen": -80.76436614990234,
|
| 363 |
+
"logps/rejected": -75.7645034790039,
|
| 364 |
+
"loss": 0.6309,
|
| 365 |
+
"rewards/accuracies": 0.762499988079071,
|
| 366 |
+
"rewards/chosen": -0.12716726958751678,
|
| 367 |
+
"rewards/margins": 0.15734827518463135,
|
| 368 |
+
"rewards/rejected": -0.2845155596733093,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 8.459915611814345,
|
| 373 |
+
"grad_norm": 0.9569210410118103,
|
| 374 |
+
"learning_rate": 3.508587904974522e-06,
|
| 375 |
+
"logits/chosen": 1.711611032485962,
|
| 376 |
+
"logits/rejected": 1.820723295211792,
|
| 377 |
+
"logps/chosen": -81.62940979003906,
|
| 378 |
+
"logps/rejected": -104.07059478759766,
|
| 379 |
+
"loss": 0.6206,
|
| 380 |
+
"rewards/accuracies": 0.800000011920929,
|
| 381 |
+
"rewards/chosen": -0.12964895367622375,
|
| 382 |
+
"rewards/margins": 0.2236514836549759,
|
| 383 |
+
"rewards/rejected": -0.35330042243003845,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.79746835443038,
|
| 388 |
+
"grad_norm": 0.9199231863021851,
|
| 389 |
+
"learning_rate": 3.3691733481883693e-06,
|
| 390 |
+
"logits/chosen": 1.860053300857544,
|
| 391 |
+
"logits/rejected": 1.8826453685760498,
|
| 392 |
+
"logps/chosen": -89.85298919677734,
|
| 393 |
+
"logps/rejected": -90.7202377319336,
|
| 394 |
+
"loss": 0.6129,
|
| 395 |
+
"rewards/accuracies": 0.75,
|
| 396 |
+
"rewards/chosen": -0.1632840931415558,
|
| 397 |
+
"rewards/margins": 0.22734332084655762,
|
| 398 |
+
"rewards/rejected": -0.3906274437904358,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.135021097046414,
|
| 403 |
+
"grad_norm": 0.996032178401947,
|
| 404 |
+
"learning_rate": 3.226611521064278e-06,
|
| 405 |
+
"logits/chosen": 1.8121602535247803,
|
| 406 |
+
"logits/rejected": 1.7851508855819702,
|
| 407 |
+
"logps/chosen": -76.85626220703125,
|
| 408 |
+
"logps/rejected": -77.3901138305664,
|
| 409 |
+
"loss": 0.6155,
|
| 410 |
+
"rewards/accuracies": 0.75,
|
| 411 |
+
"rewards/chosen": -0.16423651576042175,
|
| 412 |
+
"rewards/margins": 0.2163097858428955,
|
| 413 |
+
"rewards/rejected": -0.38054633140563965,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 9.472573839662447,
|
| 418 |
+
"grad_norm": 0.96324622631073,
|
| 419 |
+
"learning_rate": 3.0814186389357765e-06,
|
| 420 |
+
"logits/chosen": 1.7609102725982666,
|
| 421 |
+
"logits/rejected": 1.782065749168396,
|
| 422 |
+
"logps/chosen": -78.853271484375,
|
| 423 |
+
"logps/rejected": -81.43799591064453,
|
| 424 |
+
"loss": 0.5991,
|
| 425 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 426 |
+
"rewards/chosen": -0.19906465709209442,
|
| 427 |
+
"rewards/margins": 0.2417418658733368,
|
| 428 |
+
"rewards/rejected": -0.4408065378665924,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 9.810126582278482,
|
| 433 |
+
"grad_norm": 0.9327431917190552,
|
| 434 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 435 |
+
"logits/chosen": 1.7485430240631104,
|
| 436 |
+
"logits/rejected": 1.7885955572128296,
|
| 437 |
+
"logps/chosen": -81.84668731689453,
|
| 438 |
+
"logps/rejected": -84.5110855102539,
|
| 439 |
+
"loss": 0.6035,
|
| 440 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 441 |
+
"rewards/chosen": -0.24916405975818634,
|
| 442 |
+
"rewards/margins": 0.22875118255615234,
|
| 443 |
+
"rewards/rejected": -0.47791528701782227,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.147679324894515,
|
| 448 |
+
"grad_norm": 1.1683701276779175,
|
| 449 |
+
"learning_rate": 2.785250302445062e-06,
|
| 450 |
+
"logits/chosen": 1.8126602172851562,
|
| 451 |
+
"logits/rejected": 1.8814666271209717,
|
| 452 |
+
"logps/chosen": -105.7123031616211,
|
| 453 |
+
"logps/rejected": -92.78335571289062,
|
| 454 |
+
"loss": 0.5916,
|
| 455 |
+
"rewards/accuracies": 0.800000011920929,
|
| 456 |
+
"rewards/chosen": -0.257813036441803,
|
| 457 |
+
"rewards/margins": 0.28732481598854065,
|
| 458 |
+
"rewards/rejected": -0.5451378226280212,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.485232067510548,
|
| 463 |
+
"grad_norm": 1.078698754310608,
|
| 464 |
+
"learning_rate": 2.6353472714635443e-06,
|
| 465 |
+
"logits/chosen": 1.7991764545440674,
|
| 466 |
+
"logits/rejected": 1.8787552118301392,
|
| 467 |
+
"logps/chosen": -70.400634765625,
|
| 468 |
+
"logps/rejected": -72.78517150878906,
|
| 469 |
+
"loss": 0.5893,
|
| 470 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 471 |
+
"rewards/chosen": -0.23745933175086975,
|
| 472 |
+
"rewards/margins": 0.22456249594688416,
|
| 473 |
+
"rewards/rejected": -0.4620218276977539,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 10.822784810126583,
|
| 478 |
+
"grad_norm": 1.0667306184768677,
|
| 479 |
+
"learning_rate": 2.4849541490017868e-06,
|
| 480 |
+
"logits/chosen": 1.7493784427642822,
|
| 481 |
+
"logits/rejected": 1.7776050567626953,
|
| 482 |
+
"logps/chosen": -79.56948852539062,
|
| 483 |
+
"logps/rejected": -95.15191650390625,
|
| 484 |
+
"loss": 0.5943,
|
| 485 |
+
"rewards/accuracies": 0.8125,
|
| 486 |
+
"rewards/chosen": -0.2948698401451111,
|
| 487 |
+
"rewards/margins": 0.27440011501312256,
|
| 488 |
+
"rewards/rejected": -0.5692699551582336,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.160337552742616,
|
| 493 |
+
"grad_norm": 1.1734286546707153,
|
| 494 |
+
"learning_rate": 2.3346155074564712e-06,
|
| 495 |
+
"logits/chosen": 1.7588024139404297,
|
| 496 |
+
"logits/rejected": 1.6906486749649048,
|
| 497 |
+
"logps/chosen": -92.88114929199219,
|
| 498 |
+
"logps/rejected": -87.77473449707031,
|
| 499 |
+
"loss": 0.5748,
|
| 500 |
+
"rewards/accuracies": 0.8125,
|
| 501 |
+
"rewards/chosen": -0.26193878054618835,
|
| 502 |
+
"rewards/margins": 0.31644436717033386,
|
| 503 |
+
"rewards/rejected": -0.5783831477165222,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 11.49789029535865,
|
| 508 |
+
"grad_norm": 1.0506142377853394,
|
| 509 |
+
"learning_rate": 2.184875721949277e-06,
|
| 510 |
+
"logits/chosen": 1.6390129327774048,
|
| 511 |
+
"logits/rejected": 1.6817207336425781,
|
| 512 |
+
"logps/chosen": -85.6020278930664,
|
| 513 |
+
"logps/rejected": -81.51480865478516,
|
| 514 |
+
"loss": 0.5755,
|
| 515 |
+
"rewards/accuracies": 0.824999988079071,
|
| 516 |
+
"rewards/chosen": -0.2864437997341156,
|
| 517 |
+
"rewards/margins": 0.3067106604576111,
|
| 518 |
+
"rewards/rejected": -0.5931544899940491,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 11.835443037974684,
|
| 523 |
+
"grad_norm": 1.0367387533187866,
|
| 524 |
+
"learning_rate": 2.0362769991485514e-06,
|
| 525 |
+
"logits/chosen": 1.811912178993225,
|
| 526 |
+
"logits/rejected": 1.8571999073028564,
|
| 527 |
+
"logps/chosen": -79.2660903930664,
|
| 528 |
+
"logps/rejected": -105.51014709472656,
|
| 529 |
+
"loss": 0.5743,
|
| 530 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 531 |
+
"rewards/chosen": -0.2905730605125427,
|
| 532 |
+
"rewards/margins": 0.37750759720802307,
|
| 533 |
+
"rewards/rejected": -0.6680806279182434,
|
| 534 |
+
"step": 350
|
| 535 |
+
}
|
| 536 |
+
],
|
| 537 |
+
"logging_steps": 10,
|
| 538 |
+
"max_steps": 580,
|
| 539 |
+
"num_input_tokens_seen": 0,
|
| 540 |
+
"num_train_epochs": 20,
|
| 541 |
+
"save_steps": 50,
|
| 542 |
+
"stateful_callbacks": {
|
| 543 |
+
"TrainerControl": {
|
| 544 |
+
"args": {
|
| 545 |
+
"should_epoch_stop": false,
|
| 546 |
+
"should_evaluate": false,
|
| 547 |
+
"should_log": false,
|
| 548 |
+
"should_save": true,
|
| 549 |
+
"should_training_stop": false
|
| 550 |
+
},
|
| 551 |
+
"attributes": {}
|
| 552 |
+
}
|
| 553 |
+
},
|
| 554 |
+
"total_flos": 1.20200497068612e+18,
|
| 555 |
+
"train_batch_size": 1,
|
| 556 |
+
"trial_name": null,
|
| 557 |
+
"trial_params": null
|
| 558 |
+
}
|
Power_Area/checkpoint-400/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Power_Area/checkpoint-400/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Power_Area/checkpoint-400/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Power_Area/checkpoint-400/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Power_Area/checkpoint-400/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Power_Area/checkpoint-400/trainer_state.json
ADDED
|
@@ -0,0 +1,633 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 13.523206751054852,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 400,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33755274261603374,
|
| 13 |
+
"grad_norm": 0.4396141469478607,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": 1.6453087329864502,
|
| 16 |
+
"logits/rejected": 1.694819450378418,
|
| 17 |
+
"logps/chosen": -74.5937728881836,
|
| 18 |
+
"logps/rejected": -83.19783782958984,
|
| 19 |
+
"loss": 0.6928,
|
| 20 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 21 |
+
"rewards/chosen": 0.003385844174772501,
|
| 22 |
+
"rewards/margins": 0.004794469103217125,
|
| 23 |
+
"rewards/rejected": -0.0014086246956139803,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6751054852320675,
|
| 28 |
+
"grad_norm": 3.18404483795166,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": 1.7945035696029663,
|
| 31 |
+
"logits/rejected": 1.8347476720809937,
|
| 32 |
+
"logps/chosen": -95.46636199951172,
|
| 33 |
+
"logps/rejected": -101.22709655761719,
|
| 34 |
+
"loss": 0.6933,
|
| 35 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 36 |
+
"rewards/chosen": -0.0005593777750618756,
|
| 37 |
+
"rewards/margins": -0.002013001125305891,
|
| 38 |
+
"rewards/rejected": 0.0014536241069436073,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0126582278481013,
|
| 43 |
+
"grad_norm": 0.48596081137657166,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": 1.774155616760254,
|
| 46 |
+
"logits/rejected": 1.8374344110488892,
|
| 47 |
+
"logps/chosen": -82.01265716552734,
|
| 48 |
+
"logps/rejected": -84.23635864257812,
|
| 49 |
+
"loss": 0.6948,
|
| 50 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 51 |
+
"rewards/chosen": -0.0031326995231211185,
|
| 52 |
+
"rewards/margins": -0.00463916826993227,
|
| 53 |
+
"rewards/rejected": 0.0015064675826579332,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.350210970464135,
|
| 58 |
+
"grad_norm": 0.5144609808921814,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": 1.838865876197815,
|
| 61 |
+
"logits/rejected": 1.9505430459976196,
|
| 62 |
+
"logps/chosen": -73.50071716308594,
|
| 63 |
+
"logps/rejected": -88.8648452758789,
|
| 64 |
+
"loss": 0.6928,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.0035957477521151304,
|
| 67 |
+
"rewards/margins": -0.008830643258988857,
|
| 68 |
+
"rewards/rejected": 0.005234894808381796,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6877637130801688,
|
| 73 |
+
"grad_norm": 0.48295095562934875,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": 1.8197529315948486,
|
| 76 |
+
"logits/rejected": 1.8459796905517578,
|
| 77 |
+
"logps/chosen": -83.36590576171875,
|
| 78 |
+
"logps/rejected": -70.26930236816406,
|
| 79 |
+
"loss": 0.6929,
|
| 80 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 81 |
+
"rewards/chosen": -0.0030026868917047977,
|
| 82 |
+
"rewards/margins": -0.006082554347813129,
|
| 83 |
+
"rewards/rejected": 0.003079867223277688,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.0464135021097047,
|
| 88 |
+
"grad_norm": 0.5616092085838318,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": 1.7525272369384766,
|
| 91 |
+
"logits/rejected": 1.8092533349990845,
|
| 92 |
+
"logps/chosen": -82.01802062988281,
|
| 93 |
+
"logps/rejected": -78.39723205566406,
|
| 94 |
+
"loss": 0.6949,
|
| 95 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 96 |
+
"rewards/chosen": -0.0010920714121311903,
|
| 97 |
+
"rewards/margins": -0.0016235255170613527,
|
| 98 |
+
"rewards/rejected": 0.0005314538720995188,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3839662447257384,
|
| 103 |
+
"grad_norm": 0.5237122774124146,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": 1.754880666732788,
|
| 106 |
+
"logits/rejected": 1.8100305795669556,
|
| 107 |
+
"logps/chosen": -89.62864685058594,
|
| 108 |
+
"logps/rejected": -88.30036926269531,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5,
|
| 111 |
+
"rewards/chosen": -0.002314353361725807,
|
| 112 |
+
"rewards/margins": -0.001038494287058711,
|
| 113 |
+
"rewards/rejected": -0.0012758590746670961,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.721518987341772,
|
| 118 |
+
"grad_norm": 0.507128119468689,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": 1.7501789331436157,
|
| 121 |
+
"logits/rejected": 1.6666221618652344,
|
| 122 |
+
"logps/chosen": -94.74919128417969,
|
| 123 |
+
"logps/rejected": -74.9794692993164,
|
| 124 |
+
"loss": 0.6922,
|
| 125 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 126 |
+
"rewards/chosen": 0.00475720502436161,
|
| 127 |
+
"rewards/margins": 0.01054429542273283,
|
| 128 |
+
"rewards/rejected": -0.005787090864032507,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.059071729957806,
|
| 133 |
+
"grad_norm": 0.8151038885116577,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": 1.7203710079193115,
|
| 136 |
+
"logits/rejected": 1.7376699447631836,
|
| 137 |
+
"logps/chosen": -76.8824691772461,
|
| 138 |
+
"logps/rejected": -84.74555206298828,
|
| 139 |
+
"loss": 0.6925,
|
| 140 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 141 |
+
"rewards/chosen": 0.01064519863575697,
|
| 142 |
+
"rewards/margins": 0.012716365046799183,
|
| 143 |
+
"rewards/rejected": -0.0020711664110422134,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3966244725738397,
|
| 148 |
+
"grad_norm": 0.5476706027984619,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": 1.7857105731964111,
|
| 151 |
+
"logits/rejected": 1.7341340780258179,
|
| 152 |
+
"logps/chosen": -88.39775085449219,
|
| 153 |
+
"logps/rejected": -80.00445556640625,
|
| 154 |
+
"loss": 0.6893,
|
| 155 |
+
"rewards/accuracies": 0.612500011920929,
|
| 156 |
+
"rewards/chosen": 0.0052363635040819645,
|
| 157 |
+
"rewards/margins": 0.016881367191672325,
|
| 158 |
+
"rewards/rejected": -0.011645001359283924,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.7341772151898733,
|
| 163 |
+
"grad_norm": 0.6562405824661255,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": 1.737647294998169,
|
| 166 |
+
"logits/rejected": 1.7781591415405273,
|
| 167 |
+
"logps/chosen": -92.72380065917969,
|
| 168 |
+
"logps/rejected": -85.51634216308594,
|
| 169 |
+
"loss": 0.6899,
|
| 170 |
+
"rewards/accuracies": 0.512499988079071,
|
| 171 |
+
"rewards/chosen": -0.010819707065820694,
|
| 172 |
+
"rewards/margins": -0.0005886269500479102,
|
| 173 |
+
"rewards/rejected": -0.010231079533696175,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.071729957805907,
|
| 178 |
+
"grad_norm": 0.6393210291862488,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": 1.7890704870224,
|
| 181 |
+
"logits/rejected": 1.8340994119644165,
|
| 182 |
+
"logps/chosen": -87.615478515625,
|
| 183 |
+
"logps/rejected": -108.13908386230469,
|
| 184 |
+
"loss": 0.6872,
|
| 185 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 186 |
+
"rewards/chosen": 0.002250433200970292,
|
| 187 |
+
"rewards/margins": 0.012117428705096245,
|
| 188 |
+
"rewards/rejected": -0.009866995736956596,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.409282700421941,
|
| 193 |
+
"grad_norm": 0.7390326261520386,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": 1.7916072607040405,
|
| 196 |
+
"logits/rejected": 1.787153959274292,
|
| 197 |
+
"logps/chosen": -84.11034393310547,
|
| 198 |
+
"logps/rejected": -76.81166076660156,
|
| 199 |
+
"loss": 0.6844,
|
| 200 |
+
"rewards/accuracies": 0.5625,
|
| 201 |
+
"rewards/chosen": -0.003190569579601288,
|
| 202 |
+
"rewards/margins": 0.015628555789589882,
|
| 203 |
+
"rewards/rejected": -0.01881912164390087,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.746835443037975,
|
| 208 |
+
"grad_norm": 0.7888330817222595,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": 1.8455331325531006,
|
| 211 |
+
"logits/rejected": 1.8137515783309937,
|
| 212 |
+
"logps/chosen": -78.94912719726562,
|
| 213 |
+
"logps/rejected": -76.1368637084961,
|
| 214 |
+
"loss": 0.6819,
|
| 215 |
+
"rewards/accuracies": 0.625,
|
| 216 |
+
"rewards/chosen": -0.012986091896891594,
|
| 217 |
+
"rewards/margins": 0.015167826786637306,
|
| 218 |
+
"rewards/rejected": -0.02815392054617405,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.084388185654008,
|
| 223 |
+
"grad_norm": 0.7248090505599976,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": 1.6686553955078125,
|
| 226 |
+
"logits/rejected": 1.6654260158538818,
|
| 227 |
+
"logps/chosen": -78.25769805908203,
|
| 228 |
+
"logps/rejected": -71.3498306274414,
|
| 229 |
+
"loss": 0.677,
|
| 230 |
+
"rewards/accuracies": 0.612500011920929,
|
| 231 |
+
"rewards/chosen": -0.0182911679148674,
|
| 232 |
+
"rewards/margins": 0.02633112668991089,
|
| 233 |
+
"rewards/rejected": -0.04462229460477829,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.421940928270042,
|
| 238 |
+
"grad_norm": 0.7906918525695801,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": 1.8054498434066772,
|
| 241 |
+
"logits/rejected": 1.751422643661499,
|
| 242 |
+
"logps/chosen": -91.65776824951172,
|
| 243 |
+
"logps/rejected": -68.41027069091797,
|
| 244 |
+
"loss": 0.6741,
|
| 245 |
+
"rewards/accuracies": 0.574999988079071,
|
| 246 |
+
"rewards/chosen": -0.04313550516963005,
|
| 247 |
+
"rewards/margins": 0.017568334937095642,
|
| 248 |
+
"rewards/rejected": -0.060703836381435394,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.759493670886076,
|
| 253 |
+
"grad_norm": 0.8152453303337097,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": 1.742419958114624,
|
| 256 |
+
"logits/rejected": 1.9456249475479126,
|
| 257 |
+
"logps/chosen": -80.52605438232422,
|
| 258 |
+
"logps/rejected": -117.02473449707031,
|
| 259 |
+
"loss": 0.67,
|
| 260 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 261 |
+
"rewards/chosen": -0.030041133984923363,
|
| 262 |
+
"rewards/margins": 0.03393586724996567,
|
| 263 |
+
"rewards/rejected": -0.06397700309753418,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.09704641350211,
|
| 268 |
+
"grad_norm": 0.7848192453384399,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": 1.836090087890625,
|
| 271 |
+
"logits/rejected": 2.0285377502441406,
|
| 272 |
+
"logps/chosen": -72.87449645996094,
|
| 273 |
+
"logps/rejected": -101.46552276611328,
|
| 274 |
+
"loss": 0.6659,
|
| 275 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 276 |
+
"rewards/chosen": -0.04543738812208176,
|
| 277 |
+
"rewards/margins": 0.0431094653904438,
|
| 278 |
+
"rewards/rejected": -0.08854684978723526,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.434599156118144,
|
| 283 |
+
"grad_norm": 0.8349910378456116,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": 1.7459189891815186,
|
| 286 |
+
"logits/rejected": 1.8324615955352783,
|
| 287 |
+
"logps/chosen": -72.0348892211914,
|
| 288 |
+
"logps/rejected": -86.13719940185547,
|
| 289 |
+
"loss": 0.6555,
|
| 290 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 291 |
+
"rewards/chosen": -0.04952271655201912,
|
| 292 |
+
"rewards/margins": 0.07018387317657471,
|
| 293 |
+
"rewards/rejected": -0.11970658600330353,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.772151898734177,
|
| 298 |
+
"grad_norm": 0.9766960144042969,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": 1.7785131931304932,
|
| 301 |
+
"logits/rejected": 1.8624244928359985,
|
| 302 |
+
"logps/chosen": -91.82891845703125,
|
| 303 |
+
"logps/rejected": -102.28694915771484,
|
| 304 |
+
"loss": 0.6465,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.04159725084900856,
|
| 307 |
+
"rewards/margins": 0.09511855244636536,
|
| 308 |
+
"rewards/rejected": -0.1367158144712448,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.109704641350211,
|
| 313 |
+
"grad_norm": 0.9714512228965759,
|
| 314 |
+
"learning_rate": 4.024886035802432e-06,
|
| 315 |
+
"logits/chosen": 1.756864309310913,
|
| 316 |
+
"logits/rejected": 1.7497355937957764,
|
| 317 |
+
"logps/chosen": -82.28770446777344,
|
| 318 |
+
"logps/rejected": -72.7796859741211,
|
| 319 |
+
"loss": 0.6498,
|
| 320 |
+
"rewards/accuracies": 0.8125,
|
| 321 |
+
"rewards/chosen": -0.0668434351682663,
|
| 322 |
+
"rewards/margins": 0.1403656005859375,
|
| 323 |
+
"rewards/rejected": -0.2072090357542038,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.447257383966245,
|
| 328 |
+
"grad_norm": 0.9135355949401855,
|
| 329 |
+
"learning_rate": 3.9029676634059565e-06,
|
| 330 |
+
"logits/chosen": 1.677150011062622,
|
| 331 |
+
"logits/rejected": 1.7840830087661743,
|
| 332 |
+
"logps/chosen": -78.84297180175781,
|
| 333 |
+
"logps/rejected": -102.04107666015625,
|
| 334 |
+
"loss": 0.6438,
|
| 335 |
+
"rewards/accuracies": 0.75,
|
| 336 |
+
"rewards/chosen": -0.10343215614557266,
|
| 337 |
+
"rewards/margins": 0.15733790397644043,
|
| 338 |
+
"rewards/rejected": -0.2607700526714325,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.784810126582278,
|
| 343 |
+
"grad_norm": 0.8835084438323975,
|
| 344 |
+
"learning_rate": 3.7759691553595214e-06,
|
| 345 |
+
"logits/chosen": 1.8346344232559204,
|
| 346 |
+
"logits/rejected": 1.838543176651001,
|
| 347 |
+
"logps/chosen": -109.93656921386719,
|
| 348 |
+
"logps/rejected": -73.76078033447266,
|
| 349 |
+
"loss": 0.6279,
|
| 350 |
+
"rewards/accuracies": 0.75,
|
| 351 |
+
"rewards/chosen": -0.08149126917123795,
|
| 352 |
+
"rewards/margins": 0.17928050458431244,
|
| 353 |
+
"rewards/rejected": -0.26077181100845337,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.122362869198312,
|
| 358 |
+
"grad_norm": 0.9854581952095032,
|
| 359 |
+
"learning_rate": 3.6443503723320837e-06,
|
| 360 |
+
"logits/chosen": 1.7367273569107056,
|
| 361 |
+
"logits/rejected": 1.723976492881775,
|
| 362 |
+
"logps/chosen": -80.76436614990234,
|
| 363 |
+
"logps/rejected": -75.7645034790039,
|
| 364 |
+
"loss": 0.6309,
|
| 365 |
+
