Upload folder using huggingface_hub

multi_perspective/README.md

@@ -1,9 +1,9 @@
 ---
-base_model: meta-llama/Llama-3.1-8B-Instruct
+base_model: Raiff1982/codette-llama-3.1-8b-merged
 library_name: peft
 model_name: multi_perspective
 tags:
-- base_model:adapter:meta-llama/Llama-3.1-8B-Instruct
+- base_model:adapter:Raiff1982/codette-llama-3.1-8b-merged
 - lora
 - sft
 - transformers
@@ -14,7 +14,7 @@ pipeline_tag: text-generation
 
 # Model Card for multi_perspective
 
-This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct).
+This model is a fine-tuned version of [Raiff1982/codette-llama-3.1-8b-merged](https://huggingface.co/Raiff1982/codette-llama-3.1-8b-merged).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -39,10 +39,10 @@ This model was trained with SFT.
 ### Framework versions
 
 - PEFT 0.18.1
-- TRL: 0.29.1
-- Transformers: 5.3.0
-- Pytorch: 2.10.0
-- Datasets: 4.8.3
+- TRL: 1.0.0
+- Transformers: 5.5.0
+- Pytorch: 2.11.0
+- Datasets: 4.8.4
 - Tokenizers: 0.22.2
 
 ## Citations

multi_perspective/adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "base_model_name_or_path": "Raiff1982/codette-llama-3.1-8b-merged",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -30,9 +30,9 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "v_proj",
+    "k_proj",
     "q_proj",
-    "k_proj"
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

multi_perspective/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:918a0fb47f5d1ac49cebd1e6ec366cd4f732f6956c3c5203fb7ebb01eddcaec8
+oid sha256:d73a0d3e12b9090e0882b6e8d65667babc15723eed706c538c472418cefcef03
 size 27297544

multi_perspective/checkpoint-225/README.md

@@ -1,9 +1,9 @@
 ---
-base_model: meta-llama/Llama-3.1-8B-Instruct
+base_model: Raiff1982/codette-llama-3.1-8b-merged
 library_name: peft
 pipeline_tag: text-generation
 tags:
-- base_model:adapter:meta-llama/Llama-3.1-8B-Instruct
+- base_model:adapter:Raiff1982/codette-llama-3.1-8b-merged
 - lora
 - sft
 - transformers

multi_perspective/checkpoint-225/adapter_config.json

@@ -3,7 +3,7 @@
   "alpha_pattern": {},
   "arrow_config": null,
   "auto_mapping": null,
-  "base_model_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "base_model_name_or_path": "Raiff1982/codette-llama-3.1-8b-merged",
   "bias": "none",
   "corda_config": null,
   "ensure_weight_tying": false,
@@ -30,9 +30,9 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "v_proj",
+    "k_proj",
     "q_proj",
-    "k_proj"
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

multi_perspective/checkpoint-225/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:918a0fb47f5d1ac49cebd1e6ec366cd4f732f6956c3c5203fb7ebb01eddcaec8
+oid sha256:d73a0d3e12b9090e0882b6e8d65667babc15723eed706c538c472418cefcef03
 size 27297544

multi_perspective/checkpoint-225/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31fad83b8fd649a47cc654e79c768fd8ad21f7f7b1fd2b4a0c5849662ca4034f
+oid sha256:acddccc931093b64defbf3498b68cf3d23fbd768c5cdbae8a1b830cbf7aadd08
 size 54745547

multi_perspective/checkpoint-225/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06eb2e4f2392d5cff7633897aae6c92765ee0ff18fac8b62001d1a06409563d4
+oid sha256:a07e6ad37bc7018de910885b68e8722de323ece1ae4261644886f6951fc423e3
 size 1465

multi_perspective/checkpoint-225/trainer_state.json

@@ -10,222 +10,222 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "entropy": 2.499886918067932,
+      "entropy": 2.4297286450862883,
       "epoch": 0.13333333333333333,
-      "grad_norm": 0.5546875,
-      "learning_rate": 0.0001981651376146789,
-      "loss": 2.9341304779052733,
-      "mean_token_accuracy": 0.48720409646630286,
+      "grad_norm": 0.486328125,
+      "learning_rate": 9.908256880733946e-05,
+      "loss": 3.1063995361328125,
+      "mean_token_accuracy": 0.4706620879471302,
       "num_tokens": 25743.0,
       "step": 10
     },
     {
-      "entropy": 1.0729461215436458,
+      "entropy": 2.1096888720989226,
       "epoch": 0.26666666666666666,
-      "grad_norm": 0.400390625,
-      "learning_rate": 0.0001889908256880734,
-      "loss": 0.995582103729248,
-      "mean_token_accuracy": 0.787577822804451,
+      "grad_norm": 0.69140625,
+      "learning_rate": 9.44954128440367e-05,
+      "loss": 1.9874359130859376,
+      "mean_token_accuracy": 0.5988489270210267,
       "num_tokens": 51331.0,
       "step": 20
     },
     {
-      "entropy": 0.26769001968204975,
+      "entropy": 0.7344605229794979,
       "epoch": 0.4,
-      "grad_norm": 0.220703125,
-      "learning_rate": 0.0001798165137614679,
-      "loss": 0.2410867691040039,
-      "mean_token_accuracy": 0.9545496806502343,
+      "grad_norm": 0.40234375,
+      "learning_rate": 8.990825688073395e-05,
+      "loss": 0.6296343326568603,
+      "mean_token_accuracy": 0.8648389235138894,
       "num_tokens": 76925.0,
       "step": 30
     },
     {
-      "entropy": 0.1838659353554249,
+      "entropy": 0.25978546