"rewards/accuracies": 0.762499988079071,
|
| 366 |
+
"rewards/chosen": -0.12716726958751678,
|
| 367 |
+
"rewards/margins": 0.15734827518463135,
|
| 368 |
+
"rewards/rejected": -0.2845155596733093,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 8.459915611814345,
|
| 373 |
+
"grad_norm": 0.9569210410118103,
|
| 374 |
+
"learning_rate": 3.508587904974522e-06,
|
| 375 |
+
"logits/chosen": 1.711611032485962,
|
| 376 |
+
"logits/rejected": 1.820723295211792,
|
| 377 |
+
"logps/chosen": -81.62940979003906,
|
| 378 |
+
"logps/rejected": -104.07059478759766,
|
| 379 |
+
"loss": 0.6206,
|
| 380 |
+
"rewards/accuracies": 0.800000011920929,
|
| 381 |
+
"rewards/chosen": -0.12964895367622375,
|
| 382 |
+
"rewards/margins": 0.2236514836549759,
|
| 383 |
+
"rewards/rejected": -0.35330042243003845,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.79746835443038,
|
| 388 |
+
"grad_norm": 0.9199231863021851,
|
| 389 |
+
"learning_rate": 3.3691733481883693e-06,
|
| 390 |
+
"logits/chosen": 1.860053300857544,
|
| 391 |
+
"logits/rejected": 1.8826453685760498,
|
| 392 |
+
"logps/chosen": -89.85298919677734,
|
| 393 |
+
"logps/rejected": -90.7202377319336,
|
| 394 |
+
"loss": 0.6129,
|
| 395 |
+
"rewards/accuracies": 0.75,
|
| 396 |
+
"rewards/chosen": -0.1632840931415558,
|
| 397 |
+
"rewards/margins": 0.22734332084655762,
|
| 398 |
+
"rewards/rejected": -0.3906274437904358,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.135021097046414,
|
| 403 |
+
"grad_norm": 0.996032178401947,
|
| 404 |
+
"learning_rate": 3.226611521064278e-06,
|
| 405 |
+
"logits/chosen": 1.8121602535247803,
|
| 406 |
+
"logits/rejected": 1.7851508855819702,
|
| 407 |
+
"logps/chosen": -76.85626220703125,
|
| 408 |
+
"logps/rejected": -77.3901138305664,
|
| 409 |
+
"loss": 0.6155,
|
| 410 |
+
"rewards/accuracies": 0.75,
|
| 411 |
+
"rewards/chosen": -0.16423651576042175,
|
| 412 |
+
"rewards/margins": 0.2163097858428955,
|
| 413 |
+
"rewards/rejected": -0.38054633140563965,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 9.472573839662447,
|
| 418 |
+
"grad_norm": 0.96324622631073,
|
| 419 |
+
"learning_rate": 3.0814186389357765e-06,
|
| 420 |
+
"logits/chosen": 1.7609102725982666,
|
| 421 |
+
"logits/rejected": 1.782065749168396,
|
| 422 |
+
"logps/chosen": -78.853271484375,
|
| 423 |
+
"logps/rejected": -81.43799591064453,
|
| 424 |
+
"loss": 0.5991,
|
| 425 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 426 |
+
"rewards/chosen": -0.19906465709209442,
|
| 427 |
+
"rewards/margins": 0.2417418658733368,
|
| 428 |
+
"rewards/rejected": -0.4408065378665924,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 9.810126582278482,
|
| 433 |
+
"grad_norm": 0.9327431917190552,
|
| 434 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 435 |
+
"logits/chosen": 1.7485430240631104,
|
| 436 |
+
"logits/rejected": 1.7885955572128296,
|
| 437 |
+
"logps/chosen": -81.84668731689453,
|
| 438 |
+
"logps/rejected": -84.5110855102539,
|
| 439 |
+
"loss": 0.6035,
|
| 440 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 441 |
+
"rewards/chosen": -0.24916405975818634,
|
| 442 |
+
"rewards/margins": 0.22875118255615234,
|
| 443 |
+
"rewards/rejected": -0.47791528701782227,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.147679324894515,
|
| 448 |
+
"grad_norm": 1.1683701276779175,
|
| 449 |
+
"learning_rate": 2.785250302445062e-06,
|
| 450 |
+
"logits/chosen": 1.8126602172851562,
|
| 451 |
+
"logits/rejected": 1.8814666271209717,
|
| 452 |
+
"logps/chosen": -105.7123031616211,
|
| 453 |
+
"logps/rejected": -92.78335571289062,
|
| 454 |
+
"loss": 0.5916,
|
| 455 |
+
"rewards/accuracies": 0.800000011920929,
|
| 456 |
+
"rewards/chosen": -0.257813036441803,
|
| 457 |
+
"rewards/margins": 0.28732481598854065,
|
| 458 |
+
"rewards/rejected": -0.5451378226280212,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.485232067510548,
|
| 463 |
+
"grad_norm": 1.078698754310608,
|
| 464 |
+
"learning_rate": 2.6353472714635443e-06,
|
| 465 |
+
"logits/chosen": 1.7991764545440674,
|
| 466 |
+
"logits/rejected": 1.8787552118301392,
|
| 467 |
+
"logps/chosen": -70.400634765625,
|
| 468 |
+
"logps/rejected": -72.78517150878906,
|
| 469 |
+
"loss": 0.5893,
|
| 470 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 471 |
+
"rewards/chosen": -0.23745933175086975,
|
| 472 |
+
"rewards/margins": 0.22456249594688416,
|
| 473 |
+
"rewards/rejected": -0.4620218276977539,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 10.822784810126583,
|
| 478 |
+
"grad_norm": 1.0667306184768677,
|
| 479 |
+
"learning_rate": 2.4849541490017868e-06,
|
| 480 |
+
"logits/chosen": 1.7493784427642822,
|
| 481 |
+
"logits/rejected": 1.7776050567626953,
|
| 482 |
+
"logps/chosen": -79.56948852539062,
|
| 483 |
+
"logps/rejected": -95.15191650390625,
|
| 484 |
+
"loss": 0.5943,
|
| 485 |
+
"rewards/accuracies": 0.8125,
|
| 486 |
+
"rewards/chosen": -0.2948698401451111,
|
| 487 |
+
"rewards/margins": 0.27440011501312256,
|
| 488 |
+
"rewards/rejected": -0.5692699551582336,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.160337552742616,
|
| 493 |
+
"grad_norm": 1.1734286546707153,
|
| 494 |
+
"learning_rate": 2.3346155074564712e-06,
|
| 495 |
+
"logits/chosen": 1.7588024139404297,
|
| 496 |
+
"logits/rejected": 1.6906486749649048,
|
| 497 |
+
"logps/chosen": -92.88114929199219,
|
| 498 |
+
"logps/rejected": -87.77473449707031,
|
| 499 |
+
"loss": 0.5748,
|
| 500 |
+
"rewards/accuracies": 0.8125,
|
| 501 |
+
"rewards/chosen": -0.26193878054618835,
|
| 502 |
+
"rewards/margins": 0.31644436717033386,
|
| 503 |
+
"rewards/rejected": -0.5783831477165222,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 11.49789029535865,
|
| 508 |
+
"grad_norm": 1.0506142377853394,
|
| 509 |
+
"learning_rate": 2.184875721949277e-06,
|
| 510 |
+
"logits/chosen": 1.6390129327774048,
|
| 511 |
+
"logits/rejected": 1.6817207336425781,
|
| 512 |
+
"logps/chosen": -85.6020278930664,
|
| 513 |
+
"logps/rejected": -81.51480865478516,
|
| 514 |
+
"loss": 0.5755,
|
| 515 |
+
"rewards/accuracies": 0.824999988079071,
|
| 516 |
+
"rewards/chosen": -0.2864437997341156,
|
| 517 |
+
"rewards/margins": 0.3067106604576111,
|
| 518 |
+
"rewards/rejected": -0.5931544899940491,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 11.835443037974684,
|
| 523 |
+
"grad_norm": 1.0367387533187866,
|
| 524 |
+
"learning_rate": 2.0362769991485514e-06,
|
| 525 |
+
"logits/chosen": 1.811912178993225,
|
| 526 |
+
"logits/rejected": 1.8571999073028564,
|
| 527 |
+
"logps/chosen": -79.2660903930664,
|
| 528 |
+
"logps/rejected": -105.51014709472656,
|
| 529 |
+
"loss": 0.5743,
|
| 530 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 531 |
+
"rewards/chosen": -0.2905730605125427,
|
| 532 |
+
"rewards/margins": 0.37750759720802307,
|
| 533 |
+
"rewards/rejected": -0.6680806279182434,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 12.172995780590718,
|
| 538 |
+
"grad_norm": 1.249039888381958,
|
| 539 |
+
"learning_rate": 1.8893574139429226e-06,
|
| 540 |
+
"logits/chosen": 1.8357423543930054,
|
| 541 |
+
"logits/rejected": 1.8285624980926514,
|
| 542 |
+
"logps/chosen": -85.5277099609375,
|
| 543 |
+
"logps/rejected": -90.13473510742188,
|
| 544 |
+
"loss": 0.575,
|
| 545 |
+
"rewards/accuracies": 0.762499988079071,
|
| 546 |
+
"rewards/chosen": -0.36660733819007874,
|
| 547 |
+
"rewards/margins": 0.3461737632751465,
|
| 548 |
+
"rewards/rejected": -0.7127811312675476,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 12.51054852320675,
|
| 553 |
+
"grad_norm": 1.1541879177093506,
|
| 554 |
+
"learning_rate": 1.744648961076068e-06,
|
| 555 |
+
"logits/chosen": 1.790567398071289,
|
| 556 |
+
"logits/rejected": 1.7228246927261353,
|
| 557 |
+
"logps/chosen": -86.40596008300781,
|
| 558 |
+
"logps/rejected": -75.5702896118164,
|
| 559 |
+
"loss": 0.5693,
|
| 560 |
+
"rewards/accuracies": 0.762499988079071,
|
| 561 |
+
"rewards/chosen": -0.34050875902175903,
|
| 562 |
+
"rewards/margins": 0.2642201781272888,
|
| 563 |
+
"rewards/rejected": -0.6047288775444031,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 12.848101265822784,
|
| 568 |
+
"grad_norm": 1.0363268852233887,
|
| 569 |
+
"learning_rate": 1.602675628797636e-06,
|
| 570 |
+
"logits/chosen": 1.6812736988067627,
|
| 571 |
+
"logits/rejected": 1.7188876867294312,
|
| 572 |
+
"logps/chosen": -81.14212799072266,
|
| 573 |
+
"logps/rejected": -82.90364074707031,
|
| 574 |
+
"loss": 0.5594,
|
| 575 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 576 |
+
"rewards/chosen": -0.3105277419090271,
|
| 577 |
+
"rewards/margins": 0.3372951149940491,
|
| 578 |
+
"rewards/rejected": -0.6478228569030762,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 13.185654008438819,
|
| 583 |
+
"grad_norm": 1.047418475151062,
|
| 584 |
+
"learning_rate": 1.4639515015056205e-06,
|
| 585 |
+
"logits/chosen": 1.6939361095428467,
|
| 586 |
+
"logits/rejected": 1.7271579504013062,
|
| 587 |
+
"logps/chosen": -86.88213348388672,
|
| 588 |
+
"logps/rejected": -99.46037292480469,
|
| 589 |
+
"loss": 0.558,
|
| 590 |
+
"rewards/accuracies": 0.762499988079071,
|
| 591 |
+
"rewards/chosen": -0.2660979926586151,
|
| 592 |
+
"rewards/margins": 0.4496893882751465,
|
| 593 |
+
"rewards/rejected": -0.7157873511314392,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 13.523206751054852,
|
| 598 |
+
"grad_norm": 1.1949480772018433,
|
| 599 |
+
"learning_rate": 1.328978898250525e-06,
|
| 600 |
+
"logits/chosen": 1.7057956457138062,
|
| 601 |
+
"logits/rejected": 1.726438283920288,
|
| 602 |
+
"logps/chosen": -85.27348327636719,
|
| 603 |
+
"logps/rejected": -96.06895446777344,
|
| 604 |
+
"loss": 0.5553,
|
| 605 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 606 |
+
"rewards/chosen": -0.3689552843570709,
|
| 607 |
+
"rewards/margins": 0.3453688621520996,
|
| 608 |
+
"rewards/rejected": -0.7143241763114929,
|
| 609 |
+
"step": 400
|
| 610 |
+
}
|
| 611 |
+
],
|
| 612 |
+
"logging_steps": 10,
|
| 613 |
+
"max_steps": 580,
|
| 614 |
+
"num_input_tokens_seen": 0,
|
| 615 |
+
"num_train_epochs": 20,
|
| 616 |
+
"save_steps": 50,
|
| 617 |
+
"stateful_callbacks": {
|
| 618 |
+
"TrainerControl": {
|
| 619 |
+
"args": {
|
| 620 |
+
"should_epoch_stop": false,
|
| 621 |
+
"should_evaluate": false,
|
| 622 |
+
"should_log": false,
|
| 623 |
+
"should_save": true,
|
| 624 |
+
"should_training_stop": false
|
| 625 |
+
},
|
| 626 |
+
"attributes": {}
|
| 627 |
+
}
|
| 628 |
+
},
|
| 629 |
+
"total_flos": 1.3741224865384366e+18,
|
| 630 |
+
"train_batch_size": 1,
|
| 631 |
+
"trial_name": null,
|
| 632 |
+
"trial_params": null
|
| 633 |
+
}
|
Power_Area/checkpoint-450/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Power_Area/checkpoint-450/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Power_Area/checkpoint-450/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Power_Area/checkpoint-450/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Power_Area/checkpoint-450/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Power_Area/checkpoint-450/trainer_state.json
ADDED
|
@@ -0,0 +1,708 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 15.210970464135022,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 450,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33755274261603374,
|
| 13 |
+
"grad_norm": 0.4396141469478607,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": 1.6453087329864502,
|
| 16 |
+
"logits/rejected": 1.694819450378418,
|
| 17 |
+
"logps/chosen": -74.5937728881836,
|
| 18 |
+
"logps/rejected": -83.19783782958984,
|
| 19 |
+
"loss": 0.6928,
|
| 20 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 21 |
+
"rewards/chosen": 0.003385844174772501,
|
| 22 |
+
"rewards/margins": 0.004794469103217125,
|
| 23 |
+
"rewards/rejected": -0.0014086246956139803,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6751054852320675,
|
| 28 |
+
"grad_norm": 3.18404483795166,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": 1.7945035696029663,
|
| 31 |
+
"logits/rejected": 1.8347476720809937,
|
| 32 |
+
"logps/chosen": -95.46636199951172,
|
| 33 |
+
"logps/rejected": -101.22709655761719,
|
| 34 |
+
"loss": 0.6933,
|
| 35 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 36 |
+
"rewards/chosen": -0.0005593777750618756,
|
| 37 |
+
"rewards/margins": -0.002013001125305891,
|
| 38 |
+
"rewards/rejected": 0.0014536241069436073,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0126582278481013,
|
| 43 |
+
"grad_norm": 0.48596081137657166,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": 1.774155616760254,
|
| 46 |
+
"logits/rejected": 1.8374344110488892,
|
| 47 |
+
"logps/chosen": -82.01265716552734,
|
| 48 |
+
"logps/rejected": -84.23635864257812,
|
| 49 |
+
"loss": 0.6948,
|
| 50 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 51 |
+
"rewards/chosen": -0.0031326995231211185,
|
| 52 |
+
"rewards/margins": -0.00463916826993227,
|
| 53 |
+
"rewards/rejected": 0.0015064675826579332,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.350210970464135,
|
| 58 |
+
"grad_norm": 0.5144609808921814,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": 1.838865876197815,
|
| 61 |
+
"logits/rejected": 1.9505430459976196,
|
| 62 |
+
"logps/chosen": -73.50071716308594,
|
| 63 |
+
"logps/rejected": -88.8648452758789,
|
| 64 |
+
"loss": 0.6928,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.0035957477521151304,
|
| 67 |
+
"rewards/margins": -0.008830643258988857,
|
| 68 |
+
"rewards/rejected": 0.005234894808381796,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6877637130801688,
|
| 73 |
+
"grad_norm": 0.48295095562934875,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": 1.8197529315948486,
|
| 76 |
+
"logits/rejected": 1.8459796905517578,
|
| 77 |
+
"logps/chosen": -83.36590576171875,
|
| 78 |
+
"logps/rejected": -70.26930236816406,
|
| 79 |
+
"loss": 0.6929,
|
| 80 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 81 |
+
"rewards/chosen": -0.0030026868917047977,
|
| 82 |
+
"rewards/margins": -0.006082554347813129,
|
| 83 |
+
"rewards/rejected": 0.003079867223277688,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.0464135021097047,
|
| 88 |
+
"grad_norm": 0.5616092085838318,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": 1.7525272369384766,
|
| 91 |
+
"logits/rejected": 1.8092533349990845,
|
| 92 |
+
"logps/chosen": -82.01802062988281,
|
| 93 |
+
"logps/rejected": -78.39723205566406,
|
| 94 |
+
"loss": 0.6949,
|
| 95 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 96 |
+
"rewards/chosen": -0.0010920714121311903,
|
| 97 |
+
"rewards/margins": -0.0016235255170613527,
|
| 98 |
+
"rewards/rejected": 0.0005314538720995188,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3839662447257384,
|
| 103 |
+
"grad_norm": 0.5237122774124146,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": 1.754880666732788,
|
| 106 |
+
"logits/rejected": 1.8100305795669556,
|
| 107 |
+
"logps/chosen": -89.62864685058594,
|
| 108 |
+
"logps/rejected": -88.30036926269531,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5,
|
| 111 |
+
"rewards/chosen": -0.002314353361725807,
|
| 112 |
+
"rewards/margins": -0.001038494287058711,
|
| 113 |
+
"rewards/rejected": -0.0012758590746670961,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.721518987341772,
|
| 118 |
+
"grad_norm": 0.507128119468689,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": 1.7501789331436157,
|
| 121 |
+
"logits/rejected": 1.6666221618652344,
|
| 122 |
+
"logps/chosen": -94.74919128417969,
|
| 123 |
+
"logps/rejected": -74.9794692993164,
|
| 124 |
+
"loss": 0.6922,
|
| 125 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 126 |
+
"rewards/chosen": 0.00475720502436161,
|
| 127 |
+
"rewards/margins": 0.01054429542273283,
|
| 128 |
+
"rewards/rejected": -0.005787090864032507,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.059071729957806,
|
| 133 |
+
"grad_norm": 0.8151038885116577,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": 1.7203710079193115,
|
| 136 |
+
"logits/rejected": 1.7376699447631836,
|
| 137 |
+
"logps/chosen": -76.8824691772461,
|
| 138 |
+
"logps/rejected": -84.74555206298828,
|
| 139 |
+
"loss": 0.6925,
|
| 140 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 141 |
+
"rewards/chosen": 0.01064519863575697,
|
| 142 |
+
"rewards/margins": 0.012716365046799183,
|
| 143 |
+
"rewards/rejected": -0.0020711664110422134,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3966244725738397,
|
| 148 |
+
"grad_norm": 0.5476706027984619,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": 1.7857105731964111,
|
| 151 |
+
"logits/rejected": 1.7341340780258179,
|
| 152 |
+
"logps/chosen": -88.39775085449219,
|
| 153 |
+
"logps/rejected": -80.00445556640625,
|
| 154 |
+
"loss": 0.6893,
|
| 155 |
+
"rewards/accuracies": 0.612500011920929,
|
| 156 |
+
"rewards/chosen": 0.0052363635040819645,
|
| 157 |
+
"rewards/margins": 0.016881367191672325,
|
| 158 |
+
"rewards/rejected": -0.011645001359283924,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.7341772151898733,
|
| 163 |
+
"grad_norm": 0.6562405824661255,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": 1.737647294998169,
|
| 166 |
+
"logits/rejected": 1.7781591415405273,
|
| 167 |
+
"logps/chosen": -92.72380065917969,
|
| 168 |
+
"logps/rejected": -85.51634216308594,
|
| 169 |
+
"loss": 0.6899,
|
| 170 |
+
"rewards/accuracies": 0.512499988079071,
|
| 171 |
+
"rewards/chosen": -0.010819707065820694,
|
| 172 |
+
"rewards/margins": -0.0005886269500479102,
|
| 173 |
+
"rewards/rejected": -0.010231079533696175,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.071729957805907,
|
| 178 |
+
"grad_norm": 0.6393210291862488,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": 1.7890704870224,
|
| 181 |
+
"logits/rejected": 1.8340994119644165,
|
| 182 |
+
"logps/chosen": -87.615478515625,
|
| 183 |
+
"logps/rejected": -108.13908386230469,
|
| 184 |
+
"loss": 0.6872,
|
| 185 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 186 |
+
"rewards/chosen": 0.002250433200970292,
|
| 187 |
+
"rewards/margins": 0.012117428705096245,
|
| 188 |
+
"rewards/rejected": -0.009866995736956596,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.409282700421941,
|
| 193 |
+
"grad_norm": 0.7390326261520386,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": 1.7916072607040405,
|
| 196 |
+
"logits/rejected": 1.787153959274292,
|
| 197 |
+
"logps/chosen": -84.11034393310547,
|
| 198 |
+
"logps/rejected": -76.81166076660156,
|
| 199 |
+
"loss": 0.6844,
|
| 200 |
+
"rewards/accuracies": 0.5625,
|
| 201 |
+
"rewards/chosen": -0.003190569579601288,
|
| 202 |
+
"rewards/margins": 0.015628555789589882,
|
| 203 |
+
"rewards/rejected": -0.01881912164390087,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.746835443037975,
|
| 208 |
+
"grad_norm": 0.7888330817222595,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": 1.8455331325531006,
|
| 211 |
+
"logits/rejected": 1.8137515783309937,
|
| 212 |
+
"logps/chosen": -78.94912719726562,
|
| 213 |
+
"logps/rejected": -76.1368637084961,
|
| 214 |
+
"loss": 0.6819,
|
| 215 |
+
"rewards/accuracies": 0.625,
|
| 216 |
+
"rewards/chosen": -0.012986091896891594,
|
| 217 |
+
"rewards/margins": 0.015167826786637306,
|
| 218 |
+
"rewards/rejected": -0.02815392054617405,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.084388185654008,
|
| 223 |
+
"grad_norm": 0.7248090505599976,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": 1.6686553955078125,
|
| 226 |
+
"logits/rejected": 1.6654260158538818,
|
| 227 |
+
"logps/chosen": -78.25769805908203,
|
| 228 |
+
"logps/rejected": -71.3498306274414,
|
| 229 |
+
"loss": 0.677,
|
| 230 |
+
"rewards/accuracies": 0.612500011920929,
|
| 231 |
+
"rewards/chosen": -0.0182911679148674,
|
| 232 |
+
"rewards/margins": 0.02633112668991089,
|
| 233 |
+
"rewards/rejected": -0.04462229460477829,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.421940928270042,
|
| 238 |
+
"grad_norm": 0.7906918525695801,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": 1.8054498434066772,
|
| 241 |
+
"logits/rejected": 1.751422643661499,
|
| 242 |
+
"logps/chosen": -91.65776824951172,
|
| 243 |
+
"logps/rejected": -68.41027069091797,
|
| 244 |
+
"loss": 0.6741,
|
| 245 |
+
"rewards/accuracies": 0.574999988079071,
|
| 246 |
+
"rewards/chosen": -0.04313550516963005,
|
| 247 |
+
"rewards/margins": 0.017568334937095642,
|
| 248 |
+
"rewards/rejected": -0.060703836381435394,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.759493670886076,
|
| 253 |
+
"grad_norm": 0.8152453303337097,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": 1.742419958114624,
|
| 256 |
+
"logits/rejected": 1.9456249475479126,
|
| 257 |
+
"logps/chosen": -80.52605438232422,
|
| 258 |
+
"logps/rejected": -117.02473449707031,
|
| 259 |
+
"loss": 0.67,
|
| 260 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 261 |
+
"rewards/chosen": -0.030041133984923363,
|
| 262 |
+
"rewards/margins": 0.03393586724996567,
|
| 263 |
+
"rewards/rejected": -0.06397700309753418,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.09704641350211,
|
| 268 |
+
"grad_norm": 0.7848192453384399,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": 1.836090087890625,
|
| 271 |
+
"logits/rejected": 2.0285377502441406,
|
| 272 |
+
"logps/chosen": -72.87449645996094,
|
| 273 |
+
"logps/rejected": -101.46552276611328,
|
| 274 |
+
"loss": 0.6659,
|
| 275 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 276 |
+
"rewards/chosen": -0.04543738812208176,
|
| 277 |
+
"rewards/margins": 0.0431094653904438,
|
| 278 |
+
"rewards/rejected": -0.08854684978723526,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.434599156118144,
|
| 283 |
+
"grad_norm": 0.8349910378456116,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": 1.7459189891815186,
|
| 286 |
+
"logits/rejected": 1.8324615955352783,
|
| 287 |
+
"logps/chosen": -72.0348892211914,
|
| 288 |
+
"logps/rejected": -86.13719940185547,
|
| 289 |
+
"loss": 0.6555,
|
| 290 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 291 |
+
"rewards/chosen": -0.04952271655201912,
|
| 292 |
+
"rewards/margins": 0.07018387317657471,
|
| 293 |
+
"rewards/rejected": -0.11970658600330353,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.772151898734177,
|
| 298 |
+
"grad_norm": 0.9766960144042969,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": 1.7785131931304932,
|
| 301 |
+
"logits/rejected": 1.8624244928359985,
|
| 302 |
+
"logps/chosen": -91.82891845703125,
|
| 303 |
+
"logps/rejected": -102.28694915771484,
|
| 304 |
+
"loss": 0.6465,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.04159725084900856,
|
| 307 |
+
"rewards/margins": 0.09511855244636536,
|
| 308 |
+
"rewards/rejected": -0.1367158144712448,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.109704641350211,
|
| 313 |
+
"grad_norm": 0.9714512228965759,
|
| 314 |
+
"learning_rate": 4.024886035802432e-06,
|
| 315 |
+
"logits/chosen": 1.756864309310913,
|
| 316 |
+
"logits/rejected": 1.7497355937957764,
|
| 317 |
+
"logps/chosen": -82.28770446777344,
|
| 318 |
+
"logps/rejected": -72.7796859741211,
|
| 319 |
+
"loss": 0.6498,
|
| 320 |
+
"rewards/accuracies": 0.8125,
|
| 321 |
+
"rewards/chosen": -0.0668434351682663,
|
| 322 |
+
"rewards/margins": 0.1403656005859375,
|
| 323 |
+
"rewards/rejected": -0.2072090357542038,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.447257383966245,
|
| 328 |
+
"grad_norm": 0.9135355949401855,
|
| 329 |
+
"learning_rate": 3.9029676634059565e-06,
|
| 330 |
+
"logits/chosen": 1.677150011062622,
|
| 331 |
+
"logits/rejected": 1.7840830087661743,
|
| 332 |
+
"logps/chosen": -78.84297180175781,
|
| 333 |
+
"logps/rejected": -102.04107666015625,
|
| 334 |
+
"loss": 0.6438,
|
| 335 |
+
"rewards/accuracies": 0.75,
|
| 336 |
+
"rewards/chosen": -0.10343215614557266,
|
| 337 |
+
"rewards/margins": 0.15733790397644043,
|
| 338 |
+
"rewards/rejected": -0.2607700526714325,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.784810126582278,
|
| 343 |
+
"grad_norm": 0.8835084438323975,
|
| 344 |
+
"learning_rate": 3.7759691553595214e-06,
|
| 345 |
+
"logits/chosen": 1.8346344232559204,
|
| 346 |
+
"logits/rejected": 1.838543176651001,
|
| 347 |
+
"logps/chosen": -109.93656921386719,
|
| 348 |
+
"logps/rejected": -73.76078033447266,
|
| 349 |
+
"loss": 0.6279,
|
| 350 |
+
"rewards/accuracies": 0.75,
|
| 351 |
+
"rewards/chosen": -0.08149126917123795,
|
| 352 |
+
"rewards/margins": 0.17928050458431244,
|
| 353 |
+
"rewards/rejected": -0.26077181100845337,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.122362869198312,
|
| 358 |
+
"grad_norm": 0.9854581952095032,
|
| 359 |
+
"learning_rate": 3.6443503723320837e-06,
|
| 360 |
+
"logits/chosen": 1.7367273569107056,
|
| 361 |
+
"logits/rejected": 1.723976492881775,
|
| 362 |
+
"logps/chosen": -80.76436614990234,
|
| 363 |
+
"logps/rejected": -75.7645034790039,
|
| 364 |
+
"loss": 0.6309,
|
| 365 |
+
"rewards/accuracies": 0.762499988079071,
|
| 366 |
+
"rewards/chosen": -0.12716726958751678,
|
| 367 |
+
"rewards/margins": 0.15734827518463135,
|
| 368 |
+
"rewards/rejected": -0.2845155596733093,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 8.459915611814345,
|
| 373 |
+
"grad_norm": 0.9569210410118103,
|
| 374 |
+
"learning_rate": 3.508587904974522e-06,
|
| 375 |
+
"logits/chosen": 1.711611032485962,
|
| 376 |
+
"logits/rejected": 1.820723295211792,
|
| 377 |
+
"logps/chosen": -81.62940979003906,
|
| 378 |
+
"logps/rejected": -104.07059478759766,
|
| 379 |
+
"loss": 0.6206,
|
| 380 |
+
"rewards/accuracies": 0.800000011920929,
|
| 381 |
+
"rewards/chosen": -0.12964895367622375,
|
| 382 |
+
"rewards/margins": 0.2236514836549759,
|
| 383 |
+
"rewards/rejected": -0.35330042243003845,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.79746835443038,
|
| 388 |
+
"grad_norm": 0.9199231863021851,
|
| 389 |
+
"learning_rate": 3.3691733481883693e-06,
|
| 390 |
+
"logits/chosen": 1.860053300857544,
|
| 391 |
+
"logits/rejected": 1.8826453685760498,
|
| 392 |
+
"logps/chosen": -89.85298919677734,
|
| 393 |
+
"logps/rejected": -90.7202377319336,
|
| 394 |
+
"loss": 0.6129,
|
| 395 |
+
"rewards/accuracies": 0.75,
|
| 396 |
+
"rewards/chosen": -0.1632840931415558,
|
| 397 |
+
"rewards/margins": 0.22734332084655762,
|
| 398 |
+
"rewards/rejected": -0.3906274437904358,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.135021097046414,
|
| 403 |
+
"grad_norm": 0.996032178401947,
|
| 404 |
+
"learning_rate": 3.226611521064278e-06,
|
| 405 |
+
"logits/chosen": 1.8121602535247803,
|
| 406 |
+
"logits/rejected": 1.7851508855819702,
|
| 407 |
+
"logps/chosen": -76.85626220703125,
|
| 408 |
+
"logps/rejected": -77.3901138305664,
|
| 409 |
+
"loss": 0.6155,
|
| 410 |
+
"rewards/accuracies": 0.75,
|
| 411 |
+
"rewards/chosen": -0.16423651576042175,
|
| 412 |
+
"rewards/margins": 0.2163097858428955,
|
| 413 |
+
"rewards/rejected": -0.38054633140563965,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 9.472573839662447,
|
| 418 |
+
"grad_norm": 0.96324622631073,
|
| 419 |
+
"learning_rate": 3.0814186389357765e-06,
|
| 420 |
+
"logits/chosen": 1.7609102725982666,
|
| 421 |
+
"logits/rejected": 1.782065749168396,
|
| 422 |
+
"logps/chosen": -78.853271484375,
|
| 423 |
+
"logps/rejected": -81.43799591064453,
|
| 424 |
+
"loss": 0.5991,
|
| 425 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 426 |
+
"rewards/chosen": -0.19906465709209442,
|
| 427 |
+
"rewards/margins": 0.2417418658733368,
|
| 428 |
+
"rewards/rejected": -0.4408065378665924,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 9.810126582278482,
|
| 433 |
+
"grad_norm": 0.9327431917190552,
|
| 434 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 435 |
+
"logits/chosen": 1.7485430240631104,
|
| 436 |
+
"logits/rejected": 1.7885955572128296,
|
| 437 |
+
"logps/chosen": -81.84668731689453,
|
| 438 |
+
"logps/rejected": -84.5110855102539,
|
| 439 |
+
"loss": 0.6035,
|
| 440 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 441 |
+
"rewards/chosen": -0.24916405975818634,
|
| 442 |
+
"rewards/margins": 0.22875118255615234,
|
| 443 |
+
"rewards/rejected": -0.47791528701782227,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.147679324894515,
|
| 448 |
+
"grad_norm": 1.1683701276779175,
|
| 449 |
+
"learning_rate": 2.785250302445062e-06,
|
| 450 |
+
"logits/chosen": 1.8126602172851562,
|
| 451 |
+
"logits/rejected": 1.8814666271209717,
|
| 452 |
+
"logps/chosen": -105.7123031616211,
|
| 453 |
+
"logps/rejected": -92.78335571289062,
|
| 454 |
+
"loss": 0.5916,
|
| 455 |
+
"rewards/accuracies": 0.800000011920929,
|
| 456 |
+
"rewards/chosen": -0.257813036441803,
|
| 457 |
+
"rewards/margins": 0.28732481598854065,
|
| 458 |
+
"rewards/rejected": -0.5451378226280212,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.485232067510548,
|
| 463 |
+
"grad_norm": 1.078698754310608,
|
| 464 |
+
"learning_rate": 2.6353472714635443e-06,
|
| 465 |
+
"logits/chosen": 1.7991764545440674,
|
| 466 |
+
"logits/rejected": 1.8787552118301392,
|
| 467 |
+
"logps/chosen": -70.400634765625,
|
| 468 |
+
"logps/rejected": -72.78517150878906,
|
| 469 |
+
"loss": 0.5893,
|
| 470 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 471 |
+
"rewards/chosen": -0.23745933175086975,
|
| 472 |
+
"rewards/margins": 0.22456249594688416,
|
| 473 |
+
"rewards/rejected": -0.4620218276977539,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 10.822784810126583,
|
| 478 |
+
"grad_norm": 1.0667306184768677,
|
| 479 |
+
"learning_rate": 2.4849541490017868e-06,
|
| 480 |
+
"logits/chosen": 1.7493784427642822,
|
| 481 |
+
"logits/rejected": 1.7776050567626953,
|
| 482 |
+
"logps/chosen": -79.56948852539062,
|
| 483 |
+
"logps/rejected": -95.15191650390625,
|
| 484 |
+
"loss": 0.5943,
|
| 485 |
+
"rewards/accuracies": 0.8125,
|
| 486 |
+
"rewards/chosen": -0.2948698401451111,
|
| 487 |
+
"rewards/margins": 0.27440011501312256,
|
| 488 |
+
"rewards/rejected": -0.5692699551582336,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.160337552742616,
|
| 493 |
+
"grad_norm": 1.1734286546707153,
|
| 494 |
+
"learning_rate": 2.3346155074564712e-06,
|
| 495 |
+
"logits/chosen": 1.7588024139404297,
|
| 496 |
+
"logits/rejected": 1.6906486749649048,
|
| 497 |
+
"logps/chosen": -92.88114929199219,
|
| 498 |
+
"logps/rejected": -87.77473449707031,
|
| 499 |
+
"loss": 0.5748,
|
| 500 |
+
"rewards/accuracies": 0.8125,
|
| 501 |
+
"rewards/chosen": -0.26193878054618835,
|
| 502 |
+
"rewards/margins": 0.31644436717033386,
|
| 503 |
+
"rewards/rejected": -0.5783831477165222,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 11.49789029535865,
|
| 508 |
+
"grad_norm": 1.0506142377853394,
|
| 509 |
+
"learning_rate": 2.184875721949277e-06,
|
| 510 |
+
"logits/chosen": 1.6390129327774048,
|
| 511 |
+
"logits/rejected": 1.6817207336425781,
|
| 512 |
+
"logps/chosen": -85.6020278930664,
|
| 513 |
+
"logps/rejected": -81.51480865478516,
|
| 514 |
+
"loss": 0.5755,
|
| 515 |
+
"rewards/accuracies": 0.824999988079071,
|
| 516 |
+
"rewards/chosen": -0.2864437997341156,
|
| 517 |
+
"rewards/margins": 0.3067106604576111,
|
| 518 |
+
"rewards/rejected": -0.5931544899940491,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 11.835443037974684,
|
| 523 |
+
"grad_norm": 1.0367387533187866,
|
| 524 |
+
"learning_rate": 2.0362769991485514e-06,
|
| 525 |
+
"logits/chosen": 1.811912178993225,
|
| 526 |
+
"logits/rejected": 1.8571999073028564,
|
| 527 |
+
"logps/chosen": -79.2660903930664,
|
| 528 |
+
"logps/rejected": -105.51014709472656,
|
| 529 |
+
"loss": 0.5743,
|
| 530 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 531 |
+
"rewards/chosen": -0.2905730605125427,
|
| 532 |
+
"rewards/margins": 0.37750759720802307,
|
| 533 |
+
"rewards/rejected": -0.6680806279182434,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 12.172995780590718,
|
| 538 |
+
"grad_norm": 1.249039888381958,
|
| 539 |
+
"learning_rate": 1.8893574139429226e-06,
|
| 540 |
+
"logits/chosen": 1.8357423543930054,
|
| 541 |
+
"logits/rejected": 1.8285624980926514,
|
| 542 |
+
"logps/chosen": -85.5277099609375,
|
| 543 |
+
"logps/rejected": -90.13473510742188,
|
| 544 |
+
"loss": 0.575,
|
| 545 |
+
"rewards/accuracies": 0.762499988079071,
|
| 546 |
+
"rewards/chosen": -0.36660733819007874,
|
| 547 |
+
"rewards/margins": 0.3461737632751465,
|
| 548 |
+
"rewards/rejected": -0.7127811312675476,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 12.51054852320675,
|
| 553 |
+
"grad_norm": 1.1541879177093506,
|
| 554 |
+
"learning_rate": 1.744648961076068e-06,
|
| 555 |
+
"logits/chosen": 1.790567398071289,
|
| 556 |
+
"logits/rejected": 1.7228246927261353,
|
| 557 |
+
"logps/chosen": -86.40596008300781,
|
| 558 |
+
"logps/rejected": -75.5702896118164,
|
| 559 |
+
"loss": 0.5693,
|
| 560 |
+
"rewards/accuracies": 0.762499988079071,
|
| 561 |
+
"rewards/chosen": -0.34050875902175903,
|
| 562 |
+
"rewards/margins": 0.2642201781272888,
|
| 563 |
+
"rewards/rejected": -0.6047288775444031,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 12.848101265822784,
|
| 568 |
+
"grad_norm": 1.0363268852233887,
|
| 569 |
+
"learning_rate": 1.602675628797636e-06,
|
| 570 |
+
"logits/chosen": 1.6812736988067627,
|
| 571 |
+
"logits/rejected": 1.7188876867294312,
|
| 572 |
+
"logps/chosen": -81.14212799072266,
|
| 573 |
+
"logps/rejected": -82.90364074707031,
|
| 574 |
+
"loss": 0.5594,
|
| 575 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 576 |
+
"rewards/chosen": -0.3105277419090271,
|
| 577 |
+
"rewards/margins": 0.3372951149940491,
|
| 578 |
+
"rewards/rejected": -0.6478228569030762,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 13.185654008438819,
|
| 583 |
+
"grad_norm": 1.047418475151062,
|
| 584 |
+
"learning_rate": 1.4639515015056205e-06,
|
| 585 |
+
"logits/chosen": 1.6939361095428467,
|
| 586 |
+
"logits/rejected": 1.7271579504013062,
|
| 587 |
+
"logps/chosen": -86.88213348388672,
|
| 588 |
+
"logps/rejected": -99.46037292480469,
|
| 589 |
+
"loss": 0.558,
|
| 590 |
+
"rewards/accuracies": 0.762499988079071,
|
| 591 |
+
"rewards/chosen": -0.2660979926586151,
|
| 592 |
+
"rewards/margins": 0.4496893882751465,
|
| 593 |
+
"rewards/rejected": -0.7157873511314392,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 13.523206751054852,
|
| 598 |
+
"grad_norm": 1.1949480772018433,
|
| 599 |
+
"learning_rate": 1.328978898250525e-06,
|
| 600 |
+
"logits/chosen": 1.7057956457138062,
|
| 601 |
+
"logits/rejected": 1.726438283920288,
|
| 602 |
+
"logps/chosen": -85.27348327636719,
|
| 603 |
+
"logps/rejected": -96.06895446777344,
|
| 604 |
+
"loss": 0.5553,
|
| 605 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 606 |
+
"rewards/chosen": -0.3689552843570709,
|
| 607 |
+
"rewards/margins": 0.3453688621520996,
|
| 608 |
+
"rewards/rejected": -0.7143241763114929,
|
| 609 |
+
"step": 400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 13.860759493670885,
|
| 613 |
+
"grad_norm": 1.5321677923202515,
|
| 614 |
+
"learning_rate": 1.198246553841744e-06,
|
| 615 |
+
"logits/chosen": 1.8362537622451782,
|
| 616 |
+
"logits/rejected": 1.889491081237793,
|
| 617 |
+
"logps/chosen": -78.84573364257812,
|
| 618 |
+
"logps/rejected": -75.66096496582031,
|
| 619 |
+
"loss": 0.5618,
|
| 620 |
+
"rewards/accuracies": 0.762499988079071,
|
| 621 |
+
"rewards/chosen": -0.34546419978141785,
|
| 622 |
+
"rewards/margins": 0.3866986334323883,
|
| 623 |
+
"rewards/rejected": -0.7321628332138062,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 14.19831223628692,
|
| 628 |
+
"grad_norm": 1.1697853803634644,
|
| 629 |
+
"learning_rate": 1.0722278491423998e-06,
|
| 630 |
+
"logits/chosen": 1.7950217723846436,
|
| 631 |
+
"logits/rejected": 1.8145115375518799,
|
| 632 |
+
"logps/chosen": -82.2846908569336,
|
| 633 |
+
"logps/rejected": -91.40074157714844,
|
| 634 |
+
"loss": 0.5516,
|
| 635 |
+
"rewards/accuracies": 0.800000011920929,
|
| 636 |
+
"rewards/chosen": -0.37175649404525757,
|
| 637 |
+
"rewards/margins": 0.404013067483902,
|
| 638 |
+
"rewards/rejected": -0.7757695913314819,
|
| 639 |
+
"step": 420
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 14.535864978902953,
|
| 643 |
+
"grad_norm": 1.163073182106018,
|
| 644 |
+
"learning_rate": 9.513790969606926e-07,
|
| 645 |
+
"logits/chosen": 1.686415433883667,
|
| 646 |
+
"logits/rejected": 1.7637500762939453,
|
| 647 |
+
"logps/chosen": -100.37837219238281,
|
| 648 |
+
"logps/rejected": -100.43409729003906,
|
| 649 |
+
"loss": 0.5583,
|
| 650 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 651 |
+
"rewards/chosen": -0.35831838846206665,
|
| 652 |
+
"rewards/margins": 0.3624442219734192,
|
| 653 |
+
"rewards/rejected": -0.7207626104354858,
|
| 654 |
+
"step": 430
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 14.873417721518987,
|
| 658 |
+
"grad_norm": 1.148380160331726,
|
| 659 |
+
"learning_rate": 8.361378897445643e-07,
|
| 660 |
+
"logits/chosen": 1.6370818614959717,
|
| 661 |
+
"logits/rejected": 1.752598524093628,
|
| 662 |
+
"logps/chosen": -84.63670349121094,
|
| 663 |
+
"logps/rejected": -89.8626708984375,
|
| 664 |
+
"loss": 0.5584,
|
| 665 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 666 |
+
"rewards/chosen": -0.44350141286849976,
|
| 667 |
+
"rewards/margins": 0.4355877935886383,
|
| 668 |
+
"rewards/rejected": -0.8790891766548157,
|
| 669 |
+
"step": 440
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 15.210970464135022,
|
| 673 |
+
"grad_norm": 1.1012156009674072,
|
| 674 |
+
"learning_rate": 7.269215150626391e-07,
|
| 675 |
+
"logits/chosen": 1.8232038021087646,
|
| 676 |
+
"logits/rejected": 1.8113384246826172,
|
| 677 |
+
"logps/chosen": -95.2444839477539,
|
| 678 |
+
"logps/rejected": -85.72362518310547,
|
| 679 |
+
"loss": 0.5539,
|
| 680 |
+
"rewards/accuracies": 0.875,
|
| 681 |
+
"rewards/chosen": -0.3705037236213684,
|
| 682 |
+
"rewards/margins": 0.5386990308761597,
|
| 683 |
+
"rewards/rejected": -0.9092028737068176,
|
| 684 |
+
"step": 450
|
| 685 |
+
}
|
| 686 |
+
],
|
| 687 |
+
"logging_steps": 10,
|
| 688 |
+
"max_steps": 580,
|
| 689 |
+
"num_input_tokens_seen": 0,
|
| 690 |
+
"num_train_epochs": 20,
|
| 691 |
+
"save_steps": 50,
|
| 692 |
+
"stateful_callbacks": {
|
| 693 |
+
"TrainerControl": {
|
| 694 |
+
"args": {
|
| 695 |
+
"should_epoch_stop": false,
|
| 696 |
+
"should_evaluate": false,
|
| 697 |
+
"should_log": false,
|
| 698 |
+
"should_save": true,
|
| 699 |
+
"should_training_stop": false
|
| 700 |
+
},
|
| 701 |
+
"attributes": {}
|
| 702 |
+
}
|
| 703 |
+
},
|
| 704 |
+
"total_flos": 1.5466014367736136e+18,
|
| 705 |
+
"train_batch_size": 1,
|
| 706 |
+
"trial_name": null,
|
| 707 |
+
"trial_params": null
|
| 708 |
+
}
|
Power_Area/checkpoint-500/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Power_Area/checkpoint-500/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Power_Area/checkpoint-500/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Power_Area/checkpoint-500/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Power_Area/checkpoint-500/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Power_Area/checkpoint-500/trainer_state.json
ADDED
|
@@ -0,0 +1,783 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 16.89873417721519,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33755274261603374,
|
| 13 |
+
"grad_norm": 0.4396141469478607,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": 1.6453087329864502,
|
| 16 |
+
"logits/rejected": 1.694819450378418,
|
| 17 |
+
"logps/chosen": -74.5937728881836,
|
| 18 |
+
"logps/rejected": -83.19783782958984,
|
| 19 |
+
"loss": 0.6928,
|
| 20 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 21 |
+
"rewards/chosen": 0.003385844174772501,
|
| 22 |
+
"rewards/margins": 0.004794469103217125,
|
| 23 |
+
"rewards/rejected": -0.0014086246956139803,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6751054852320675,
|
| 28 |
+
"grad_norm": 3.18404483795166,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": 1.7945035696029663,
|
| 31 |
+
"logits/rejected": 1.8347476720809937,
|
| 32 |
+
"logps/chosen": -95.46636199951172,
|
| 33 |
+
"logps/rejected": -101.22709655761719,
|
| 34 |
+
"loss": 0.6933,
|
| 35 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 36 |
+
"rewards/chosen": -0.0005593777750618756,
|
| 37 |
+
"rewards/margins": -0.002013001125305891,
|
| 38 |
+
"rewards/rejected": 0.0014536241069436073,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0126582278481013,
|
| 43 |
+
"grad_norm": 0.48596081137657166,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": 1.774155616760254,
|
| 46 |
+
"logits/rejected": 1.8374344110488892,
|
| 47 |
+
"logps/chosen": -82.01265716552734,
|
| 48 |
+
"logps/rejected": -84.23635864257812,
|
| 49 |
+
"loss": 0.6948,
|
| 50 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 51 |
+
"rewards/chosen": -0.0031326995231211185,
|
| 52 |
+
"rewards/margins": -0.00463916826993227,
|
| 53 |
+
"rewards/rejected": 0.0015064675826579332,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.350210970464135,
|
| 58 |
+
"grad_norm": 0.5144609808921814,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": 1.838865876197815,
|
| 61 |
+
"logits/rejected": 1.9505430459976196,
|
| 62 |
+
"logps/chosen": -73.50071716308594,
|
| 63 |
+
"logps/rejected": -88.8648452758789,
|
| 64 |
+
"loss": 0.6928,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.0035957477521151304,
|
| 67 |
+
"rewards/margins": -0.008830643258988857,
|
| 68 |
+
"rewards/rejected": 0.005234894808381796,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6877637130801688,
|
| 73 |
+
"grad_norm": 0.48295095562934875,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": 1.8197529315948486,
|
| 76 |
+
"logits/rejected": 1.8459796905517578,
|
| 77 |
+
"logps/chosen": -83.36590576171875,
|
| 78 |
+
"logps/rejected": -70.26930236816406,
|
| 79 |
+
"loss": 0.6929,
|
| 80 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 81 |
+
"rewards/chosen": -0.0030026868917047977,
|
| 82 |
+
"rewards/margins": -0.006082554347813129,
|
| 83 |
+
"rewards/rejected": 0.003079867223277688,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.0464135021097047,
|
| 88 |
+
"grad_norm": 0.5616092085838318,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": 1.7525272369384766,
|
| 91 |
+
"logits/rejected": 1.8092533349990845,
|
| 92 |
+
"logps/chosen": -82.01802062988281,
|
| 93 |
+
"logps/rejected": -78.39723205566406,
|
| 94 |
+
"loss": 0.6949,
|
| 95 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 96 |
+
"rewards/chosen": -0.0010920714121311903,
|
| 97 |
+
"rewards/margins": -0.0016235255170613527,
|
| 98 |
+
"rewards/rejected": 0.0005314538720995188,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3839662447257384,
|
| 103 |
+
"grad_norm": 0.5237122774124146,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": 1.754880666732788,
|
| 106 |
+
"logits/rejected": 1.8100305795669556,
|
| 107 |
+
"logps/chosen": -89.62864685058594,
|
| 108 |
+
"logps/rejected": -88.30036926269531,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5,
|
| 111 |
+
"rewards/chosen": -0.002314353361725807,
|
| 112 |
+
"rewards/margins": -0.001038494287058711,
|
| 113 |
+
"rewards/rejected": -0.0012758590746670961,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.721518987341772,
|
| 118 |
+
"grad_norm": 0.507128119468689,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": 1.7501789331436157,
|
| 121 |
+
"logits/rejected": 1.6666221618652344,
|
| 122 |
+
"logps/chosen": -94.74919128417969,
|
| 123 |
+
"logps/rejected": -74.9794692993164,
|
| 124 |
+
"loss": 0.6922,
|
| 125 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 126 |
+
"rewards/chosen": 0.00475720502436161,
|
| 127 |
+
"rewards/margins": 0.01054429542273283,
|
| 128 |
+
"rewards/rejected": -0.005787090864032507,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.059071729957806,
|
| 133 |
+
"grad_norm": 0.8151038885116577,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": 1.7203710079193115,
|
| 136 |
+
"logits/rejected": 1.7376699447631836,
|
| 137 |
+
"logps/chosen": -76.8824691772461,
|
| 138 |
+
"logps/rejected": -84.74555206298828,
|
| 139 |
+
"loss": 0.6925,
|
| 140 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 141 |
+
"rewards/chosen": 0.01064519863575697,
|
| 142 |
+
"rewards/margins": 0.012716365046799183,
|
| 143 |
+
"rewards/rejected": -0.0020711664110422134,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3966244725738397,
|
| 148 |
+
"grad_norm": 0.5476706027984619,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": 1.7857105731964111,
|
| 151 |
+
"logits/rejected": 1.7341340780258179,
|
| 152 |
+
"logps/chosen": -88.39775085449219,
|
| 153 |
+
"logps/rejected": -80.00445556640625,
|
| 154 |
+
"loss": 0.6893,
|
| 155 |
+
"rewards/accuracies": 0.612500011920929,
|
| 156 |
+
"rewards/chosen": 0.0052363635040819645,
|
| 157 |
+
"rewards/margins": 0.016881367191672325,
|
| 158 |
+
"rewards/rejected": -0.011645001359283924,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.7341772151898733,
|
| 163 |
+
"grad_norm": 0.6562405824661255,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": 1.737647294998169,
|
| 166 |
+
"logits/rejected": 1.7781591415405273,
|
| 167 |
+
"logps/chosen": -92.72380065917969,
|
| 168 |
+
"logps/rejected": -85.51634216308594,
|
| 169 |
+
"loss": 0.6899,
|
| 170 |
+
"rewards/accuracies": 0.512499988079071,
|
| 171 |
+
"rewards/chosen": -0.010819707065820694,
|
| 172 |
+
"rewards/margins": -0.0005886269500479102,
|
| 173 |
+
"rewards/rejected": -0.010231079533696175,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.071729957805907,
|
| 178 |
+
"grad_norm": 0.6393210291862488,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": 1.7890704870224,
|
| 181 |
+
"logits/rejected": 1.8340994119644165,
|
| 182 |
+
"logps/chosen": -87.615478515625,
|
| 183 |
+
"logps/rejected": -108.13908386230469,
|
| 184 |
+
"loss": 0.6872,
|
| 185 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 186 |
+
"rewards/chosen": 0.002250433200970292,
|
| 187 |
+
"rewards/margins": 0.012117428705096245,
|
| 188 |
+
"rewards/rejected": -0.009866995736956596,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.409282700421941,
|
| 193 |
+
"grad_norm": 0.7390326261520386,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": 1.7916072607040405,
|
| 196 |
+
"logits/rejected": 1.787153959274292,
|
| 197 |
+
"logps/chosen": -84.11034393310547,
|
| 198 |
+
"logps/rejected": -76.81166076660156,
|
| 199 |
+
"loss": 0.6844,
|
| 200 |
+
"rewards/accuracies": 0.5625,
|
| 201 |
+
"rewards/chosen": -0.003190569579601288,
|
| 202 |
+
"rewards/margins": 0.015628555789589882,
|
| 203 |
+
"rewards/rejected": -0.01881912164390087,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.746835443037975,
|
| 208 |
+
"grad_norm": 0.7888330817222595,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": 1.8455331325531006,
|
| 211 |
+
"logits/rejected": 1.8137515783309937,
|
| 212 |
+
"logps/chosen": -78.94912719726562,
|
| 213 |
+
"logps/rejected": -76.1368637084961,
|
| 214 |
+
"loss": 0.6819,
|
| 215 |
+
"rewards/accuracies": 0.625,
|
| 216 |
+
"rewards/chosen": -0.012986091896891594,
|
| 217 |
+
"rewards/margins": 0.015167826786637306,
|
| 218 |
+
"rewards/rejected": -0.02815392054617405,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.084388185654008,
|
| 223 |
+
"grad_norm": 0.7248090505599976,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": 1.6686553955078125,
|
| 226 |
+
"logits/rejected": 1.6654260158538818,
|
| 227 |
+
"logps/chosen": -78.25769805908203,
|
| 228 |
+
"logps/rejected": -71.3498306274414,
|
| 229 |
+
"loss": 0.677,
|
| 230 |
+
"rewards/accuracies": 0.612500011920929,
|
| 231 |
+
"rewards/chosen": -0.0182911679148674,
|
| 232 |
+
"rewards/margins": 0.02633112668991089,
|
| 233 |
+
"rewards/rejected": -0.04462229460477829,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.421940928270042,
|
| 238 |
+
"grad_norm": 0.7906918525695801,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": 1.8054498434066772,
|
| 241 |
+
"logits/rejected": 1.751422643661499,
|
| 242 |
+
"logps/chosen": -91.65776824951172,
|
| 243 |
+
"logps/rejected": -68.41027069091797,
|
| 244 |
+
"loss": 0.6741,
|
| 245 |
+
"rewards/accuracies": 0.574999988079071,
|
| 246 |
+
"rewards/chosen": -0.04313550516963005,
|
| 247 |
+
"rewards/margins": 0.017568334937095642,
|
| 248 |
+
"rewards/rejected": -0.060703836381435394,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.759493670886076,
|
| 253 |
+
"grad_norm": 0.8152453303337097,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": 1.742419958114624,
|
| 256 |
+
"logits/rejected": 1.9456249475479126,
|
| 257 |
+
"logps/chosen": -80.52605438232422,
|
| 258 |
+
"logps/rejected": -117.02473449707031,
|
| 259 |
+
"loss": 0.67,
|
| 260 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 261 |
+
"rewards/chosen": -0.030041133984923363,
|
| 262 |
+
"rewards/margins": 0.03393586724996567,
|
| 263 |
+
"rewards/rejected": -0.06397700309753418,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.09704641350211,
|
| 268 |
+
"grad_norm": 0.7848192453384399,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": 1.836090087890625,
|
| 271 |
+
"logits/rejected": 2.0285377502441406,
|
| 272 |
+
"logps/chosen": -72.87449645996094,
|
| 273 |
+
"logps/rejected": -101.46552276611328,
|
| 274 |
+
"loss": 0.6659,
|
| 275 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 276 |
+
"rewards/chosen": -0.04543738812208176,
|
| 277 |
+
"rewards/margins": 0.0431094653904438,
|
| 278 |
+
"rewards/rejected": -0.08854684978723526,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.434599156118144,
|
| 283 |
+
"grad_norm": 0.8349910378456116,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": 1.7459189891815186,
|
| 286 |
+
"logits/rejected": 1.8324615955352783,
|
| 287 |
+
"logps/chosen": -72.0348892211914,
|
| 288 |
+
"logps/rejected": -86.13719940185547,
|
| 289 |
+
"loss": 0.6555,
|
| 290 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 291 |
+
"rewards/chosen": -0.04952271655201912,
|
| 292 |
+
"rewards/margins": 0.07018387317657471,
|
| 293 |
+
"rewards/rejected": -0.11970658600330353,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.772151898734177,
|
| 298 |
+
"grad_norm": 0.9766960144042969,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": 1.7785131931304932,
|
| 301 |
+
"logits/rejected": 1.8624244928359985,
|
| 302 |
+
"logps/chosen": -91.82891845703125,
|
| 303 |
+
"logps/rejected": -102.28694915771484,
|
| 304 |
+
"loss": 0.6465,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.04159725084900856,
|
| 307 |
+
"rewards/margins": 0.09511855244636536,
|
| 308 |
+
"rewards/rejected": -0.1367158144712448,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.109704641350211,
|
| 313 |
+
"grad_norm": 0.9714512228965759,
|
| 314 |
+
"learning_rate": 4.024886035802432e-06,
|
| 315 |
+
"logits/chosen": 1.756864309310913,
|
| 316 |
+
"logits/rejected": 1.7497355937957764,
|
| 317 |
+
"logps/chosen": -82.28770446777344,
|
| 318 |
+
"logps/rejected": -72.7796859741211,
|
| 319 |
+
"loss": 0.6498,
|
| 320 |
+
"rewards/accuracies": 0.8125,
|
| 321 |
+
"rewards/chosen": -0.0668434351682663,
|
| 322 |
+
"rewards/margins": 0.1403656005859375,
|
| 323 |
+
"rewards/rejected": -0.2072090357542038,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.447257383966245,
|
| 328 |
+
"grad_norm": 0.9135355949401855,
|
| 329 |
+
"learning_rate": 3.9029676634059565e-06,
|
| 330 |
+
"logits/chosen": 1.677150011062622,
|
| 331 |
+
"logits/rejected": 1.7840830087661743,
|
| 332 |
+
"logps/chosen": -78.84297180175781,
|
| 333 |
+
"logps/rejected": -102.04107666015625,
|
| 334 |
+
"loss": 0.6438,
|
| 335 |
+
"rewards/accuracies": 0.75,
|
| 336 |
+
"rewards/chosen": -0.10343215614557266,
|
| 337 |
+
"rewards/margins": 0.15733790397644043,
|
| 338 |
+
"rewards/rejected": -0.2607700526714325,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.784810126582278,
|
| 343 |
+
"grad_norm": 0.8835084438323975,
|
| 344 |
+
"learning_rate": 3.7759691553595214e-06,
|
| 345 |
+
"logits/chosen": 1.8346344232559204,
|
| 346 |
+
"logits/rejected": 1.838543176651001,
|
| 347 |
+
"logps/chosen": -109.93656921386719,
|
| 348 |
+
"logps/rejected": -73.76078033447266,
|
| 349 |
+
"loss": 0.6279,
|
| 350 |
+
"rewards/accuracies": 0.75,
|
| 351 |
+
"rewards/chosen": -0.08149126917123795,
|
| 352 |
+
"rewards/margins": 0.17928050458431244,
|
| 353 |
+
"rewards/rejected": -0.26077181100845337,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.122362869198312,
|
| 358 |
+
"grad_norm": 0.9854581952095032,
|
| 359 |
+
"learning_rate": 3.6443503723320837e-06,
|
| 360 |
+
"logits/chosen": 1.7367273569107056,
|
| 361 |
+
"logits/rejected": 1.723976492881775,
|
| 362 |
+
"logps/chosen": -80.76436614990234,
|
| 363 |
+
"logps/rejected": -75.7645034790039,
|
| 364 |
+
"loss": 0.6309,
|
| 365 |
+
"rewards/accuracies": 0.762499988079071,
|
| 366 |
+
"rewards/chosen": -0.12716726958751678,
|
| 367 |
+
"rewards/margins": 0.15734827518463135,
|
| 368 |
+
"rewards/rejected": -0.2845155596733093,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 8.459915611814345,
|
| 373 |
+
"grad_norm": 0.9569210410118103,
|
| 374 |
+
"learning_rate": 3.508587904974522e-06,
|
| 375 |
+
"logits/chosen": 1.711611032485962,
|
| 376 |
+
"logits/rejected": 1.820723295211792,
|
| 377 |
+
"logps/chosen": -81.62940979003906,
|
| 378 |
+
"logps/rejected": -104.07059478759766,
|
| 379 |
+
"loss": 0.6206,
|
| 380 |
+
"rewards/accuracies": 0.800000011920929,
|
| 381 |
+
"rewards/chosen": -0.12964895367622375,
|
| 382 |
+
"rewards/margins": 0.2236514836549759,
|
| 383 |
+
"rewards/rejected": -0.35330042243003845,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.79746835443038,
|
| 388 |
+
"grad_norm": 0.9199231863021851,
|
| 389 |
+
"learning_rate": 3.3691733481883693e-06,
|
| 390 |
+
"logits/chosen": 1.860053300857544,
|
| 391 |
+
"logits/rejected": 1.8826453685760498,
|
| 392 |
+
"logps/chosen": -89.85298919677734,
|
| 393 |
+
"logps/rejected": -90.7202377319336,
|
| 394 |
+
"loss": 0.6129,
|
| 395 |
+
"rewards/accuracies": 0.75,
|
| 396 |
+
"rewards/chosen": -0.1632840931415558,
|
| 397 |
+
"rewards/margins": 0.22734332084655762,
|
| 398 |
+
"rewards/rejected": -0.3906274437904358,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.135021097046414,
|
| 403 |
+
"grad_norm": 0.996032178401947,
|
| 404 |
+
"learning_rate": 3.226611521064278e-06,
|
| 405 |
+
"logits/chosen": 1.8121602535247803,
|
| 406 |
+
"logits/rejected": 1.7851508855819702,
|
| 407 |
+
"logps/chosen": -76.85626220703125,
|
| 408 |
+
"logps/rejected": -77.3901138305664,
|
| 409 |
+
"loss": 0.6155,
|
| 410 |
+
"rewards/accuracies": 0.75,
|
| 411 |
+
"rewards/chosen": -0.16423651576042175,
|
| 412 |
+
"rewards/margins": 0.2163097858428955,
|
| 413 |
+
"rewards/rejected": -0.38054633140563965,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 9.472573839662447,
|
| 418 |
+
"grad_norm": 0.96324622631073,
|
| 419 |
+
"learning_rate": 3.0814186389357765e-06,
|
| 420 |
+
"logits/chosen": 1.7609102725982666,
|
| 421 |
+
"logits/rejected": 1.782065749168396,
|
| 422 |
+
"logps/chosen": -78.853271484375,
|
| 423 |
+
"logps/rejected": -81.43799591064453,
|
| 424 |
+
"loss": 0.5991,
|
| 425 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 426 |
+
"rewards/chosen": -0.19906465709209442,
|
| 427 |
+
"rewards/margins": 0.2417418658733368,
|
| 428 |
+
"rewards/rejected": -0.4408065378665924,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 9.810126582278482,
|
| 433 |
+
"grad_norm": 0.9327431917190552,
|
| 434 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 435 |
+
"logits/chosen": 1.7485430240631104,
|
| 436 |
+
"logits/rejected": 1.7885955572128296,
|
| 437 |
+
"logps/chosen": -81.84668731689453,
|
| 438 |
+
"logps/rejected": -84.5110855102539,
|
| 439 |
+
"loss": 0.6035,
|
| 440 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 441 |
+
"rewards/chosen": -0.24916405975818634,
|
| 442 |
+
"rewards/margins": 0.22875118255615234,
|
| 443 |
+
"rewards/rejected": -0.47791528701782227,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.147679324894515,
|
| 448 |
+
"grad_norm": 1.1683701276779175,
|
| 449 |
+
"learning_rate": 2.785250302445062e-06,
|
| 450 |
+
"logits/chosen": 1.8126602172851562,
|
| 451 |
+
"logits/rejected": 1.8814666271209717,
|
| 452 |
+
"logps/chosen": -105.7123031616211,
|
| 453 |
+
"logps/rejected": -92.78335571289062,
|
| 454 |
+
"loss": 0.5916,
|
| 455 |
+
"rewards/accuracies": 0.800000011920929,
|
| 456 |
+
"rewards/chosen": -0.257813036441803,
|
| 457 |
+
"rewards/margins": 0.28732481598854065,
|
| 458 |
+
"rewards/rejected": -0.5451378226280212,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.485232067510548,
|
| 463 |
+
"grad_norm": 1.078698754310608,
|
| 464 |
+
"learning_rate": 2.6353472714635443e-06,
|
| 465 |
+
"logits/chosen": 1.7991764545440674,
|
| 466 |
+
"logits/rejected": 1.8787552118301392,
|
| 467 |
+
"logps/chosen": -70.400634765625,
|
| 468 |
+
"logps/rejected": -72.78517150878906,
|
| 469 |
+
"loss": 0.5893,
|
| 470 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 471 |
+
"rewards/chosen": -0.23745933175086975,
|
| 472 |
+
"rewards/margins": 0.22456249594688416,
|
| 473 |
+
"rewards/rejected": -0.4620218276977539,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 10.822784810126583,
|
| 478 |
+
"grad_norm": 1.0667306184768677,
|
| 479 |
+
"learning_rate": 2.4849541490017868e-06,
|
| 480 |
+
"logits/chosen": 1.7493784427642822,
|
| 481 |
+
"logits/rejected": 1.7776050567626953,
|
| 482 |
+
"logps/chosen": -79.56948852539062,
|
| 483 |
+
"logps/rejected": -95.15191650390625,
|
| 484 |
+
"loss": 0.5943,
|
| 485 |
+
"rewards/accuracies": 0.8125,
|
| 486 |
+
"rewards/chosen": -0.2948698401451111,
|
| 487 |
+
"rewards/margins": 0.27440011501312256,
|
| 488 |
+
"rewards/rejected": -0.5692699551582336,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.160337552742616,
|
| 493 |
+
"grad_norm": 1.1734286546707153,
|
| 494 |
+
"learning_rate": 2.3346155074564712e-06,
|
| 495 |
+
"logits/chosen": 1.7588024139404297,
|
| 496 |
+
"logits/rejected": 1.6906486749649048,
|
| 497 |
+
"logps/chosen": -92.88114929199219,
|
| 498 |
+
"logps/rejected": -87.77473449707031,
|
| 499 |
+
"loss": 0.5748,
|
| 500 |
+
"rewards/accuracies": 0.8125,
|
| 501 |
+
"rewards/chosen": -0.26193878054618835,
|
| 502 |
+
"rewards/margins": 0.31644436717033386,
|
| 503 |
+
"rewards/rejected": -0.5783831477165222,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 11.49789029535865,
|
| 508 |
+
"grad_norm": 1.0506142377853394,
|
| 509 |
+
"learning_rate": 2.184875721949277e-06,
|
| 510 |
+
"logits/chosen": 1.6390129327774048,
|
| 511 |
+
"logits/rejected": 1.6817207336425781,
|
| 512 |
+
"logps/chosen": -85.6020278930664,
|
| 513 |
+
"logps/rejected": -81.51480865478516,
|
| 514 |
+
"loss": 0.5755,
|
| 515 |
+
"rewards/accuracies": 0.824999988079071,
|
| 516 |
+
"rewards/chosen": -0.2864437997341156,
|
| 517 |
+
"rewards/margins": 0.3067106604576111,
|
| 518 |
+
"rewards/rejected": -0.5931544899940491,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 11.835443037974684,
|
| 523 |
+
"grad_norm": 1.0367387533187866,
|
| 524 |
+
"learning_rate": 2.0362769991485514e-06,
|
| 525 |
+
"logits/chosen": 1.811912178993225,
|
| 526 |
+
"logits/rejected": 1.8571999073028564,
|
| 527 |
+
"logps/chosen": -79.2660903930664,
|
| 528 |
+
"logps/rejected": -105.51014709472656,
|
| 529 |
+
"loss": 0.5743,
|
| 530 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 531 |
+
"rewards/chosen": -0.2905730605125427,
|
| 532 |
+
"rewards/margins": 0.37750759720802307,
|
| 533 |
+
"rewards/rejected": -0.6680806279182434,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 12.172995780590718,
|
| 538 |
+
"grad_norm": 1.249039888381958,
|
| 539 |
+
"learning_rate": 1.8893574139429226e-06,
|
| 540 |
+
"logits/chosen": 1.8357423543930054,
|
| 541 |
+
"logits/rejected": 1.8285624980926514,
|
| 542 |
+
"logps/chosen": -85.5277099609375,
|
| 543 |
+
"logps/rejected": -90.13473510742188,
|
| 544 |
+
"loss": 0.575,
|
| 545 |
+
"rewards/accuracies": 0.762499988079071,
|
| 546 |
+
"rewards/chosen": -0.36660733819007874,
|
| 547 |
+
"rewards/margins": 0.3461737632751465,
|
| 548 |
+
"rewards/rejected": -0.7127811312675476,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 12.51054852320675,
|
| 553 |
+
"grad_norm": 1.1541879177093506,
|
| 554 |
+
"learning_rate": 1.744648961076068e-06,
|
| 555 |
+
"logits/chosen": 1.790567398071289,
|
| 556 |
+
"logits/rejected": 1.7228246927261353,
|
| 557 |
+
"logps/chosen": -86.40596008300781,
|
| 558 |
+
"logps/rejected": -75.5702896118164,
|
| 559 |
+
"loss": 0.5693,
|
| 560 |
+
"rewards/accuracies": 0.762499988079071,
|
| 561 |
+
"rewards/chosen": -0.34050875902175903,
|
| 562 |
+
"rewards/margins": 0.2642201781272888,
|
| 563 |
+
"rewards/rejected": -0.6047288775444031,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 12.848101265822784,
|
| 568 |
+
"grad_norm": 1.0363268852233887,
|
| 569 |
+
"learning_rate": 1.602675628797636e-06,
|
| 570 |
+
"logits/chosen": 1.6812736988067627,
|
| 571 |
+
"logits/rejected": 1.7188876867294312,
|
| 572 |
+
"logps/chosen": -81.14212799072266,
|
| 573 |
+
"logps/rejected": -82.90364074707031,
|
| 574 |
+
"loss": 0.5594,
|
| 575 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 576 |
+
"rewards/chosen": -0.3105277419090271,
|
| 577 |
+
"rewards/margins": 0.3372951149940491,
|
| 578 |
+
"rewards/rejected": -0.6478228569030762,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 13.185654008438819,
|
| 583 |
+
"grad_norm": 1.047418475151062,
|
| 584 |
+
"learning_rate": 1.4639515015056205e-06,
|
| 585 |
+
"logits/chosen": 1.6939361095428467,
|
| 586 |
+
"logits/rejected": 1.7271579504013062,
|
| 587 |
+
"logps/chosen": -86.88213348388672,
|
| 588 |
+
"logps/rejected": -99.46037292480469,
|
| 589 |
+
"loss": 0.558,
|
| 590 |
+
"rewards/accuracies": 0.762499988079071,
|
| 591 |
+
"rewards/chosen": -0.2660979926586151,
|
| 592 |
+
"rewards/margins": 0.4496893882751465,
|
| 593 |
+
"rewards/rejected": -0.7157873511314392,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 13.523206751054852,
|
| 598 |
+
"grad_norm": 1.1949480772018433,
|
| 599 |
+
"learning_rate": 1.328978898250525e-06,
|
| 600 |
+
"logits/chosen": 1.7057956457138062,
|
| 601 |
+
"logits/rejected": 1.726438283920288,
|
| 602 |
+
"logps/chosen": -85.27348327636719,
|
| 603 |
+
"logps/rejected": -96.06895446777344,
|
| 604 |
+
"loss": 0.5553,
|
| 605 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 606 |
+
"rewards/chosen": -0.3689552843570709,
|
| 607 |
+
"rewards/margins": 0.3453688621520996,
|
| 608 |
+
"rewards/rejected": -0.7143241763114929,
|
| 609 |
+
"step": 400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 13.860759493670885,
|
| 613 |
+
"grad_norm": 1.5321677923202515,
|
| 614 |
+
"learning_rate": 1.198246553841744e-06,
|
| 615 |
+
"logits/chosen": 1.8362537622451782,
|
| 616 |
+
"logits/rejected": 1.889491081237793,
|
| 617 |
+
"logps/chosen": -78.84573364257812,
|
| 618 |
+
"logps/rejected": -75.66096496582031,
|
| 619 |
+
"loss": 0.5618,
|
| 620 |
+
"rewards/accuracies": 0.762499988079071,
|
| 621 |
+
"rewards/chosen": -0.34546419978141785,
|
| 622 |
+
"rewards/margins": 0.3866986334323883,
|
| 623 |
+
"rewards/rejected": -0.7321628332138062,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 14.19831223628692,
|
| 628 |
+
"grad_norm": 1.1697853803634644,
|
| 629 |
+
"learning_rate": 1.0722278491423998e-06,
|
| 630 |
+
"logits/chosen": 1.7950217723846436,
|
| 631 |
+
"logits/rejected": 1.8145115375518799,
|
| 632 |
+
"logps/chosen": -82.2846908569336,
|
| 633 |
+
"logps/rejected": -91.40074157714844,
|
| 634 |
+
"loss": 0.5516,
|
| 635 |
+
"rewards/accuracies": 0.800000011920929,
|
| 636 |
+
"rewards/chosen": -0.37175649404525757,
|
| 637 |
+
"rewards/margins": 0.404013067483902,
|
| 638 |
+
"rewards/rejected": -0.7757695913314819,
|
| 639 |
+
"step": 420
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 14.535864978902953,
|
| 643 |
+
"grad_norm": 1.163073182106018,
|
| 644 |
+
"learning_rate": 9.513790969606926e-07,
|
| 645 |
+
"logits/chosen": 1.686415433883667,
|
| 646 |
+
"logits/rejected": 1.7637500762939453,
|
| 647 |
+
"logps/chosen": -100.37837219238281,
|
| 648 |
+
"logps/rejected": -100.43409729003906,
|
| 649 |
+
"loss": 0.5583,
|
| 650 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 651 |
+
"rewards/chosen": -0.35831838846206665,
|
| 652 |
+
"rewards/margins": 0.3624442219734192,
|
| 653 |
+
"rewards/rejected": -0.7207626104354858,
|
| 654 |
+
"step": 430
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 14.873417721518987,
|
| 658 |
+
"grad_norm": 1.148380160331726,
|
| 659 |
+
"learning_rate": 8.361378897445643e-07,
|
| 660 |
+
"logits/chosen": 1.6370818614959717,
|
| 661 |
+
"logits/rejected": 1.752598524093628,
|
| 662 |
+
"logps/chosen": -84.63670349121094,
|
| 663 |
+
"logps/rejected": -89.8626708984375,
|
| 664 |
+
"loss": 0.5584,
|
| 665 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 666 |
+
"rewards/chosen": -0.44350141286849976,
|
| 667 |
+
"rewards/margins": 0.4355877935886383,
|
| 668 |
+
"rewards/rejected": -0.8790891766548157,
|
| 669 |
+
"step": 440
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 15.210970464135022,
|
| 673 |
+
"grad_norm": 1.1012156009674072,
|
| 674 |
+
"learning_rate": 7.269215150626391e-07,
|
| 675 |
+
"logits/chosen": 1.8232038021087646,
|
| 676 |
+
"logits/rejected": 1.8113384246826172,
|
| 677 |
+
"logps/chosen": -95.2444839477539,
|
| 678 |
+
"logps/rejected": -85.72362518310547,
|
| 679 |
+
"loss": 0.5539,
|
| 680 |
+
"rewards/accuracies": 0.875,
|
| 681 |
+
"rewards/chosen": -0.3705037236213684,
|
| 682 |
+
"rewards/margins": 0.5386990308761597,
|
| 683 |
+
"rewards/rejected": -0.9092028737068176,
|
| 684 |
+
"step": 450
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 15.548523206751055,
|
| 688 |
+
"grad_norm": 1.0890499353408813,
|
| 689 |
+
"learning_rate": 6.241254446089942e-07,
|
| 690 |
+
"logits/chosen": 1.6102081537246704,
|
| 691 |
+
"logits/rejected": 1.6902793645858765,
|
| 692 |
+
"logps/chosen": -77.29241943359375,
|
| 693 |
+
"logps/rejected": -87.38616943359375,
|
| 694 |
+
"loss": 0.554,
|
| 695 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 696 |
+
"rewards/chosen": -0.36334335803985596,
|
| 697 |
+
"rewards/margins": 0.41814422607421875,
|
| 698 |
+
"rewards/rejected": -0.7814875841140747,
|
| 699 |
+
"step": 460
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 15.886075949367088,
|
| 703 |
+
"grad_norm": 1.1587886810302734,
|
| 704 |
+
"learning_rate": 5.281219022030423e-07,
|
| 705 |
+
"logits/chosen": 1.7049728631973267,
|
| 706 |
+
"logits/rejected": 1.7815492153167725,
|
| 707 |
+
"logps/chosen": -79.66454315185547,
|
| 708 |
+
"logps/rejected": -91.70343017578125,
|
| 709 |
+
"loss": 0.5472,
|
| 710 |
+
"rewards/accuracies": 0.800000011920929,
|
| 711 |
+
"rewards/chosen": -0.3898239731788635,
|
| 712 |
+
"rewards/margins": 0.40187686681747437,
|
| 713 |
+
"rewards/rejected": -0.7917007803916931,
|
| 714 |
+
"step": 470
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 16.223628691983123,
|
| 718 |
+
"grad_norm": 1.5429887771606445,
|
| 719 |
+
"learning_rate": 4.392585159698087e-07,
|
| 720 |
+
"logits/chosen": 1.6508013010025024,
|
| 721 |
+
"logits/rejected": 1.7940822839736938,
|
| 722 |
+
"logps/chosen": -77.51395416259766,
|
| 723 |
+
"logps/rejected": -90.20869445800781,
|
| 724 |
+
"loss": 0.5512,
|
| 725 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 726 |
+
"rewards/chosen": -0.35601454973220825,
|
| 727 |
+
"rewards/margins": 0.3707844018936157,
|
| 728 |
+
"rewards/rejected": -0.7267988920211792,
|
| 729 |
+
"step": 480
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 16.561181434599156,
|
| 733 |
+
"grad_norm": 1.1558414697647095,
|
| 734 |
+
"learning_rate": 3.578570595810274e-07,
|
| 735 |
+
"logits/chosen": 1.6670711040496826,
|
| 736 |
+
"logits/rejected": 1.6244487762451172,
|
| 737 |
+
"logps/chosen": -101.91804504394531,
|
| 738 |
+
"logps/rejected": -91.96507263183594,
|
| 739 |
+
"loss": 0.5452,
|
| 740 |
+
"rewards/accuracies": 0.824999988079071,
|
| 741 |
+
"rewards/chosen": -0.40192681550979614,
|
| 742 |
+
"rewards/margins": 0.44803065061569214,
|
| 743 |
+
"rewards/rejected": -0.8499574661254883,
|
| 744 |
+
"step": 490
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 16.89873417721519,
|
| 748 |
+
"grad_norm": 1.1151753664016724,
|
| 749 |
+
"learning_rate": 2.8421228711503127e-07,
|
| 750 |
+
"logits/chosen": 1.7409915924072266,
|
| 751 |
+
"logits/rejected": 1.8301231861114502,
|
| 752 |
+
"logps/chosen": -71.89210510253906,
|
| 753 |
+
"logps/rejected": -90.07672119140625,
|
| 754 |
+
"loss": 0.5423,
|
| 755 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 756 |
+
"rewards/chosen": -0.4172780513763428,
|
| 757 |
+
"rewards/margins": 0.394390344619751,
|
| 758 |
+
"rewards/rejected": -0.8116683959960938,
|
| 759 |
+
"step": 500
|
| 760 |
+
}
|
| 761 |
+
],
|
| 762 |
+
"logging_steps": 10,
|
| 763 |
+
"max_steps": 580,
|
| 764 |
+
"num_input_tokens_seen": 0,
|
| 765 |
+
"num_train_epochs": 20,
|
| 766 |
+
"save_steps": 50,
|
| 767 |
+
"stateful_callbacks": {
|
| 768 |
+
"TrainerControl": {
|
| 769 |
+
"args": {
|
| 770 |
+
"should_epoch_stop": false,
|
| 771 |
+
"should_evaluate": false,
|
| 772 |
+
"should_log": false,
|
| 773 |
+
"should_save": true,
|
| 774 |
+
"should_training_stop": false
|
| 775 |
+
},
|
| 776 |
+
"attributes": {}
|
| 777 |
+
}
|
| 778 |
+
},
|
| 779 |
+
"total_flos": 1.7176766542575043e+18,
|
| 780 |
+
"train_batch_size": 1,
|
| 781 |
+
"trial_name": null,
|
| 782 |
+
"trial_params": null
|
| 783 |
+
}
|
Power_Area/checkpoint-550/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Power_Area/checkpoint-550/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Power_Area/checkpoint-550/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Power_Area/checkpoint-550/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Power_Area/checkpoint-550/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Power_Area/checkpoint-550/trainer_state.json
ADDED
|
@@ -0,0 +1,858 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 18.58649789029536,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 550,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33755274261603374,
|
| 13 |
+
"grad_norm": 0.4396141469478607,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": 1.6453087329864502,
|
| 16 |
+
"logits/rejected": 1.694819450378418,
|
| 17 |
+
"logps/chosen": -74.5937728881836,
|
| 18 |
+
"logps/rejected": -83.19783782958984,
|
| 19 |
+
"loss": 0.6928,
|
| 20 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 21 |
+
"rewards/chosen": 0.003385844174772501,
|
| 22 |
+
"rewards/margins": 0.004794469103217125,
|
| 23 |
+
"rewards/rejected": -0.0014086246956139803,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6751054852320675,
|
| 28 |
+
"grad_norm": 3.18404483795166,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": 1.7945035696029663,
|
| 31 |
+
"logits/rejected": 1.8347476720809937,
|
| 32 |
+
"logps/chosen": -95.46636199951172,
|
| 33 |
+
"logps/rejected": -101.22709655761719,
|
| 34 |
+
"loss": 0.6933,
|
| 35 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 36 |
+
"rewards/chosen": -0.0005593777750618756,
|
| 37 |
+
"rewards/margins": -0.002013001125305891,
|
| 38 |
+
"rewards/rejected": 0.0014536241069436073,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0126582278481013,
|
| 43 |
+
"grad_norm": 0.48596081137657166,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": 1.774155616760254,
|
| 46 |
+
"logits/rejected": 1.8374344110488892,
|
| 47 |
+
"logps/chosen": -82.01265716552734,
|
| 48 |
+
"logps/rejected": -84.23635864257812,
|
| 49 |
+
"loss": 0.6948,
|
| 50 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 51 |
+
"rewards/chosen": -0.0031326995231211185,
|
| 52 |
+
"rewards/margins": -0.00463916826993227,
|
| 53 |
+
"rewards/rejected": 0.0015064675826579332,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.350210970464135,
|
| 58 |
+
"grad_norm": 0.5144609808921814,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": 1.838865876197815,
|
| 61 |
+
"logits/rejected": 1.9505430459976196,
|
| 62 |
+
"logps/chosen": -73.50071716308594,
|
| 63 |
+
"logps/rejected": -88.8648452758789,
|
| 64 |
+
"loss": 0.6928,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.0035957477521151304,
|
| 67 |
+
"rewards/margins": -0.008830643258988857,
|
| 68 |
+
"rewards/rejected": 0.005234894808381796,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6877637130801688,
|
| 73 |
+
"grad_norm": 0.48295095562934875,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": 1.8197529315948486,
|
| 76 |
+
"logits/rejected": 1.8459796905517578,
|
| 77 |
+
"logps/chosen": -83.36590576171875,
|
| 78 |
+
"logps/rejected": -70.26930236816406,
|
| 79 |
+
"loss": 0.6929,
|
| 80 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 81 |
+
"rewards/chosen": -0.0030026868917047977,
|
| 82 |
+
"rewards/margins": -0.006082554347813129,
|
| 83 |
+
"rewards/rejected": 0.003079867223277688,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.0464135021097047,
|
| 88 |
+
"grad_norm": 0.5616092085838318,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": 1.7525272369384766,
|
| 91 |
+
"logits/rejected": 1.8092533349990845,
|
| 92 |
+
"logps/chosen": -82.01802062988281,
|
| 93 |
+
"logps/rejected": -78.39723205566406,
|
| 94 |
+
"loss": 0.6949,
|
| 95 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 96 |
+
"rewards/chosen": -0.0010920714121311903,
|
| 97 |
+
"rewards/margins": -0.0016235255170613527,
|
| 98 |
+
"rewards/rejected": 0.0005314538720995188,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3839662447257384,
|
| 103 |
+
"grad_norm": 0.5237122774124146,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": 1.754880666732788,
|
| 106 |
+
"logits/rejected": 1.8100305795669556,
|
| 107 |
+
"logps/chosen": -89.62864685058594,
|
| 108 |
+
"logps/rejected": -88.30036926269531,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5,
|
| 111 |
+
"rewards/chosen": -0.002314353361725807,
|
| 112 |
+
"rewards/margins": -0.001038494287058711,
|
| 113 |
+
"rewards/rejected": -0.0012758590746670961,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.721518987341772,
|
| 118 |
+
"grad_norm": 0.507128119468689,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": 1.7501789331436157,
|
| 121 |
+
"logits/rejected": 1.6666221618652344,
|
| 122 |
+
"logps/chosen": -94.74919128417969,
|
| 123 |
+
"logps/rejected": -74.9794692993164,
|
| 124 |
+
"loss": 0.6922,
|
| 125 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 126 |
+
"rewards/chosen": 0.00475720502436161,
|
| 127 |
+
"rewards/margins": 0.01054429542273283,
|
| 128 |
+
"rewards/rejected": -0.005787090864032507,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.059071729957806,
|
| 133 |
+
"grad_norm": 0.8151038885116577,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": 1.7203710079193115,
|
| 136 |
+
"logits/rejected": 1.7376699447631836,
|
| 137 |
+
"logps/chosen": -76.8824691772461,
|
| 138 |
+
"logps/rejected": -84.74555206298828,
|
| 139 |
+
"loss": 0.6925,
|
| 140 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 141 |
+
"rewards/chosen": 0.01064519863575697,
|
| 142 |
+
"rewards/margins": 0.012716365046799183,
|
| 143 |
+
"rewards/rejected": -0.0020711664110422134,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3966244725738397,
|
| 148 |
+
"grad_norm": 0.5476706027984619,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": 1.7857105731964111,
|
| 151 |
+
"logits/rejected": 1.7341340780258179,
|
| 152 |
+
"logps/chosen": -88.39775085449219,
|
| 153 |
+
"logps/rejected": -80.00445556640625,
|
| 154 |
+
"loss": 0.6893,
|
| 155 |
+
"rewards/accuracies": 0.612500011920929,
|
| 156 |
+
"rewards/chosen": 0.0052363635040819645,
|
| 157 |
+
"rewards/margins": 0.016881367191672325,
|
| 158 |
+
"rewards/rejected": -0.011645001359283924,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.7341772151898733,
|
| 163 |
+
"grad_norm": 0.6562405824661255,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": 1.737647294998169,
|
| 166 |
+
"logits/rejected": 1.7781591415405273,
|
| 167 |
+
"logps/chosen": -92.72380065917969,
|
| 168 |
+
"logps/rejected": -85.51634216308594,
|
| 169 |
+
"loss": 0.6899,
|
| 170 |
+
"rewards/accuracies": 0.512499988079071,
|
| 171 |
+
"rewards/chosen": -0.010819707065820694,
|
| 172 |
+
"rewards/margins": -0.0005886269500479102,
|
| 173 |
+
"rewards/rejected": -0.010231079533696175,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.071729957805907,
|
| 178 |
+
"grad_norm": 0.6393210291862488,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": 1.7890704870224,
|
| 181 |
+
"logits/rejected": 1.8340994119644165,
|
| 182 |
+
"logps/chosen": -87.615478515625,
|
| 183 |
+
"logps/rejected": -108.13908386230469,
|
| 184 |
+
"loss": 0.6872,
|
| 185 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 186 |
+
"rewards/chosen": 0.002250433200970292,
|
| 187 |
+
"rewards/margins": 0.012117428705096245,
|
| 188 |
+
"rewards/rejected": -0.009866995736956596,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.409282700421941,
|
| 193 |
+
"grad_norm": 0.7390326261520386,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": 1.7916072607040405,
|
| 196 |
+
"logits/rejected": 1.787153959274292,
|
| 197 |
+
"logps/chosen": -84.11034393310547,
|
| 198 |
+
"logps/rejected": -76.81166076660156,
|
| 199 |
+
"loss": 0.6844,
|
| 200 |
+
"rewards/accuracies": 0.5625,
|
| 201 |
+
"rewards/chosen": -0.003190569579601288,
|
| 202 |
+
"rewards/margins": 0.015628555789589882,
|
| 203 |
+
"rewards/rejected": -0.01881912164390087,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.746835443037975,
|
| 208 |
+
"grad_norm": 0.7888330817222595,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": 1.8455331325531006,
|
| 211 |
+
"logits/rejected": 1.8137515783309937,
|
| 212 |
+
"logps/chosen": -78.94912719726562,
|
| 213 |
+
"logps/rejected": -76.1368637084961,
|
| 214 |
+
"loss": 0.6819,
|
| 215 |
+
"rewards/accuracies": 0.625,
|
| 216 |
+
"rewards/chosen": -0.012986091896891594,
|
| 217 |
+
"rewards/margins": 0.015167826786637306,
|
| 218 |
+
"rewards/rejected": -0.02815392054617405,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.084388185654008,
|
| 223 |
+
"grad_norm": 0.7248090505599976,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": 1.6686553955078125,
|
| 226 |
+
"logits/rejected": 1.6654260158538818,
|
| 227 |
+
"logps/chosen": -78.25769805908203,
|
| 228 |
+
"logps/rejected": -71.3498306274414,
|
| 229 |
+
"loss": 0.677,
|
| 230 |
+
"rewards/accuracies": 0.612500011920929,
|
| 231 |
+
"rewards/chosen": -0.0182911679148674,
|
| 232 |
+
"rewards/margins": 0.02633112668991089,
|
| 233 |
+
"rewards/rejected": -0.04462229460477829,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.421940928270042,
|
| 238 |
+
"grad_norm": 0.7906918525695801,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": 1.8054498434066772,
|
| 241 |
+
"logits/rejected": 1.751422643661499,
|
| 242 |
+
"logps/chosen": -91.65776824951172,
|
| 243 |
+
"logps/rejected": -68.41027069091797,
|
| 244 |
+
"loss": 0.6741,
|
| 245 |
+
"rewards/accuracies": 0.574999988079071,
|
| 246 |
+
"rewards/chosen": -0.04313550516963005,
|
| 247 |
+
"rewards/margins": 0.017568334937095642,
|
| 248 |
+
"rewards/rejected": -0.060703836381435394,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.759493670886076,
|
| 253 |
+
"grad_norm": 0.8152453303337097,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": 1.742419958114624,
|
| 256 |
+
"logits/rejected": 1.9456249475479126,
|
| 257 |
+
"logps/chosen": -80.52605438232422,
|
| 258 |
+
"logps/rejected": -117.02473449707031,
|
| 259 |
+
"loss": 0.67,
|
| 260 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 261 |
+
"rewards/chosen": -0.030041133984923363,
|
| 262 |
+
"rewards/margins": 0.03393586724996567,
|
| 263 |
+
"rewards/rejected": -0.06397700309753418,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.09704641350211,
|
| 268 |
+
"grad_norm": 0.7848192453384399,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": 1.836090087890625,
|
| 271 |
+
"logits/rejected": 2.0285377502441406,
|
| 272 |
+
"logps/chosen": -72.87449645996094,
|
| 273 |
+
"logps/rejected": -101.46552276611328,
|
| 274 |
+
"loss": 0.6659,
|
| 275 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 276 |
+
"rewards/chosen": -0.04543738812208176,
|
| 277 |
+
"rewards/margins": 0.0431094653904438,
|
| 278 |
+
"rewards/rejected": -0.08854684978723526,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.434599156118144,
|
| 283 |
+
"grad_norm": 0.8349910378456116,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": 1.7459189891815186,
|
| 286 |
+
"logits/rejected": 1.8324615955352783,
|
| 287 |
+
"logps/chosen": -72.0348892211914,
|
| 288 |
+
"logps/rejected": -86.13719940185547,
|
| 289 |
+
"loss": 0.6555,
|
| 290 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 291 |
+
"rewards/chosen": -0.04952271655201912,
|
| 292 |
+
"rewards/margins": 0.07018387317657471,
|
| 293 |
+
"rewards/rejected": -0.11970658600330353,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.772151898734177,
|
| 298 |
+
"grad_norm": 0.9766960144042969,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": 1.7785131931304932,
|
| 301 |
+
"logits/rejected": 1.8624244928359985,
|
| 302 |
+
"logps/chosen": -91.82891845703125,
|
| 303 |
+
"logps/rejected": -102.28694915771484,
|
| 304 |
+
"loss": 0.6465,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.04159725084900856,
|
| 307 |
+
"rewards/margins": 0.09511855244636536,
|
| 308 |
+
"rewards/rejected": -0.1367158144712448,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.109704641350211,
|
| 313 |
+
"grad_norm": 0.9714512228965759,
|
| 314 |
+
"learning_rate": 4.024886035802432e-06,
|
| 315 |
+
"logits/chosen": 1.756864309310913,
|
| 316 |
+
"logits/rejected": 1.7497355937957764,
|
| 317 |
+
"logps/chosen": -82.28770446777344,
|
| 318 |
+
"logps/rejected": -72.7796859741211,
|
| 319 |
+
"loss": 0.6498,
|
| 320 |
+
"rewards/accuracies": 0.8125,
|
| 321 |
+
"rewards/chosen": -0.0668434351682663,
|
| 322 |
+
"rewards/margins": 0.1403656005859375,
|
| 323 |
+
"rewards/rejected": -0.2072090357542038,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.447257383966245,
|
| 328 |
+
"grad_norm": 0.9135355949401855,
|
| 329 |
+
"learning_rate": 3.9029676634059565e-06,
|
| 330 |
+
"logits/chosen": 1.677150011062622,
|
| 331 |
+
"logits/rejected": 1.7840830087661743,
|
| 332 |
+
"logps/chosen": -78.84297180175781,
|
| 333 |
+
"logps/rejected": -102.04107666015625,
|
| 334 |
+
"loss": 0.6438,
|
| 335 |
+
"rewards/accuracies": 0.75,
|
| 336 |
+
"rewards/chosen": -0.10343215614557266,
|
| 337 |
+
"rewards/margins": 0.15733790397644043,
|
| 338 |
+
"rewards/rejected": -0.2607700526714325,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.784810126582278,
|
| 343 |
+
"grad_norm": 0.8835084438323975,
|
| 344 |
+
"learning_rate": 3.7759691553595214e-06,
|
| 345 |
+
"logits/chosen": 1.8346344232559204,
|
| 346 |
+
"logits/rejected": 1.838543176651001,
|
| 347 |
+
"logps/chosen": -109.93656921386719,
|
| 348 |
+
"logps/rejected": -73.76078033447266,
|
| 349 |
+
"loss": 0.6279,
|
| 350 |
+
"rewards/accuracies": 0.75,
|
| 351 |
+
"rewards/chosen": -0.08149126917123795,
|
| 352 |
+
"rewards/margins": 0.17928050458431244,
|
| 353 |
+
"rewards/rejected": -0.26077181100845337,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.122362869198312,
|
| 358 |
+
"grad_norm": 0.9854581952095032,
|
| 359 |
+
"learning_rate": 3.6443503723320837e-06,
|
| 360 |
+
"logits/chosen": 1.7367273569107056,
|
| 361 |
+
"logits/rejected": 1.723976492881775,
|
| 362 |
+
"logps/chosen": -80.76436614990234,
|
| 363 |
+
"logps/rejected": -75.7645034790039,
|
| 364 |
+
"loss": 0.6309,
|
| 365 |
+
"rewards/accuracies": 0.762499988079071,
|
| 366 |
+
"rewards/chosen": -0.12716726958751678,
|
| 367 |
+
"rewards/margins": 0.15734827518463135,
|
| 368 |
+
"rewards/rejected": -0.2845155596733093,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 8.459915611814345,
|
| 373 |
+
"grad_norm": 0.9569210410118103,
|
| 374 |
+
"learning_rate": 3.508587904974522e-06,
|
| 375 |
+
"logits/chosen": 1.711611032485962,
|
| 376 |
+
"logits/rejected": 1.820723295211792,
|
| 377 |
+
"logps/chosen": -81.62940979003906,
|
| 378 |
+
"logps/rejected": -104.07059478759766,
|
| 379 |
+
"loss": 0.6206,
|
| 380 |
+
"rewards/accuracies": 0.800000011920929,
|
| 381 |
+
"rewards/chosen": -0.12964895367622375,
|
| 382 |
+
"rewards/margins": 0.2236514836549759,
|
| 383 |
+
"rewards/rejected": -0.35330042243003845,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.79746835443038,
|
| 388 |
+
"grad_norm": 0.9199231863021851,
|
| 389 |
+
"learning_rate": 3.3691733481883693e-06,
|
| 390 |
+
"logits/chosen": 1.860053300857544,
|
| 391 |
+
"logits/rejected": 1.8826453685760498,
|
| 392 |
+
"logps/chosen": -89.85298919677734,
|
| 393 |
+
"logps/rejected": -90.7202377319336,
|
| 394 |
+
"loss": 0.6129,
|
| 395 |
+
"rewards/accuracies": 0.75,
|
| 396 |
+
"rewards/chosen": -0.1632840931415558,
|
| 397 |
+
"rewards/margins": 0.22734332084655762,
|
| 398 |
+
"rewards/rejected": -0.3906274437904358,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.135021097046414,
|
| 403 |
+
"grad_norm": 0.996032178401947,
|
| 404 |
+
"learning_rate": 3.226611521064278e-06,
|
| 405 |
+
"logits/chosen": 1.8121602535247803,
|
| 406 |
+
"logits/rejected": 1.7851508855819702,
|
| 407 |
+
"logps/chosen": -76.85626220703125,
|
| 408 |
+
"logps/rejected": -77.3901138305664,
|
| 409 |
+
"loss": 0.6155,
|
| 410 |
+
"rewards/accuracies": 0.75,
|
| 411 |
+
"rewards/chosen": -0.16423651576042175,
|
| 412 |
+
"rewards/margins": 0.2163097858428955,
|
| 413 |
+
"rewards/rejected": -0.38054633140563965,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 9.472573839662447,
|
| 418 |
+
"grad_norm": 0.96324622631073,
|
| 419 |
+
"learning_rate": 3.0814186389357765e-06,
|
| 420 |
+
"logits/chosen": 1.7609102725982666,
|
| 421 |
+
"logits/rejected": 1.782065749168396,
|
| 422 |
+
"logps/chosen": -78.853271484375,
|
| 423 |
+
"logps/rejected": -81.43799591064453,
|
| 424 |
+
"loss": 0.5991,
|
| 425 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 426 |
+
"rewards/chosen": -0.19906465709209442,
|
| 427 |
+
"rewards/margins": 0.2417418658733368,
|
| 428 |
+
"rewards/rejected": -0.4408065378665924,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 9.810126582278482,
|
| 433 |
+
"grad_norm": 0.9327431917190552,
|
| 434 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 435 |
+
"logits/chosen": 1.7485430240631104,
|
| 436 |
+
"logits/rejected": 1.7885955572128296,
|
| 437 |
+
"logps/chosen": -81.84668731689453,
|
| 438 |
+
"logps/rejected": -84.5110855102539,
|
| 439 |
+
"loss": 0.6035,
|
| 440 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 441 |
+
"rewards/chosen": -0.24916405975818634,
|
| 442 |
+
"rewards/margins": 0.22875118255615234,
|
| 443 |
+
"rewards/rejected": -0.47791528701782227,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.147679324894515,
|
| 448 |
+
"grad_norm": 1.1683701276779175,
|
| 449 |
+
"learning_rate": 2.785250302445062e-06,
|
| 450 |
+
"logits/chosen": 1.8126602172851562,
|
| 451 |
+
"logits/rejected": 1.8814666271209717,
|
| 452 |
+
"logps/chosen": -105.7123031616211,
|
| 453 |
+
"logps/rejected": -92.78335571289062,
|
| 454 |
+
"loss": 0.5916,
|
| 455 |
+
"rewards/accuracies": 0.800000011920929,
|
| 456 |
+
"rewards/chosen": -0.257813036441803,
|
| 457 |
+
"rewards/margins": 0.28732481598854065,
|
| 458 |
+
"rewards/rejected": -0.5451378226280212,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.485232067510548,
|
| 463 |
+
"grad_norm": 1.078698754310608,
|
| 464 |
+
"learning_rate": 2.6353472714635443e-06,
|
| 465 |
+
"logits/chosen": 1.7991764545440674,
|
| 466 |
+
"logits/rejected": 1.8787552118301392,
|
| 467 |
+
"logps/chosen": -70.400634765625,
|
| 468 |
+
"logps/rejected": -72.78517150878906,
|
| 469 |
+
"loss": 0.5893,
|
| 470 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 471 |
+
"rewards/chosen": -0.23745933175086975,
|
| 472 |
+
"rewards/margins": 0.22456249594688416,
|
| 473 |
+
"rewards/rejected": -0.4620218276977539,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 10.822784810126583,
|
| 478 |
+
"grad_norm": 1.0667306184768677,
|
| 479 |
+
"learning_rate": 2.4849541490017868e-06,
|
| 480 |
+
"logits/chosen": 1.7493784427642822,
|
| 481 |
+
"logits/rejected": 1.7776050567626953,
|
| 482 |
+
"logps/chosen": -79.56948852539062,
|
| 483 |
+
"logps/rejected": -95.15191650390625,
|
| 484 |
+
"loss": 0.5943,
|
| 485 |
+
"rewards/accuracies": 0.8125,
|
| 486 |
+
"rewards/chosen": -0.2948698401451111,
|
| 487 |
+
"rewards/margins": 0.27440011501312256,
|
| 488 |
+
"rewards/rejected": -0.5692699551582336,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.160337552742616,
|
| 493 |
+
"grad_norm": 1.1734286546707153,
|
| 494 |
+
"learning_rate": 2.3346155074564712e-06,
|
| 495 |
+
"logits/chosen": 1.7588024139404297,
|
| 496 |
+
"logits/rejected": 1.6906486749649048,
|
| 497 |
+
"logps/chosen": -92.88114929199219,
|
| 498 |
+
"logps/rejected": -87.77473449707031,
|
| 499 |
+
"loss": 0.5748,
|
| 500 |
+
"rewards/accuracies": 0.8125,
|
| 501 |
+
"rewards/chosen": -0.26193878054618835,
|
| 502 |
+
"rewards/margins": 0.31644436717033386,
|
| 503 |
+
"rewards/rejected": -0.5783831477165222,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 11.49789029535865,
|
| 508 |
+
"grad_norm": 1.0506142377853394,
|
| 509 |
+
"learning_rate": 2.184875721949277e-06,
|
| 510 |
+
"logits/chosen": 1.6390129327774048,
|
| 511 |
+
"logits/rejected": 1.6817207336425781,
|
| 512 |
+
"logps/chosen": -85.6020278930664,
|
| 513 |
+
"logps/rejected": -81.51480865478516,
|
| 514 |
+
"loss": 0.5755,
|
| 515 |
+
"rewards/accuracies": 0.824999988079071,
|
| 516 |
+
"rewards/chosen": -0.2864437997341156,
|
| 517 |
+
"rewards/margins": 0.3067106604576111,
|
| 518 |
+
"rewards/rejected": -0.5931544899940491,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 11.835443037974684,
|
| 523 |
+
"grad_norm": 1.0367387533187866,
|
| 524 |
+
"learning_rate": 2.0362769991485514e-06,
|
| 525 |
+
"logits/chosen": 1.811912178993225,
|
| 526 |
+
"logits/rejected": 1.8571999073028564,
|
| 527 |
+
"logps/chosen": -79.2660903930664,
|
| 528 |
+
"logps/rejected": -105.51014709472656,
|
| 529 |
+
"loss": 0.5743,
|
| 530 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 531 |
+
"rewards/chosen": -0.2905730605125427,
|
| 532 |
+
"rewards/margins": 0.37750759720802307,
|
| 533 |
+
"rewards/rejected": -0.6680806279182434,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 12.172995780590718,
|
| 538 |
+
"grad_norm": 1.249039888381958,
|
| 539 |
+
"learning_rate": 1.8893574139429226e-06,
|
| 540 |
+
"logits/chosen": 1.8357423543930054,
|
| 541 |
+
"logits/rejected": 1.8285624980926514,
|
| 542 |
+
"logps/chosen": -85.5277099609375,
|
| 543 |
+
"logps/rejected": -90.13473510742188,
|
| 544 |
+
"loss": 0.575,
|
| 545 |
+
"rewards/accuracies": 0.762499988079071,
|
| 546 |
+
"rewards/chosen": -0.36660733819007874,
|
| 547 |
+
"rewards/margins": 0.3461737632751465,
|
| 548 |
+
"rewards/rejected": -0.7127811312675476,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 12.51054852320675,
|
| 553 |
+
"grad_norm": 1.1541879177093506,
|
| 554 |
+
"learning_rate": 1.744648961076068e-06,
|
| 555 |
+
"logits/chosen": 1.790567398071289,
|
| 556 |
+
"logits/rejected": 1.7228246927261353,
|
| 557 |
+
"logps/chosen": -86.40596008300781,
|
| 558 |
+
"logps/rejected": -75.5702896118164,
|
| 559 |
+
"loss": 0.5693,
|
| 560 |
+
"rewards/accuracies": 0.762499988079071,
|
| 561 |
+
"rewards/chosen": -0.34050875902175903,
|
| 562 |
+
"rewards/margins": 0.2642201781272888,
|
| 563 |
+
"rewards/rejected": -0.6047288775444031,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 12.848101265822784,
|
| 568 |
+
"grad_norm": 1.0363268852233887,
|
| 569 |
+
"learning_rate": 1.602675628797636e-06,
|
| 570 |
+
"logits/chosen": 1.6812736988067627,
|
| 571 |
+
"logits/rejected": 1.7188876867294312,
|
| 572 |
+
"logps/chosen": -81.14212799072266,
|
| 573 |
+
"logps/rejected": -82.90364074707031,
|
| 574 |
+
"loss": 0.5594,
|
| 575 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 576 |
+
"rewards/chosen": -0.3105277419090271,
|
| 577 |
+
"rewards/margins": 0.3372951149940491,
|
| 578 |
+
"rewards/rejected": -0.6478228569030762,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 13.185654008438819,
|
| 583 |
+
"grad_norm": 1.047418475151062,
|
| 584 |
+
"learning_rate": 1.4639515015056205e-06,
|
| 585 |
+
"logits/chosen": 1.6939361095428467,
|
| 586 |
+
"logits/rejected": 1.7271579504013062,
|
| 587 |
+
"logps/chosen": -86.88213348388672,
|
| 588 |
+
"logps/rejected": -99.46037292480469,
|
| 589 |
+
"loss": 0.558,
|
| 590 |
+
"rewards/accuracies": 0.762499988079071,
|
| 591 |
+
"rewards/chosen": -0.2660979926586151,
|
| 592 |
+
"rewards/margins": 0.4496893882751465,
|
| 593 |
+
"rewards/rejected": -0.7157873511314392,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 13.523206751054852,
|
| 598 |
+
"grad_norm": 1.1949480772018433,
|
| 599 |
+
"learning_rate": 1.328978898250525e-06,
|
| 600 |
+
"logits/chosen": 1.7057956457138062,
|
| 601 |
+
"logits/rejected": 1.726438283920288,
|
| 602 |
+
"logps/chosen": -85.27348327636719,
|
| 603 |
+
"logps/rejected": -96.06895446777344,
|
| 604 |
+
"loss": 0.5553,
|
| 605 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 606 |
+
"rewards/chosen": -0.3689552843570709,
|
| 607 |
+
"rewards/margins": 0.3453688621520996,
|
| 608 |
+
"rewards/rejected": -0.7143241763114929,
|
| 609 |
+
"step": 400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 13.860759493670885,
|
| 613 |
+
"grad_norm": 1.5321677923202515,
|
| 614 |
+
"learning_rate": 1.198246553841744e-06,
|
| 615 |
+
"logits/chosen": 1.8362537622451782,
|
| 616 |
+
"logits/rejected": 1.889491081237793,
|
| 617 |
+
"logps/chosen": -78.84573364257812,
|
| 618 |
+
"logps/rejected": -75.66096496582031,
|
| 619 |
+
"loss": 0.5618,
|
| 620 |
+
"rewards/accuracies": 0.762499988079071,
|
| 621 |
+
"rewards/chosen": -0.34546419978141785,
|
| 622 |
+
"rewards/margins": 0.3866986334323883,
|
| 623 |
+
"rewards/rejected": -0.7321628332138062,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 14.19831223628692,
|
| 628 |
+
"grad_norm": 1.1697853803634644,
|
| 629 |
+
"learning_rate": 1.0722278491423998e-06,
|
| 630 |
+
"logits/chosen": 1.7950217723846436,
|
| 631 |
+
"logits/rejected": 1.8145115375518799,
|
| 632 |
+
"logps/chosen": -82.2846908569336,
|
| 633 |
+
"logps/rejected": -91.40074157714844,
|
| 634 |
+
"loss": 0.5516,
|
| 635 |
+
"rewards/accuracies": 0.800000011920929,
|
| 636 |
+
"rewards/chosen": -0.37175649404525757,
|
| 637 |
+
"rewards/margins": 0.404013067483902,
|
| 638 |
+
"rewards/rejected": -0.7757695913314819,
|
| 639 |
+
"step": 420
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 14.535864978902953,
|
| 643 |
+
"grad_norm": 1.163073182106018,
|
| 644 |
+
"learning_rate": 9.513790969606926e-07,
|
| 645 |
+
"logits/chosen": 1.686415433883667,
|
| 646 |
+
"logits/rejected": 1.7637500762939453,
|
| 647 |
+
"logps/chosen": -100.37837219238281,
|
| 648 |
+
"logps/rejected": -100.43409729003906,
|
| 649 |
+
"loss": 0.5583,
|
| 650 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 651 |
+
"rewards/chosen": -0.35831838846206665,
|
| 652 |
+
"rewards/margins": 0.3624442219734192,
|
| 653 |
+
"rewards/rejected": -0.7207626104354858,
|
| 654 |
+
"step": 430
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 14.873417721518987,
|
| 658 |
+
"grad_norm": 1.148380160331726,
|
| 659 |
+
"learning_rate": 8.361378897445643e-07,
|
| 660 |
+
"logits/chosen": 1.6370818614959717,
|
| 661 |
+
"logits/rejected": 1.752598524093628,
|
| 662 |
+
"logps/chosen": -84.63670349121094,
|
| 663 |
+
"logps/rejected": -89.8626708984375,
|
| 664 |
+
"loss": 0.5584,
|
| 665 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 666 |
+
"rewards/chosen": -0.44350141286849976,
|
| 667 |
+
"rewards/margins": 0.4355877935886383,
|
| 668 |
+
"rewards/rejected": -0.8790891766548157,
|
| 669 |
+
"step": 440
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 15.210970464135022,
|
| 673 |
+
"grad_norm": 1.1012156009674072,
|
| 674 |
+
"learning_rate": 7.269215150626391e-07,
|
| 675 |
+
"logits/chosen": 1.8232038021087646,
|
| 676 |
+
"logits/rejected": 1.8113384246826172,
|
| 677 |
+
"logps/chosen": -95.2444839477539,
|
| 678 |
+
"logps/rejected": -85.72362518310547,
|
| 679 |
+
"loss": 0.5539,
|
| 680 |
+
"rewards/accuracies": 0.875,
|
| 681 |
+
"rewards/chosen": -0.3705037236213684,
|
| 682 |
+
"rewards/margins": 0.5386990308761597,
|
| 683 |
+
"rewards/rejected": -0.9092028737068176,
|
| 684 |
+
"step": 450
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 15.548523206751055,
|
| 688 |
+
"grad_norm": 1.0890499353408813,
|
| 689 |
+
"learning_rate": 6.241254446089942e-07,
|
| 690 |
+
"logits/chosen": 1.6102081537246704,
|
| 691 |
+
"logits/rejected": 1.6902793645858765,
|
| 692 |
+
"logps/chosen": -77.29241943359375,
|
| 693 |
+
"logps/rejected": -87.38616943359375,
|
| 694 |
+
"loss": 0.554,
|
| 695 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 696 |
+
"rewards/chosen": -0.36334335803985596,
|
| 697 |
+
"rewards/margins": 0.41814422607421875,
|
| 698 |
+
"rewards/rejected": -0.7814875841140747,
|
| 699 |
+
"step": 460
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 15.886075949367088,
|
| 703 |
+
"grad_norm": 1.1587886810302734,
|
| 704 |
+
"learning_rate": 5.281219022030423e-07,
|
| 705 |
+
"logits/chosen": 1.7049728631973267,
|
| 706 |
+
"logits/rejected": 1.7815492153167725,
|
| 707 |
+
"logps/chosen": -79.66454315185547,
|
| 708 |
+
"logps/rejected": -91.70343017578125,
|
| 709 |
+
"loss": 0.5472,
|
| 710 |
+
"rewards/accuracies": 0.800000011920929,
|
| 711 |
+
"rewards/chosen": -0.3898239731788635,
|
| 712 |
+
"rewards/margins": 0.40187686681747437,
|
| 713 |
+
"rewards/rejected": -0.7917007803916931,
|
| 714 |
+
"step": 470
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 16.223628691983123,
|
| 718 |
+
"grad_norm": 1.5429887771606445,
|
| 719 |
+
"learning_rate": 4.392585159698087e-07,
|
| 720 |
+
"logits/chosen": 1.6508013010025024,
|
| 721 |
+
"logits/rejected": 1.7940822839736938,
|
| 722 |
+
"logps/chosen": -77.51395416259766,
|
| 723 |
+
"logps/rejected": -90.20869445800781,
|
| 724 |
+
"loss": 0.5512,
|
| 725 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 726 |
+
"rewards/chosen": -0.35601454973220825,
|
| 727 |
+
"rewards/margins": 0.3707844018936157,
|
| 728 |
+
"rewards/rejected": -0.7267988920211792,
|
| 729 |
+
"step": 480
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 16.561181434599156,
|
| 733 |
+
"grad_norm": 1.1558414697647095,
|
| 734 |
+
"learning_rate": 3.578570595810274e-07,
|
| 735 |
+
"logits/chosen": 1.6670711040496826,
|
| 736 |
+
"logits/rejected": 1.6244487762451172,
|
| 737 |
+
"logps/chosen": -101.91804504394531,
|
| 738 |
+
"logps/rejected": -91.96507263183594,
|
| 739 |
+
"loss": 0.5452,
|
| 740 |
+
"rewards/accuracies": 0.824999988079071,
|
| 741 |
+
"rewards/chosen": -0.40192681550979614,
|
| 742 |
+
"rewards/margins": 0.44803065061569214,
|
| 743 |
+
"rewards/rejected": -0.8499574661254883,
|
| 744 |
+
"step": 490
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 16.89873417721519,
|
| 748 |
+
"grad_norm": 1.1151753664016724,
|
| 749 |
+
"learning_rate": 2.8421228711503127e-07,
|
| 750 |
+
"logits/chosen": 1.7409915924072266,
|
| 751 |
+
"logits/rejected": 1.8301231861114502,
|
| 752 |
+
"logps/chosen": -71.89210510253906,
|
| 753 |
+
"logps/rejected": -90.07672119140625,
|
| 754 |
+
"loss": 0.5423,
|
| 755 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 756 |
+
"rewards/chosen": -0.4172780513763428,
|
| 757 |
+
"rewards/margins": 0.394390344619751,
|
| 758 |
+
"rewards/rejected": -0.8116683959960938,
|
| 759 |
+
"step": 500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 17.236286919831223,
|
| 763 |
+
"grad_norm": 1.1430857181549072,
|
| 764 |
+
"learning_rate": 2.1859086575439225e-07,
|
| 765 |
+
"logits/chosen": 1.668222188949585,
|
| 766 |
+
"logits/rejected": 1.7431071996688843,
|
| 767 |
+
"logps/chosen": -80.20066833496094,
|
| 768 |
+
"logps/rejected": -88.21453094482422,
|
| 769 |
+
"loss": 0.5312,
|
| 770 |
+
"rewards/accuracies": 0.8125,
|
| 771 |
+
"rewards/chosen": -0.3836023807525635,
|
| 772 |
+
"rewards/margins": 0.41132551431655884,
|
| 773 |
+
"rewards/rejected": -0.7949277758598328,
|
| 774 |
+
"step": 510
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 17.573839662447256,
|
| 778 |
+
"grad_norm": 1.3264650106430054,
|
| 779 |
+
"learning_rate": 1.6123041018599766e-07,
|
| 780 |
+
"logits/chosen": 1.6724201440811157,
|
| 781 |
+
"logits/rejected": 1.782766580581665,
|
| 782 |
+
"logps/chosen": -87.28868103027344,
|
| 783 |
+
"logps/rejected": -109.66194152832031,
|
| 784 |
+
"loss": 0.5529,
|
| 785 |
+
"rewards/accuracies": 0.800000011920929,
|
| 786 |
+
"rewards/chosen": -0.4659019112586975,
|
| 787 |
+
"rewards/margins": 0.3525821268558502,
|
| 788 |
+
"rewards/rejected": -0.8184840083122253,
|
| 789 |
+
"step": 520
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 17.911392405063292,
|
| 793 |
+
"grad_norm": 1.2674906253814697,
|
| 794 |
+
"learning_rate": 1.1233862220001168e-07,
|
| 795 |
+
"logits/chosen": 1.6698293685913086,
|
| 796 |
+
"logits/rejected": 1.696459412574768,
|
| 797 |
+
"logps/chosen": -95.00108337402344,
|
| 798 |
+
"logps/rejected": -84.9312973022461,
|
| 799 |
+
"loss": 0.5565,
|
| 800 |
+
"rewards/accuracies": 0.8125,
|
| 801 |
+
"rewards/chosen": -0.3677830696105957,
|
| 802 |
+
"rewards/margins": 0.4486306607723236,
|
| 803 |
+
"rewards/rejected": -0.8164137005805969,
|
| 804 |
+
"step": 530
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 18.248945147679326,
|
| 808 |
+
"grad_norm": 1.1495198011398315,
|
| 809 |
+
"learning_rate": 7.209253860320897e-08,
|
| 810 |
+
"logits/chosen": 1.7104814052581787,
|
| 811 |
+
"logits/rejected": 1.7387645244598389,
|
| 812 |
+
"logps/chosen": -84.37834167480469,
|
| 813 |
+
"logps/rejected": -82.36712646484375,
|
| 814 |
+
"loss": 0.5475,
|
| 815 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 816 |
+
"rewards/chosen": -0.4061828553676605,
|
| 817 |
+
"rewards/margins": 0.3533913493156433,
|
| 818 |
+
"rewards/rejected": -0.7595741748809814,
|
| 819 |
+
"step": 540
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 18.58649789029536,
|
| 823 |
+
"grad_norm": 1.0989700555801392,
|
| 824 |
+
"learning_rate": 4.063789016999331e-08,
|
| 825 |
+
"logits/chosen": 1.6560907363891602,
|
| 826 |
+
"logits/rejected": 1.7722400426864624,
|
| 827 |
+
"logps/chosen": -80.30384826660156,
|
| 828 |
+
"logps/rejected": -84.69402313232422,
|
| 829 |
+
"loss": 0.5462,
|
| 830 |
+
"rewards/accuracies": 0.8125,
|
| 831 |
+
"rewards/chosen": -0.3671244978904724,
|
| 832 |
+
"rewards/margins": 0.41629084944725037,
|
| 833 |
+
"rewards/rejected": -0.7834154367446899,
|
| 834 |
+
"step": 550
|
| 835 |
+
}
|
| 836 |
+
],
|
| 837 |
+
"logging_steps": 10,
|
| 838 |
+
"max_steps": 580,
|
| 839 |
+
"num_input_tokens_seen": 0,
|
| 840 |
+
"num_train_epochs": 20,
|
| 841 |
+
"save_steps": 50,
|
| 842 |
+
"stateful_callbacks": {
|
| 843 |
+
"TrainerControl": {
|
| 844 |
+
"args": {
|
| 845 |
+
"should_epoch_stop": false,
|
| 846 |
+
"should_evaluate": false,
|
| 847 |
+
"should_log": false,
|
| 848 |
+
"should_save": true,
|
| 849 |
+
"should_training_stop": false
|
| 850 |
+
},
|
| 851 |
+
"attributes": {}
|
| 852 |
+
}
|
| 853 |
+
},
|
| 854 |
+
"total_flos": 1.8891190313156608e+18,
|
| 855 |
+
"train_batch_size": 1,
|
| 856 |
+
"trial_name": null,
|
| 857 |
+
"trial_params": null
|
| 858 |
+
}
|
Power_Area/checkpoint-580/README.md
ADDED
|
@@ -0,0 +1,202 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: deepseek-ai/deepseek-coder-6.7b-instruct
|
| 3 |
+
library_name: peft
|
| 4 |
+
---
|
| 5 |
+
|
| 6 |
+
# Model Card for Model ID
|
| 7 |
+
|
| 8 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
## Model Details
|
| 13 |
+
|
| 14 |
+
### Model Description
|
| 15 |
+
|
| 16 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- **Developed by:** [More Information Needed]
|
| 21 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 22 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 23 |
+
- **Model type:** [More Information Needed]
|
| 24 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 25 |
+
- **License:** [More Information Needed]
|
| 26 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 27 |
+
|
| 28 |
+
### Model Sources [optional]
|
| 29 |
+
|
| 30 |
+
<!-- Provide the basic links for the model. -->
|
| 31 |
+
|
| 32 |
+
- **Repository:** [More Information Needed]
|
| 33 |
+
- **Paper [optional]:** [More Information Needed]
|
| 34 |
+
- **Demo [optional]:** [More Information Needed]
|
| 35 |
+
|
| 36 |
+
## Uses
|
| 37 |
+
|
| 38 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 39 |
+
|
| 40 |
+
### Direct Use
|
| 41 |
+
|
| 42 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 43 |
+
|
| 44 |
+
[More Information Needed]
|
| 45 |
+
|
| 46 |
+
### Downstream Use [optional]
|
| 47 |
+
|
| 48 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 49 |
+
|
| 50 |
+
[More Information Needed]
|
| 51 |
+
|
| 52 |
+
### Out-of-Scope Use
|
| 53 |
+
|
| 54 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 55 |
+
|
| 56 |
+
[More Information Needed]
|
| 57 |
+
|
| 58 |
+
## Bias, Risks, and Limitations
|
| 59 |
+
|
| 60 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 61 |
+
|
| 62 |
+
[More Information Needed]
|
| 63 |
+
|
| 64 |
+
### Recommendations
|
| 65 |
+
|
| 66 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 67 |
+
|
| 68 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 69 |
+
|
| 70 |
+
## How to Get Started with the Model
|
| 71 |
+
|
| 72 |
+
Use the code below to get started with the model.
|
| 73 |
+
|
| 74 |
+
[More Information Needed]
|
| 75 |
+
|
| 76 |
+
## Training Details
|
| 77 |
+
|
| 78 |
+
### Training Data
|
| 79 |
+
|
| 80 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 81 |
+
|
| 82 |
+
[More Information Needed]
|
| 83 |
+
|
| 84 |
+
### Training Procedure
|
| 85 |
+
|
| 86 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 87 |
+
|
| 88 |
+
#### Preprocessing [optional]
|
| 89 |
+
|
| 90 |
+
[More Information Needed]
|
| 91 |
+
|
| 92 |
+
|
| 93 |
+
#### Training Hyperparameters
|
| 94 |
+
|
| 95 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 96 |
+
|
| 97 |
+
#### Speeds, Sizes, Times [optional]
|
| 98 |
+
|
| 99 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 100 |
+
|
| 101 |
+
[More Information Needed]
|
| 102 |
+
|
| 103 |
+
## Evaluation
|
| 104 |
+
|
| 105 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 106 |
+
|
| 107 |
+
### Testing Data, Factors & Metrics
|
| 108 |
+
|
| 109 |
+
#### Testing Data
|
| 110 |
+
|
| 111 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 112 |
+
|
| 113 |
+
[More Information Needed]
|
| 114 |
+
|
| 115 |
+
#### Factors
|
| 116 |
+
|
| 117 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 118 |
+
|
| 119 |
+
[More Information Needed]
|
| 120 |
+
|
| 121 |
+
#### Metrics
|
| 122 |
+
|
| 123 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 124 |
+
|
| 125 |
+
[More Information Needed]
|
| 126 |
+
|
| 127 |
+
### Results
|
| 128 |
+
|
| 129 |
+
[More Information Needed]
|
| 130 |
+
|
| 131 |
+
#### Summary
|
| 132 |
+
|
| 133 |
+
|
| 134 |
+
|
| 135 |
+
## Model Examination [optional]
|
| 136 |
+
|
| 137 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 138 |
+
|
| 139 |
+
[More Information Needed]
|
| 140 |
+
|
| 141 |
+
## Environmental Impact
|
| 142 |
+
|
| 143 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 144 |
+
|
| 145 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 146 |
+
|
| 147 |
+
- **Hardware Type:** [More Information Needed]
|
| 148 |
+
- **Hours used:** [More Information Needed]
|
| 149 |
+
- **Cloud Provider:** [More Information Needed]
|
| 150 |
+
- **Compute Region:** [More Information Needed]
|
| 151 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 152 |
+
|
| 153 |
+
## Technical Specifications [optional]
|
| 154 |
+
|
| 155 |
+
### Model Architecture and Objective
|
| 156 |
+
|
| 157 |
+
[More Information Needed]
|
| 158 |
+
|
| 159 |
+
### Compute Infrastructure
|
| 160 |
+
|
| 161 |
+
[More Information Needed]
|
| 162 |
+
|
| 163 |
+
#### Hardware
|
| 164 |
+
|
| 165 |
+
[More Information Needed]
|
| 166 |
+
|
| 167 |
+
#### Software
|
| 168 |
+
|
| 169 |
+
[More Information Needed]
|
| 170 |
+
|
| 171 |
+
## Citation [optional]
|
| 172 |
+
|
| 173 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 174 |
+
|
| 175 |
+
**BibTeX:**
|
| 176 |
+
|
| 177 |
+
[More Information Needed]
|
| 178 |
+
|
| 179 |
+
**APA:**
|
| 180 |
+
|
| 181 |
+
[More Information Needed]
|
| 182 |
+
|
| 183 |
+
## Glossary [optional]
|
| 184 |
+
|
| 185 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 186 |
+
|
| 187 |
+
[More Information Needed]
|
| 188 |
+
|
| 189 |
+
## More Information [optional]
|
| 190 |
+
|
| 191 |
+
[More Information Needed]
|
| 192 |
+
|
| 193 |
+
## Model Card Authors [optional]
|
| 194 |
+
|
| 195 |
+
[More Information Needed]
|
| 196 |
+
|
| 197 |
+
## Model Card Contact
|
| 198 |
+
|
| 199 |
+
[More Information Needed]
|
| 200 |
+
### Framework versions
|
| 201 |
+
|
| 202 |
+
- PEFT 0.12.0
|
Power_Area/checkpoint-580/adapter_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "deepseek-ai/deepseek-coder-6.7b-instruct",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 16,
|
| 14 |
+
"lora_dropout": 0.0,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 8,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": [
|
| 23 |
+
"q_proj",
|
| 24 |
+
"up_proj",
|
| 25 |
+
"v_proj",
|
| 26 |
+
"gate_proj",
|
| 27 |
+
"o_proj",
|
| 28 |
+
"k_proj",
|
| 29 |
+
"down_proj"
|
| 30 |
+
],
|
| 31 |
+
"task_type": "CAUSAL_LM",
|
| 32 |
+
"use_dora": false,
|
| 33 |
+
"use_rslora": false
|
| 34 |
+
}
|
Power_Area/checkpoint-580/special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "<|EOT|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
Power_Area/checkpoint-580/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
Power_Area/checkpoint-580/tokenizer_config.json
ADDED
|
@@ -0,0 +1,196 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"add_prefix_space": null,
|
| 5 |
+
"added_tokens_decoder": {
|
| 6 |
+
"32000": {
|
| 7 |
+
"content": "õ",
|
| 8 |
+
"lstrip": false,
|
| 9 |
+
"normalized": true,
|
| 10 |
+
"rstrip": false,
|
| 11 |
+
"single_word": false,
|
| 12 |
+
"special": false
|
| 13 |
+
},
|
| 14 |
+
"32001": {
|
| 15 |
+
"content": "÷",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false,
|
| 20 |
+
"special": false
|
| 21 |
+
},
|
| 22 |
+
"32002": {
|
| 23 |
+
"content": "Á",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": true,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"special": false
|
| 29 |
+
},
|
| 30 |
+
"32003": {
|
| 31 |
+
"content": "ý",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false,
|
| 36 |
+
"special": false
|
| 37 |
+
},
|
| 38 |
+
"32004": {
|
| 39 |
+
"content": "À",
|
| 40 |
+
"lstrip": false,
|
| 41 |
+
"normalized": true,
|
| 42 |
+
"rstrip": false,
|
| 43 |
+
"single_word": false,
|
| 44 |
+
"special": false
|
| 45 |
+
},
|
| 46 |
+
"32005": {
|
| 47 |
+
"content": "ÿ",
|
| 48 |
+
"lstrip": false,
|
| 49 |
+
"normalized": true,
|
| 50 |
+
"rstrip": false,
|
| 51 |
+
"single_word": false,
|
| 52 |
+
"special": false
|
| 53 |
+
},
|
| 54 |
+
"32006": {
|
| 55 |
+
"content": "ø",
|
| 56 |
+
"lstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
+
"rstrip": false,
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"special": false
|
| 61 |
+
},
|
| 62 |
+
"32007": {
|
| 63 |
+
"content": "ú",
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"normalized": true,
|
| 66 |
+
"rstrip": false,
|
| 67 |
+
"single_word": false,
|
| 68 |
+
"special": false
|
| 69 |
+
},
|
| 70 |
+
"32008": {
|
| 71 |
+
"content": "þ",
|
| 72 |
+
"lstrip": false,
|
| 73 |
+
"normalized": true,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"single_word": false,
|
| 76 |
+
"special": false
|
| 77 |
+
},
|
| 78 |
+
"32009": {
|
| 79 |
+
"content": "ü",
|
| 80 |
+
"lstrip": false,
|
| 81 |
+
"normalized": true,
|
| 82 |
+
"rstrip": false,
|
| 83 |
+
"single_word": false,
|
| 84 |
+
"special": false
|
| 85 |
+
},
|
| 86 |
+
"32010": {
|
| 87 |
+
"content": "ù",
|
| 88 |
+
"lstrip": false,
|
| 89 |
+
"normalized": true,
|
| 90 |
+
"rstrip": false,
|
| 91 |
+
"single_word": false,
|
| 92 |
+
"special": false
|
| 93 |
+
},
|
| 94 |
+
"32011": {
|
| 95 |
+
"content": "ö",
|
| 96 |
+
"lstrip": false,
|
| 97 |
+
"normalized": true,
|
| 98 |
+
"rstrip": false,
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"special": false
|
| 101 |
+
},
|
| 102 |
+
"32012": {
|
| 103 |
+
"content": "û",
|
| 104 |
+
"lstrip": false,
|
| 105 |
+
"normalized": true,
|
| 106 |
+
"rstrip": false,
|
| 107 |
+
"single_word": false,
|
| 108 |
+
"special": false
|
| 109 |
+
},
|
| 110 |
+
"32013": {
|
| 111 |
+
"content": "<｜begin▁of▁sentence｜>",
|
| 112 |
+
"lstrip": false,
|
| 113 |
+
"normalized": true,
|
| 114 |
+
"rstrip": false,
|
| 115 |
+
"single_word": false,
|
| 116 |
+
"special": true
|
| 117 |
+
},
|
| 118 |
+
"32014": {
|
| 119 |
+
"content": "<｜end▁of▁sentence｜>",
|
| 120 |
+
"lstrip": false,
|
| 121 |
+
"normalized": true,
|
| 122 |
+
"rstrip": false,
|
| 123 |
+
"single_word": false,
|
| 124 |
+
"special": true
|
| 125 |
+
},
|
| 126 |
+
"32015": {
|
| 127 |
+
"content": "<｜fim▁hole｜>",
|
| 128 |
+
"lstrip": false,
|
| 129 |
+
"normalized": true,
|
| 130 |
+
"rstrip": false,
|
| 131 |
+
"single_word": false,
|
| 132 |
+
"special": false
|
| 133 |
+
},
|
| 134 |
+
"32016": {
|
| 135 |
+
"content": "<｜fim▁begin｜>",
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"normalized": true,
|
| 138 |
+
"rstrip": false,
|
| 139 |
+
"single_word": false,
|
| 140 |
+
"special": false
|
| 141 |
+
},
|
| 142 |
+
"32017": {
|
| 143 |
+
"content": "<｜fim▁end｜>",
|
| 144 |
+
"lstrip": false,
|
| 145 |
+
"normalized": true,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"single_word": false,
|
| 148 |
+
"special": false
|
| 149 |
+
},
|
| 150 |
+
"32018": {
|
| 151 |
+
"content": "<pad>",
|
| 152 |
+
"lstrip": false,
|
| 153 |
+
"normalized": true,
|
| 154 |
+
"rstrip": false,
|
| 155 |
+
"single_word": false,
|
| 156 |
+
"special": false
|
| 157 |
+
},
|
| 158 |
+
"32019": {
|
| 159 |
+
"content": "<|User|>",
|
| 160 |
+
"lstrip": false,
|
| 161 |
+
"normalized": true,
|
| 162 |
+
"rstrip": false,
|
| 163 |
+
"single_word": false,
|
| 164 |
+
"special": false
|
| 165 |
+
},
|
| 166 |
+
"32020": {
|
| 167 |
+
"content": "<|Assistant|>",
|
| 168 |
+
"lstrip": false,
|
| 169 |
+
"normalized": true,
|
| 170 |
+
"rstrip": false,
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"special": false
|
| 173 |
+
},
|
| 174 |
+
"32021": {
|
| 175 |
+
"content": "<|EOT|>",
|
| 176 |
+
"lstrip": false,
|
| 177 |
+
"normalized": true,
|
| 178 |
+
"rstrip": false,
|
| 179 |
+
"single_word": false,
|
| 180 |
+
"special": true
|
| 181 |
+
}
|
| 182 |
+
},
|
| 183 |
+
"bos_token": "<｜begin▁of▁sentence｜>",
|
| 184 |
+
"chat_template": "{{ '<｜begin▁of▁sentence｜>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message + '\n\n' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'User: ' + content + '\n\nAssistant:' }}{% elif message['role'] == 'assistant' %}{{ content + '<|EOT|>' }}{% endif %}{% endfor %}",
|
| 185 |
+
"clean_up_tokenization_spaces": false,
|
| 186 |
+
"eos_token": "<|EOT|>",
|
| 187 |
+
"legacy": true,
|
| 188 |
+
"model_max_length": 16384,
|
| 189 |
+
"pad_token": "<｜end▁of▁sentence｜>",
|
| 190 |
+
"padding_side": "right",
|
| 191 |
+
"sp_model_kwargs": {},
|
| 192 |
+
"split_special_tokens": false,
|
| 193 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 194 |
+
"unk_token": null,
|
| 195 |
+
"use_default_system_prompt": false
|
| 196 |
+
}
|
Power_Area/checkpoint-580/trainer_state.json
ADDED
|
@@ -0,0 +1,903 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 19.59915611814346,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 580,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33755274261603374,
|
| 13 |
+
"grad_norm": 0.4396141469478607,
|
| 14 |
+
"learning_rate": 8.620689655172415e-07,
|
| 15 |
+
"logits/chosen": 1.6453087329864502,
|
| 16 |
+
"logits/rejected": 1.694819450378418,
|
| 17 |
+
"logps/chosen": -74.5937728881836,
|
| 18 |
+
"logps/rejected": -83.19783782958984,
|
| 19 |
+
"loss": 0.6928,
|
| 20 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 21 |
+
"rewards/chosen": 0.003385844174772501,
|
| 22 |
+
"rewards/margins": 0.004794469103217125,
|
| 23 |
+
"rewards/rejected": -0.0014086246956139803,
|
| 24 |
+
"step": 10
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.6751054852320675,
|
| 28 |
+
"grad_norm": 3.18404483795166,
|
| 29 |
+
"learning_rate": 1.724137931034483e-06,
|
| 30 |
+
"logits/chosen": 1.7945035696029663,
|
| 31 |
+
"logits/rejected": 1.8347476720809937,
|
| 32 |
+
"logps/chosen": -95.46636199951172,
|
| 33 |
+
"logps/rejected": -101.22709655761719,
|
| 34 |
+
"loss": 0.6933,
|
| 35 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 36 |
+
"rewards/chosen": -0.0005593777750618756,
|
| 37 |
+
"rewards/margins": -0.002013001125305891,
|
| 38 |
+
"rewards/rejected": 0.0014536241069436073,
|
| 39 |
+
"step": 20
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.0126582278481013,
|
| 43 |
+
"grad_norm": 0.48596081137657166,
|
| 44 |
+
"learning_rate": 2.5862068965517246e-06,
|
| 45 |
+
"logits/chosen": 1.774155616760254,
|
| 46 |
+
"logits/rejected": 1.8374344110488892,
|
| 47 |
+
"logps/chosen": -82.01265716552734,
|
| 48 |
+
"logps/rejected": -84.23635864257812,
|
| 49 |
+
"loss": 0.6948,
|
| 50 |
+
"rewards/accuracies": 0.44999998807907104,
|
| 51 |
+
"rewards/chosen": -0.0031326995231211185,
|
| 52 |
+
"rewards/margins": -0.00463916826993227,
|
| 53 |
+
"rewards/rejected": 0.0015064675826579332,
|
| 54 |
+
"step": 30
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"epoch": 1.350210970464135,
|
| 58 |
+
"grad_norm": 0.5144609808921814,
|
| 59 |
+
"learning_rate": 3.448275862068966e-06,
|
| 60 |
+
"logits/chosen": 1.838865876197815,
|
| 61 |
+
"logits/rejected": 1.9505430459976196,
|
| 62 |
+
"logps/chosen": -73.50071716308594,
|
| 63 |
+
"logps/rejected": -88.8648452758789,
|
| 64 |
+
"loss": 0.6928,
|
| 65 |
+
"rewards/accuracies": 0.42500001192092896,
|
| 66 |
+
"rewards/chosen": -0.0035957477521151304,
|
| 67 |
+
"rewards/margins": -0.008830643258988857,
|
| 68 |
+
"rewards/rejected": 0.005234894808381796,
|
| 69 |
+
"step": 40
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 1.6877637130801688,
|
| 73 |
+
"grad_norm": 0.48295095562934875,
|
| 74 |
+
"learning_rate": 4.310344827586207e-06,
|
| 75 |
+
"logits/chosen": 1.8197529315948486,
|
| 76 |
+
"logits/rejected": 1.8459796905517578,
|
| 77 |
+
"logps/chosen": -83.36590576171875,
|
| 78 |
+
"logps/rejected": -70.26930236816406,
|
| 79 |
+
"loss": 0.6929,
|
| 80 |
+
"rewards/accuracies": 0.4749999940395355,
|
| 81 |
+
"rewards/chosen": -0.0030026868917047977,
|
| 82 |
+
"rewards/margins": -0.006082554347813129,
|
| 83 |
+
"rewards/rejected": 0.003079867223277688,
|
| 84 |
+
"step": 50
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 2.0464135021097047,
|
| 88 |
+
"grad_norm": 0.5616092085838318,
|
| 89 |
+
"learning_rate": 4.999818897894192e-06,
|
| 90 |
+
"logits/chosen": 1.7525272369384766,
|
| 91 |
+
"logits/rejected": 1.8092533349990845,
|
| 92 |
+
"logps/chosen": -82.01802062988281,
|
| 93 |
+
"logps/rejected": -78.39723205566406,
|
| 94 |
+
"loss": 0.6949,
|
| 95 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 96 |
+
"rewards/chosen": -0.0010920714121311903,
|
| 97 |
+
"rewards/margins": -0.0016235255170613527,
|
| 98 |
+
"rewards/rejected": 0.0005314538720995188,
|
| 99 |
+
"step": 60
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 2.3839662447257384,
|
| 103 |
+
"grad_norm": 0.5237122774124146,
|
| 104 |
+
"learning_rate": 4.9934830787948756e-06,
|
| 105 |
+
"logits/chosen": 1.754880666732788,
|
| 106 |
+
"logits/rejected": 1.8100305795669556,
|
| 107 |
+
"logps/chosen": -89.62864685058594,
|
| 108 |
+
"logps/rejected": -88.30036926269531,
|
| 109 |
+
"loss": 0.694,
|
| 110 |
+
"rewards/accuracies": 0.5,
|
| 111 |
+
"rewards/chosen": -0.002314353361725807,
|
| 112 |
+
"rewards/margins": -0.001038494287058711,
|
| 113 |
+
"rewards/rejected": -0.0012758590746670961,
|
| 114 |
+
"step": 70
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"epoch": 2.721518987341772,
|
| 118 |
+
"grad_norm": 0.507128119468689,
|
| 119 |
+
"learning_rate": 4.978118375700895e-06,
|
| 120 |
+
"logits/chosen": 1.7501789331436157,
|
| 121 |
+
"logits/rejected": 1.6666221618652344,
|
| 122 |
+
"logps/chosen": -94.74919128417969,
|
| 123 |
+
"logps/rejected": -74.9794692993164,
|
| 124 |
+
"loss": 0.6922,
|
| 125 |
+
"rewards/accuracies": 0.4625000059604645,
|
| 126 |
+
"rewards/chosen": 0.00475720502436161,
|
| 127 |
+
"rewards/margins": 0.01054429542273283,
|
| 128 |
+
"rewards/rejected": -0.005787090864032507,
|
| 129 |
+
"step": 80
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 3.059071729957806,
|
| 133 |
+
"grad_norm": 0.8151038885116577,
|
| 134 |
+
"learning_rate": 4.953780424089803e-06,
|
| 135 |
+
"logits/chosen": 1.7203710079193115,
|
| 136 |
+
"logits/rejected": 1.7376699447631836,
|
| 137 |
+
"logps/chosen": -76.8824691772461,
|
| 138 |
+
"logps/rejected": -84.74555206298828,
|
| 139 |
+
"loss": 0.6925,
|
| 140 |
+
"rewards/accuracies": 0.5375000238418579,
|
| 141 |
+
"rewards/chosen": 0.01064519863575697,
|
| 142 |
+
"rewards/margins": 0.012716365046799183,
|
| 143 |
+
"rewards/rejected": -0.0020711664110422134,
|
| 144 |
+
"step": 90
|
| 145 |
+
},
|
| 146 |
+
{
|
| 147 |
+
"epoch": 3.3966244725738397,
|
| 148 |
+
"grad_norm": 0.5476706027984619,
|
| 149 |
+
"learning_rate": 4.920557351506409e-06,
|
| 150 |
+
"logits/chosen": 1.7857105731964111,
|
| 151 |
+
"logits/rejected": 1.7341340780258179,
|
| 152 |
+
"logps/chosen": -88.39775085449219,
|
| 153 |
+
"logps/rejected": -80.00445556640625,
|
| 154 |
+
"loss": 0.6893,
|
| 155 |
+
"rewards/accuracies": 0.612500011920929,
|
| 156 |
+
"rewards/chosen": 0.0052363635040819645,
|
| 157 |
+
"rewards/margins": 0.016881367191672325,
|
| 158 |
+
"rewards/rejected": -0.011645001359283924,
|
| 159 |
+
"step": 100
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 3.7341772151898733,
|
| 163 |
+
"grad_norm": 0.6562405824661255,
|
| 164 |
+
"learning_rate": 4.878569458453592e-06,
|
| 165 |
+
"logits/chosen": 1.737647294998169,
|
| 166 |
+
"logits/rejected": 1.7781591415405273,
|
| 167 |
+
"logps/chosen": -92.72380065917969,
|
| 168 |
+
"logps/rejected": -85.51634216308594,
|
| 169 |
+
"loss": 0.6899,
|
| 170 |
+
"rewards/accuracies": 0.512499988079071,
|
| 171 |
+
"rewards/chosen": -0.010819707065820694,
|
| 172 |
+
"rewards/margins": -0.0005886269500479102,
|
| 173 |
+
"rewards/rejected": -0.010231079533696175,
|
| 174 |
+
"step": 110
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 4.071729957805907,
|
| 178 |
+
"grad_norm": 0.6393210291862488,
|
| 179 |
+
"learning_rate": 4.827968782785062e-06,
|
| 180 |
+
"logits/chosen": 1.7890704870224,
|
| 181 |
+
"logits/rejected": 1.8340994119644165,
|
| 182 |
+
"logps/chosen": -87.615478515625,
|
| 183 |
+
"logps/rejected": -108.13908386230469,
|
| 184 |
+
"loss": 0.6872,
|
| 185 |
+
"rewards/accuracies": 0.5249999761581421,
|
| 186 |
+
"rewards/chosen": 0.002250433200970292,
|
| 187 |
+
"rewards/margins": 0.012117428705096245,
|
| 188 |
+
"rewards/rejected": -0.009866995736956596,
|
| 189 |
+
"step": 120
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 4.409282700421941,
|
| 193 |
+
"grad_norm": 0.7390326261520386,
|
| 194 |
+
"learning_rate": 4.7689385491773934e-06,
|
| 195 |
+
"logits/chosen": 1.7916072607040405,
|
| 196 |
+
"logits/rejected": 1.787153959274292,
|
| 197 |
+
"logps/chosen": -84.11034393310547,
|
| 198 |
+
"logps/rejected": -76.81166076660156,
|
| 199 |
+
"loss": 0.6844,
|
| 200 |
+
"rewards/accuracies": 0.5625,
|
| 201 |
+
"rewards/chosen": -0.003190569579601288,
|
| 202 |
+
"rewards/margins": 0.015628555789589882,
|
| 203 |
+
"rewards/rejected": -0.01881912164390087,
|
| 204 |
+
"step": 130
|
| 205 |
+
},
|
| 206 |
+
{
|
| 207 |
+
"epoch": 4.746835443037975,
|
| 208 |
+
"grad_norm": 0.7888330817222595,
|
| 209 |
+
"learning_rate": 4.70169250567482e-06,
|
| 210 |
+
"logits/chosen": 1.8455331325531006,
|
| 211 |
+
"logits/rejected": 1.8137515783309937,
|
| 212 |
+
"logps/chosen": -78.94912719726562,
|
| 213 |
+
"logps/rejected": -76.1368637084961,
|
| 214 |
+
"loss": 0.6819,
|
| 215 |
+
"rewards/accuracies": 0.625,
|
| 216 |
+
"rewards/chosen": -0.012986091896891594,
|
| 217 |
+
"rewards/margins": 0.015167826786637306,
|
| 218 |
+
"rewards/rejected": -0.02815392054617405,
|
| 219 |
+
"step": 140
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 5.084388185654008,
|
| 223 |
+
"grad_norm": 0.7248090505599976,
|
| 224 |
+
"learning_rate": 4.626474149709127e-06,
|
| 225 |
+
"logits/chosen": 1.6686553955078125,
|
| 226 |
+
"logits/rejected": 1.6654260158538818,
|
| 227 |
+
"logps/chosen": -78.25769805908203,
|
| 228 |
+
"logps/rejected": -71.3498306274414,
|
| 229 |
+
"loss": 0.677,
|
| 230 |
+
"rewards/accuracies": 0.612500011920929,
|
| 231 |
+
"rewards/chosen": -0.0182911679148674,
|
| 232 |
+
"rewards/margins": 0.02633112668991089,
|
| 233 |
+
"rewards/rejected": -0.04462229460477829,
|
| 234 |
+
"step": 150
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 5.421940928270042,
|
| 238 |
+
"grad_norm": 0.7906918525695801,
|
| 239 |
+
"learning_rate": 4.54355584639723e-06,
|
| 240 |
+
"logits/chosen": 1.8054498434066772,
|
| 241 |
+
"logits/rejected": 1.751422643661499,
|
| 242 |
+
"logps/chosen": -91.65776824951172,
|
| 243 |
+
"logps/rejected": -68.41027069091797,
|
| 244 |
+
"loss": 0.6741,
|
| 245 |
+
"rewards/accuracies": 0.574999988079071,
|
| 246 |
+
"rewards/chosen": -0.04313550516963005,
|
| 247 |
+
"rewards/margins": 0.017568334937095642,
|
| 248 |
+
"rewards/rejected": -0.060703836381435394,
|
| 249 |
+
"step": 160
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 5.759493670886076,
|
| 253 |
+
"grad_norm": 0.8152453303337097,
|
| 254 |
+
"learning_rate": 4.45323784230908e-06,
|
| 255 |
+
"logits/chosen": 1.742419958114624,
|
| 256 |
+
"logits/rejected": 1.9456249475479126,
|
| 257 |
+
"logps/chosen": -80.52605438232422,
|
| 258 |
+
"logps/rejected": -117.02473449707031,
|
| 259 |
+
"loss": 0.67,
|
| 260 |
+
"rewards/accuracies": 0.5874999761581421,
|
| 261 |
+
"rewards/chosen": -0.030041133984923363,
|
| 262 |
+
"rewards/margins": 0.03393586724996567,
|
| 263 |
+
"rewards/rejected": -0.06397700309753418,
|
| 264 |
+
"step": 170
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 6.09704641350211,
|
| 268 |
+
"grad_norm": 0.7848192453384399,
|
| 269 |
+
"learning_rate": 4.355847178277025e-06,
|
| 270 |
+
"logits/chosen": 1.836090087890625,
|
| 271 |
+
"logits/rejected": 2.0285377502441406,
|
| 272 |
+
"logps/chosen": -72.87449645996094,
|
| 273 |
+
"logps/rejected": -101.46552276611328,
|
| 274 |
+
"loss": 0.6659,
|
| 275 |
+
"rewards/accuracies": 0.6000000238418579,
|
| 276 |
+
"rewards/chosen": -0.04543738812208176,
|
| 277 |
+
"rewards/margins": 0.0431094653904438,
|
| 278 |
+
"rewards/rejected": -0.08854684978723526,
|
| 279 |
+
"step": 180
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 6.434599156118144,
|
| 283 |
+
"grad_norm": 0.8349910378456116,
|
| 284 |
+
"learning_rate": 4.2517365051833564e-06,
|
| 285 |
+
"logits/chosen": 1.7459189891815186,
|
| 286 |
+
"logits/rejected": 1.8324615955352783,
|
| 287 |
+
"logps/chosen": -72.0348892211914,
|
| 288 |
+
"logps/rejected": -86.13719940185547,
|
| 289 |
+
"loss": 0.6555,
|
| 290 |
+
"rewards/accuracies": 0.6499999761581421,
|
| 291 |
+
"rewards/chosen": -0.04952271655201912,
|
| 292 |
+
"rewards/margins": 0.07018387317657471,
|
| 293 |
+
"rewards/rejected": -0.11970658600330353,
|
| 294 |
+
"step": 190
|
| 295 |
+
},
|
| 296 |
+
{
|
| 297 |
+
"epoch": 6.772151898734177,
|
| 298 |
+
"grad_norm": 0.9766960144042969,
|
| 299 |
+
"learning_rate": 4.141282807014034e-06,
|
| 300 |
+
"logits/chosen": 1.7785131931304932,
|
| 301 |
+
"logits/rejected": 1.8624244928359985,
|
| 302 |
+
"logps/chosen": -91.82891845703125,
|
| 303 |
+
"logps/rejected": -102.28694915771484,
|
| 304 |
+
"loss": 0.6465,
|
| 305 |
+
"rewards/accuracies": 0.6875,
|
| 306 |
+
"rewards/chosen": -0.04159725084900856,
|
| 307 |
+
"rewards/margins": 0.09511855244636536,
|
| 308 |
+
"rewards/rejected": -0.1367158144712448,
|
| 309 |
+
"step": 200
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 7.109704641350211,
|
| 313 |
+
"grad_norm": 0.9714512228965759,
|
| 314 |
+
"learning_rate": 4.024886035802432e-06,
|
| 315 |
+
"logits/chosen": 1.756864309310913,
|
| 316 |
+
"logits/rejected": 1.7497355937957764,
|
| 317 |
+
"logps/chosen": -82.28770446777344,
|
| 318 |
+
"logps/rejected": -72.7796859741211,
|
| 319 |
+
"loss": 0.6498,
|
| 320 |
+
"rewards/accuracies": 0.8125,
|
| 321 |
+
"rewards/chosen": -0.0668434351682663,
|
| 322 |
+
"rewards/margins": 0.1403656005859375,
|
| 323 |
+
"rewards/rejected": -0.2072090357542038,
|
| 324 |
+
"step": 210
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 7.447257383966245,
|
| 328 |
+
"grad_norm": 0.9135355949401855,
|
| 329 |
+
"learning_rate": 3.9029676634059565e-06,
|
| 330 |
+
"logits/chosen": 1.677150011062622,
|
| 331 |
+
"logits/rejected": 1.7840830087661743,
|
| 332 |
+
"logps/chosen": -78.84297180175781,
|
| 333 |
+
"logps/rejected": -102.04107666015625,
|
| 334 |
+
"loss": 0.6438,
|
| 335 |
+
"rewards/accuracies": 0.75,
|
| 336 |
+
"rewards/chosen": -0.10343215614557266,
|
| 337 |
+
"rewards/margins": 0.15733790397644043,
|
| 338 |
+
"rewards/rejected": -0.2607700526714325,
|
| 339 |
+
"step": 220
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 7.784810126582278,
|
| 343 |
+
"grad_norm": 0.8835084438323975,
|
| 344 |
+
"learning_rate": 3.7759691553595214e-06,
|
| 345 |
+
"logits/chosen": 1.8346344232559204,
|
| 346 |
+
"logits/rejected": 1.838543176651001,
|
| 347 |
+
"logps/chosen": -109.93656921386719,
|
| 348 |
+
"logps/rejected": -73.76078033447266,
|
| 349 |
+
"loss": 0.6279,
|
| 350 |
+
"rewards/accuracies": 0.75,
|
| 351 |
+
"rewards/chosen": -0.08149126917123795,
|
| 352 |
+
"rewards/margins": 0.17928050458431244,
|
| 353 |
+
"rewards/rejected": -0.26077181100845337,
|
| 354 |
+
"step": 230
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 8.122362869198312,
|
| 358 |
+
"grad_norm": 0.9854581952095032,
|
| 359 |
+
"learning_rate": 3.6443503723320837e-06,
|
| 360 |
+
"logits/chosen": 1.7367273569107056,
|
| 361 |
+
"logits/rejected": 1.723976492881775,
|
| 362 |
+
"logps/chosen": -80.76436614990234,
|
| 363 |
+
"logps/rejected": -75.7645034790039,
|
| 364 |
+
"loss": 0.6309,
|
| 365 |
+
"rewards/accuracies": 0.762499988079071,
|
| 366 |
+
"rewards/chosen": -0.12716726958751678,
|
| 367 |
+
"rewards/margins": 0.15734827518463135,
|
| 368 |
+
"rewards/rejected": -0.2845155596733093,
|
| 369 |
+
"step": 240
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 8.459915611814345,
|
| 373 |
+
"grad_norm": 0.9569210410118103,
|
| 374 |
+
"learning_rate": 3.508587904974522e-06,
|
| 375 |
+
"logits/chosen": 1.711611032485962,
|
| 376 |
+
"logits/rejected": 1.820723295211792,
|
| 377 |
+
"logps/chosen": -81.62940979003906,
|
| 378 |
+
"logps/rejected": -104.07059478759766,
|
| 379 |
+
"loss": 0.6206,
|
| 380 |
+
"rewards/accuracies": 0.800000011920929,
|
| 381 |
+
"rewards/chosen": -0.12964895367622375,
|
| 382 |
+
"rewards/margins": 0.2236514836549759,
|
| 383 |
+
"rewards/rejected": -0.35330042243003845,
|
| 384 |
+
"step": 250
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 8.79746835443038,
|
| 388 |
+
"grad_norm": 0.9199231863021851,
|
| 389 |
+
"learning_rate": 3.3691733481883693e-06,
|
| 390 |
+
"logits/chosen": 1.860053300857544,
|
| 391 |
+
"logits/rejected": 1.8826453685760498,
|
| 392 |
+
"logps/chosen": -89.85298919677734,
|
| 393 |
+
"logps/rejected": -90.7202377319336,
|
| 394 |
+
"loss": 0.6129,
|
| 395 |
+
"rewards/accuracies": 0.75,
|
| 396 |
+
"rewards/chosen": -0.1632840931415558,
|
| 397 |
+
"rewards/margins": 0.22734332084655762,
|
| 398 |
+
"rewards/rejected": -0.3906274437904358,
|
| 399 |
+
"step": 260
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 9.135021097046414,
|
| 403 |
+
"grad_norm": 0.996032178401947,
|
| 404 |
+
"learning_rate": 3.226611521064278e-06,
|
| 405 |
+
"logits/chosen": 1.8121602535247803,
|
| 406 |
+
"logits/rejected": 1.7851508855819702,
|
| 407 |
+
"logps/chosen": -76.85626220703125,
|
| 408 |
+
"logps/rejected": -77.3901138305664,
|
| 409 |
+
"loss": 0.6155,
|
| 410 |
+
"rewards/accuracies": 0.75,
|
| 411 |
+
"rewards/chosen": -0.16423651576042175,
|
| 412 |
+
"rewards/margins": 0.2163097858428955,
|
| 413 |
+
"rewards/rejected": -0.38054633140563965,
|
| 414 |
+
"step": 270
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"epoch": 9.472573839662447,
|
| 418 |
+
"grad_norm": 0.96324622631073,
|
| 419 |
+
"learning_rate": 3.0814186389357765e-06,
|
| 420 |
+
"logits/chosen": 1.7609102725982666,
|
| 421 |
+
"logits/rejected": 1.782065749168396,
|
| 422 |
+
"logps/chosen": -78.853271484375,
|
| 423 |
+
"logps/rejected": -81.43799591064453,
|
| 424 |
+
"loss": 0.5991,
|
| 425 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 426 |
+
"rewards/chosen": -0.19906465709209442,
|
| 427 |
+
"rewards/margins": 0.2417418658733368,
|
| 428 |
+
"rewards/rejected": -0.4408065378665924,
|
| 429 |
+
"step": 280
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 9.810126582278482,
|
| 433 |
+
"grad_norm": 0.9327431917190552,
|
| 434 |
+
"learning_rate": 2.9341204441673267e-06,
|
| 435 |
+
"logits/chosen": 1.7485430240631104,
|
| 436 |
+
"logits/rejected": 1.7885955572128296,
|
| 437 |
+
"logps/chosen": -81.84668731689453,
|
| 438 |
+
"logps/rejected": -84.5110855102539,
|
| 439 |
+
"loss": 0.6035,
|
| 440 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 441 |
+
"rewards/chosen": -0.24916405975818634,
|
| 442 |
+
"rewards/margins": 0.22875118255615234,
|
| 443 |
+
"rewards/rejected": -0.47791528701782227,
|
| 444 |
+
"step": 290
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 10.147679324894515,
|
| 448 |
+
"grad_norm": 1.1683701276779175,
|
| 449 |
+
"learning_rate": 2.785250302445062e-06,
|
| 450 |
+
"logits/chosen": 1.8126602172851562,
|
| 451 |
+
"logits/rejected": 1.8814666271209717,
|
| 452 |
+
"logps/chosen": -105.7123031616211,
|
| 453 |
+
"logps/rejected": -92.78335571289062,
|
| 454 |
+
"loss": 0.5916,
|
| 455 |
+
"rewards/accuracies": 0.800000011920929,
|
| 456 |
+
"rewards/chosen": -0.257813036441803,
|
| 457 |
+
"rewards/margins": 0.28732481598854065,
|
| 458 |
+
"rewards/rejected": -0.5451378226280212,
|
| 459 |
+
"step": 300
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 10.485232067510548,
|
| 463 |
+
"grad_norm": 1.078698754310608,
|
| 464 |
+
"learning_rate": 2.6353472714635443e-06,
|
| 465 |
+
"logits/chosen": 1.7991764545440674,
|
| 466 |
+
"logits/rejected": 1.8787552118301392,
|
| 467 |
+
"logps/chosen": -70.400634765625,
|
| 468 |
+
"logps/rejected": -72.78517150878906,
|
| 469 |
+
"loss": 0.5893,
|
| 470 |
+
"rewards/accuracies": 0.7250000238418579,
|
| 471 |
+
"rewards/chosen": -0.23745933175086975,
|
| 472 |
+
"rewards/margins": 0.22456249594688416,
|
| 473 |
+
"rewards/rejected": -0.4620218276977539,
|
| 474 |
+
"step": 310
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 10.822784810126583,
|
| 478 |
+
"grad_norm": 1.0667306184768677,
|
| 479 |
+
"learning_rate": 2.4849541490017868e-06,
|
| 480 |
+
"logits/chosen": 1.7493784427642822,
|
| 481 |
+
"logits/rejected": 1.7776050567626953,
|
| 482 |
+
"logps/chosen": -79.56948852539062,
|
| 483 |
+
"logps/rejected": -95.15191650390625,
|
| 484 |
+
"loss": 0.5943,
|
| 485 |
+
"rewards/accuracies": 0.8125,
|
| 486 |
+
"rewards/chosen": -0.2948698401451111,
|
| 487 |
+
"rewards/margins": 0.27440011501312256,
|
| 488 |
+
"rewards/rejected": -0.5692699551582336,
|
| 489 |
+
"step": 320
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 11.160337552742616,
|
| 493 |
+
"grad_norm": 1.1734286546707153,
|
| 494 |
+
"learning_rate": 2.3346155074564712e-06,
|
| 495 |
+
"logits/chosen": 1.7588024139404297,
|
| 496 |
+
"logits/rejected": 1.6906486749649048,
|
| 497 |
+
"logps/chosen": -92.88114929199219,
|
| 498 |
+
"logps/rejected": -87.77473449707031,
|
| 499 |
+
"loss": 0.5748,
|
| 500 |
+
"rewards/accuracies": 0.8125,
|
| 501 |
+
"rewards/chosen": -0.26193878054618835,
|
| 502 |
+
"rewards/margins": 0.31644436717033386,
|
| 503 |
+
"rewards/rejected": -0.5783831477165222,
|
| 504 |
+
"step": 330
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 11.49789029535865,
|
| 508 |
+
"grad_norm": 1.0506142377853394,
|
| 509 |
+
"learning_rate": 2.184875721949277e-06,
|
| 510 |
+
"logits/chosen": 1.6390129327774048,
|
| 511 |
+
"logits/rejected": 1.6817207336425781,
|
| 512 |
+
"logps/chosen": -85.6020278930664,
|
| 513 |
+
"logps/rejected": -81.51480865478516,
|
| 514 |
+
"loss": 0.5755,
|
| 515 |
+
"rewards/accuracies": 0.824999988079071,
|
| 516 |
+
"rewards/chosen": -0.2864437997341156,
|
| 517 |
+
"rewards/margins": 0.3067106604576111,
|
| 518 |
+
"rewards/rejected": -0.5931544899940491,
|
| 519 |
+
"step": 340
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 11.835443037974684,
|
| 523 |
+
"grad_norm": 1.0367387533187866,
|
| 524 |
+
"learning_rate": 2.0362769991485514e-06,
|
| 525 |
+
"logits/chosen": 1.811912178993225,
|
| 526 |
+
"logits/rejected": 1.8571999073028564,
|
| 527 |
+
"logps/chosen": -79.2660903930664,
|
| 528 |
+
"logps/rejected": -105.51014709472656,
|
| 529 |
+
"loss": 0.5743,
|
| 530 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 531 |
+
"rewards/chosen": -0.2905730605125427,
|
| 532 |
+
"rewards/margins": 0.37750759720802307,
|
| 533 |
+
"rewards/rejected": -0.6680806279182434,
|
| 534 |
+
"step": 350
|
| 535 |
+
},
|
| 536 |
+
{
|
| 537 |
+
"epoch": 12.172995780590718,
|
| 538 |
+
"grad_norm": 1.249039888381958,
|
| 539 |
+
"learning_rate": 1.8893574139429226e-06,
|
| 540 |
+
"logits/chosen": 1.8357423543930054,
|
| 541 |
+
"logits/rejected": 1.8285624980926514,
|
| 542 |
+
"logps/chosen": -85.5277099609375,
|
| 543 |
+
"logps/rejected": -90.13473510742188,
|
| 544 |
+
"loss": 0.575,
|
| 545 |
+
"rewards/accuracies": 0.762499988079071,
|
| 546 |
+
"rewards/chosen": -0.36660733819007874,
|
| 547 |
+
"rewards/margins": 0.3461737632751465,
|
| 548 |
+
"rewards/rejected": -0.7127811312675476,
|
| 549 |
+
"step": 360
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 12.51054852320675,
|
| 553 |
+
"grad_norm": 1.1541879177093506,
|
| 554 |
+
"learning_rate": 1.744648961076068e-06,
|
| 555 |
+
"logits/chosen": 1.790567398071289,
|
| 556 |
+
"logits/rejected": 1.7228246927261353,
|
| 557 |
+
"logps/chosen": -86.40596008300781,
|
| 558 |
+
"logps/rejected": -75.5702896118164,
|
| 559 |
+
"loss": 0.5693,
|
| 560 |
+
"rewards/accuracies": 0.762499988079071,
|
| 561 |
+
"rewards/chosen": -0.34050875902175903,
|
| 562 |
+
"rewards/margins": 0.2642201781272888,
|
| 563 |
+
"rewards/rejected": -0.6047288775444031,
|
| 564 |
+
"step": 370
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 12.848101265822784,
|
| 568 |
+
"grad_norm": 1.0363268852233887,
|
| 569 |
+
"learning_rate": 1.602675628797636e-06,
|
| 570 |
+
"logits/chosen": 1.6812736988067627,
|
| 571 |
+
"logits/rejected": 1.7188876867294312,
|
| 572 |
+
"logps/chosen": -81.14212799072266,
|
| 573 |
+
"logps/rejected": -82.90364074707031,
|
| 574 |
+
"loss": 0.5594,
|
| 575 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 576 |
+
"rewards/chosen": -0.3105277419090271,
|
| 577 |
+
"rewards/margins": 0.3372951149940491,
|
| 578 |
+
"rewards/rejected": -0.6478228569030762,
|
| 579 |
+
"step": 380
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 13.185654008438819,
|
| 583 |
+
"grad_norm": 1.047418475151062,
|
| 584 |
+
"learning_rate": 1.4639515015056205e-06,
|
| 585 |
+
"logits/chosen": 1.6939361095428467,
|
| 586 |
+
"logits/rejected": 1.7271579504013062,
|
| 587 |
+
"logps/chosen": -86.88213348388672,
|
| 588 |
+
"logps/rejected": -99.46037292480469,
|
| 589 |
+
"loss": 0.558,
|
| 590 |
+
"rewards/accuracies": 0.762499988079071,
|
| 591 |
+
"rewards/chosen": -0.2660979926586151,
|
| 592 |
+
"rewards/margins": 0.4496893882751465,
|
| 593 |
+
"rewards/rejected": -0.7157873511314392,
|
| 594 |
+
"step": 390
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"epoch": 13.523206751054852,
|
| 598 |
+
"grad_norm": 1.1949480772018433,
|
| 599 |
+
"learning_rate": 1.328978898250525e-06,
|
| 600 |
+
"logits/chosen": 1.7057956457138062,
|
| 601 |
+
"logits/rejected": 1.726438283920288,
|
| 602 |
+
"logps/chosen": -85.27348327636719,
|
| 603 |
+
"logps/rejected": -96.06895446777344,
|
| 604 |
+
"loss": 0.5553,
|
| 605 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 606 |
+
"rewards/chosen": -0.3689552843570709,
|
| 607 |
+
"rewards/margins": 0.3453688621520996,
|
| 608 |
+
"rewards/rejected": -0.7143241763114929,
|
| 609 |
+
"step": 400
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 13.860759493670885,
|
| 613 |
+
"grad_norm": 1.5321677923202515,
|
| 614 |
+
"learning_rate": 1.198246553841744e-06,
|
| 615 |
+
"logits/chosen": 1.8362537622451782,
|
| 616 |
+
"logits/rejected": 1.889491081237793,
|
| 617 |
+
"logps/chosen": -78.84573364257812,
|
| 618 |
+
"logps/rejected": -75.66096496582031,
|
| 619 |
+
"loss": 0.5618,
|
| 620 |
+
"rewards/accuracies": 0.762499988079071,
|
| 621 |
+
"rewards/chosen": -0.34546419978141785,
|
| 622 |
+
"rewards/margins": 0.3866986334323883,
|
| 623 |
+
"rewards/rejected": -0.7321628332138062,
|
| 624 |
+
"step": 410
|
| 625 |
+
},
|
| 626 |
+
{
|
| 627 |
+
"epoch": 14.19831223628692,
|
| 628 |
+
"grad_norm": 1.1697853803634644,
|
| 629 |
+
"learning_rate": 1.0722278491423998e-06,
|
| 630 |
+
"logits/chosen": 1.7950217723846436,
|
| 631 |
+
"logits/rejected": 1.8145115375518799,
|
| 632 |
+
"logps/chosen": -82.2846908569336,
|
| 633 |
+
"logps/rejected": -91.40074157714844,
|
| 634 |
+
"loss": 0.5516,
|
| 635 |
+
"rewards/accuracies": 0.800000011920929,
|
| 636 |
+
"rewards/chosen": -0.37175649404525757,
|
| 637 |
+
"rewards/margins": 0.404013067483902,
|
| 638 |
+
"rewards/rejected": -0.7757695913314819,
|
| 639 |
+
"step": 420
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 14.535864978902953,
|
| 643 |
+
"grad_norm": 1.163073182106018,
|
| 644 |
+
"learning_rate": 9.513790969606926e-07,
|
| 645 |
+
"logits/chosen": 1.686415433883667,
|
| 646 |
+
"logits/rejected": 1.7637500762939453,
|
| 647 |
+
"logps/chosen": -100.37837219238281,
|
| 648 |
+
"logps/rejected": -100.43409729003906,
|
| 649 |
+
"loss": 0.5583,
|
| 650 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 651 |
+
"rewards/chosen": -0.35831838846206665,
|
| 652 |
+
"rewards/margins": 0.3624442219734192,
|
| 653 |
+
"rewards/rejected": -0.7207626104354858,
|
| 654 |
+
"step": 430
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 14.873417721518987,
|
| 658 |
+
"grad_norm": 1.148380160331726,
|
| 659 |
+
"learning_rate": 8.361378897445643e-07,
|
| 660 |
+
"logits/chosen": 1.6370818614959717,
|
| 661 |
+
"logits/rejected": 1.752598524093628,
|
| 662 |
+
"logps/chosen": -84.63670349121094,
|
| 663 |
+
"logps/rejected": -89.8626708984375,
|
| 664 |
+
"loss": 0.5584,
|
| 665 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 666 |
+
"rewards/chosen": -0.44350141286849976,
|
| 667 |
+
"rewards/margins": 0.4355877935886383,
|
| 668 |
+
"rewards/rejected": -0.8790891766548157,
|
| 669 |
+
"step": 440
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 15.210970464135022,
|
| 673 |
+
"grad_norm": 1.1012156009674072,
|
| 674 |
+
"learning_rate": 7.269215150626391e-07,
|
| 675 |
+
"logits/chosen": 1.8232038021087646,
|
| 676 |
+
"logits/rejected": 1.8113384246826172,
|
| 677 |
+
"logps/chosen": -95.2444839477539,
|
| 678 |
+
"logps/rejected": -85.72362518310547,
|
| 679 |
+
"loss": 0.5539,
|
| 680 |
+
"rewards/accuracies": 0.875,
|
| 681 |
+
"rewards/chosen": -0.3705037236213684,
|
| 682 |
+
"rewards/margins": 0.5386990308761597,
|
| 683 |
+
"rewards/rejected": -0.9092028737068176,
|
| 684 |
+
"step": 450
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"epoch": 15.548523206751055,
|
| 688 |
+
"grad_norm": 1.0890499353408813,
|
| 689 |
+
"learning_rate": 6.241254446089942e-07,
|
| 690 |
+
"logits/chosen": 1.6102081537246704,
|
| 691 |
+
"logits/rejected": 1.6902793645858765,
|
| 692 |
+
"logps/chosen": -77.29241943359375,
|
| 693 |
+
"logps/rejected": -87.38616943359375,
|
| 694 |
+
"loss": 0.554,
|
| 695 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 696 |
+
"rewards/chosen": -0.36334335803985596,
|
| 697 |
+
"rewards/margins": 0.41814422607421875,
|
| 698 |
+
"rewards/rejected": -0.7814875841140747,
|
| 699 |
+
"step": 460
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 15.886075949367088,
|
| 703 |
+
"grad_norm": 1.1587886810302734,
|
| 704 |
+
"learning_rate": 5.281219022030423e-07,
|
| 705 |
+
"logits/chosen": 1.7049728631973267,
|
| 706 |
+
"logits/rejected": 1.7815492153167725,
|
| 707 |
+
"logps/chosen": -79.66454315185547,
|
| 708 |
+
"logps/rejected": -91.70343017578125,
|
| 709 |
+
"loss": 0.5472,
|
| 710 |
+
"rewards/accuracies": 0.800000011920929,
|
| 711 |
+
"rewards/chosen": -0.3898239731788635,
|
| 712 |
+
"rewards/margins": 0.40187686681747437,
|
| 713 |
+
"rewards/rejected": -0.7917007803916931,
|
| 714 |
+
"step": 470
|
| 715 |
+
},
|
| 716 |
+
{
|
| 717 |
+
"epoch": 16.223628691983123,
|
| 718 |
+
"grad_norm": 1.5429887771606445,
|
| 719 |
+
"learning_rate": 4.392585159698087e-07,
|
| 720 |
+
"logits/chosen": 1.6508013010025024,
|
| 721 |
+
"logits/rejected": 1.7940822839736938,
|
| 722 |
+
"logps/chosen": -77.51395416259766,
|
| 723 |
+
"logps/rejected": -90.20869445800781,
|
| 724 |
+
"loss": 0.5512,
|
| 725 |
+
"rewards/accuracies": 0.7875000238418579,
|
| 726 |
+
"rewards/chosen": -0.35601454973220825,
|
| 727 |
+
"rewards/margins": 0.3707844018936157,
|
| 728 |
+
"rewards/rejected": -0.7267988920211792,
|
| 729 |
+
"step": 480
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 16.561181434599156,
|
| 733 |
+
"grad_norm": 1.1558414697647095,
|
| 734 |
+
"learning_rate": 3.578570595810274e-07,
|
| 735 |
+
"logits/chosen": 1.6670711040496826,
|
| 736 |
+
"logits/rejected": 1.6244487762451172,
|
| 737 |
+
"logps/chosen": -101.91804504394531,
|
| 738 |
+
"logps/rejected": -91.96507263183594,
|
| 739 |
+
"loss": 0.5452,
|
| 740 |
+
"rewards/accuracies": 0.824999988079071,
|
| 741 |
+
"rewards/chosen": -0.40192681550979614,
|
| 742 |
+
"rewards/margins": 0.44803065061569214,
|
| 743 |
+
"rewards/rejected": -0.8499574661254883,
|
| 744 |
+
"step": 490
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 16.89873417721519,
|
| 748 |
+
"grad_norm": 1.1151753664016724,
|
| 749 |
+
"learning_rate": 2.8421228711503127e-07,
|
| 750 |
+
"logits/chosen": 1.7409915924072266,
|
| 751 |
+
"logits/rejected": 1.8301231861114502,
|
| 752 |
+
"logps/chosen": -71.89210510253906,
|
| 753 |
+
"logps/rejected": -90.07672119140625,
|
| 754 |
+
"loss": 0.5423,
|
| 755 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 756 |
+
"rewards/chosen": -0.4172780513763428,
|
| 757 |
+
"rewards/margins": 0.394390344619751,
|
| 758 |
+
"rewards/rejected": -0.8116683959960938,
|
| 759 |
+
"step": 500
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 17.236286919831223,
|
| 763 |
+
"grad_norm": 1.1430857181549072,
|
| 764 |
+
"learning_rate": 2.1859086575439225e-07,
|
| 765 |
+
"logits/chosen": 1.668222188949585,
|
| 766 |
+
"logits/rejected": 1.7431071996688843,
|
| 767 |
+
"logps/chosen": -80.20066833496094,
|
| 768 |
+
"logps/rejected": -88.21453094482422,
|
| 769 |
+
"loss": 0.5312,
|
| 770 |
+
"rewards/accuracies": 0.8125,
|
| 771 |
+
"rewards/chosen": -0.3836023807525635,
|
| 772 |
+
"rewards/margins": 0.41132551431655884,
|
| 773 |
+
"rewards/rejected": -0.7949277758598328,
|
| 774 |
+
"step": 510
|
| 775 |
+
},
|
| 776 |
+
{
|
| 777 |
+
"epoch": 17.573839662447256,
|
| 778 |
+
"grad_norm": 1.3264650106430054,
|
| 779 |
+
"learning_rate": 1.6123041018599766e-07,
|
| 780 |
+
"logits/chosen": 1.6724201440811157,
|
| 781 |
+
"logits/rejected": 1.782766580581665,
|
| 782 |
+
"logps/chosen": -87.28868103027344,
|
| 783 |
+
"logps/rejected": -109.66194152832031,
|
| 784 |
+
"loss": 0.5529,
|
| 785 |
+
"rewards/accuracies": 0.800000011920929,
|
| 786 |
+
"rewards/chosen": -0.4659019112586975,
|
| 787 |
+
"rewards/margins": 0.3525821268558502,
|
| 788 |
+
"rewards/rejected": -0.8184840083122253,
|
| 789 |
+
"step": 520
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 17.911392405063292,
|
| 793 |
+
"grad_norm": 1.2674906253814697,
|
| 794 |
+
"learning_rate": 1.1233862220001168e-07,
|
| 795 |
+
"logits/chosen": 1.6698293685913086,
|
| 796 |
+
"logits/rejected": 1.696459412574768,
|
| 797 |
+
"logps/chosen": -95.00108337402344,
|
| 798 |
+
"logps/rejected": -84.9312973022461,
|
| 799 |
+
"loss": 0.5565,
|
| 800 |
+
"rewards/accuracies": 0.8125,
|
| 801 |
+
"rewards/chosen": -0.3677830696105957,
|
| 802 |
+
"rewards/margins": 0.4486306607723236,
|
| 803 |
+
"rewards/rejected": -0.8164137005805969,
|
| 804 |
+
"step": 530
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 18.248945147679326,
|
| 808 |
+
"grad_norm": 1.1495198011398315,
|
| 809 |
+
"learning_rate": 7.209253860320897e-08,
|
| 810 |
+
"logits/chosen": 1.7104814052581787,
|
| 811 |
+
"logits/rejected": 1.7387645244598389,
|
| 812 |
+
"logps/chosen": -84.37834167480469,
|
| 813 |
+
"logps/rejected": -82.36712646484375,
|
| 814 |
+
"loss": 0.5475,
|
| 815 |
+
"rewards/accuracies": 0.7749999761581421,
|
| 816 |
+
"rewards/chosen": -0.4061828553676605,
|
| 817 |
+
"rewards/margins": 0.3533913493156433,
|
| 818 |
+
"rewards/rejected": -0.7595741748809814,
|
| 819 |
+
"step": 540
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 18.58649789029536,
|
| 823 |
+
"grad_norm": 1.0989700555801392,
|
| 824 |
+
"learning_rate": 4.063789016999331e-08,
|
| 825 |
+
"logits/chosen": 1.6560907363891602,
|
| 826 |
+
"logits/rejected": 1.7722400426864624,
|
| 827 |
+
"logps/chosen": -80.30384826660156,
|
| 828 |
+
"logps/rejected": -84.69402313232422,
|
| 829 |
+
"loss": 0.5462,
|
| 830 |
+
"rewards/accuracies": 0.8125,
|
| 831 |
+
"rewards/chosen": -0.3671244978904724,
|
| 832 |
+
"rewards/margins": 0.41629084944725037,
|
| 833 |
+
"rewards/rejected": -0.7834154367446899,
|
| 834 |
+
"step": 550
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 18.924050632911392,
|
| 838 |
+
"grad_norm": 1.159568428993225,
|
| 839 |
+
"learning_rate": 1.808857395232788e-08,
|
| 840 |
+
"logits/chosen": 1.738085389137268,
|
| 841 |
+
"logits/rejected": 1.6417734622955322,
|
| 842 |
+
"logps/chosen": -107.0008316040039,
|
| 843 |
+
"logps/rejected": -72.6747817993164,
|
| 844 |
+
"loss": 0.5327,
|
| 845 |
+
"rewards/accuracies": 0.8374999761581421,
|
| 846 |
+
"rewards/chosen": -0.34443432092666626,
|
| 847 |
+
"rewards/margins": 0.4274899363517761,
|
| 848 |
+
"rewards/rejected": -0.7719243168830872,
|
| 849 |
+
"step": 560
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 19.261603375527425,
|
| 853 |
+
"grad_norm": 1.208256483078003,
|
| 854 |
+
"learning_rate": 4.526240859345499e-09,
|
| 855 |
+
"logits/chosen": 1.7233607769012451,
|
| 856 |
+
"logits/rejected": 1.7593921422958374,
|
| 857 |
+
"logps/chosen": -88.6917953491211,
|
| 858 |
+
"logps/rejected": -82.6318359375,
|
| 859 |
+
"loss": 0.5552,
|
| 860 |
+
"rewards/accuracies": 0.824999988079071,
|
| 861 |
+
"rewards/chosen": -0.31639525294303894,
|
| 862 |
+
"rewards/margins": 0.3895270824432373,
|
| 863 |
+
"rewards/rejected": -0.7059223055839539,
|
| 864 |
+
"step": 570
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 19.59915611814346,
|
| 868 |
+
"grad_norm": 1.0889534950256348,
|
| 869 |
+
"learning_rate": 0.0,
|
| 870 |
+
"logits/chosen": 1.706377625465393,
|
| 871 |
+
"logits/rejected": 1.853161096572876,
|
| 872 |
+
"logps/chosen": -77.8305892944336,
|
| 873 |
+
"logps/rejected": -102.3224868774414,
|
| 874 |
+
"loss": 0.5454,
|
| 875 |
+
"rewards/accuracies": 0.862500011920929,
|
| 876 |
+
"rewards/chosen": -0.357083261013031,
|
| 877 |
+
"rewards/margins": 0.48699983954429626,
|
| 878 |
+
"rewards/rejected": -0.8440830111503601,
|
| 879 |
+
"step": 580
|
| 880 |
+
}
|
| 881 |
+
],
|
| 882 |
+
"logging_steps": 10,
|
| 883 |
+
"max_steps": 580,
|
| 884 |
+
"num_input_tokens_seen": 0,
|
| 885 |
+
"num_train_epochs": 20,
|
| 886 |
+
"save_steps": 50,
|
| 887 |
+
"stateful_callbacks": {
|
| 888 |
+
"TrainerControl": {
|
| 889 |
+
"args": {
|
| 890 |
+
"should_epoch_stop": false,
|
| 891 |
+
"should_evaluate": false,
|
| 892 |
+
"should_log": false,
|
| 893 |
+
"should_save": true,
|
| 894 |
+
"should_training_stop": true
|
| 895 |
+
},
|
| 896 |
+
"attributes": {}
|
| 897 |
+
}
|
| 898 |
+
},
|
| 899 |
+
"total_flos": 1.9914349255044628e+18,
|
| 900 |
+
"train_batch_size": 1,
|
| 901 |
+
"trial_name": null,
|
| 902 |
+
"trial_params": null
|
| 903 |
+
}
|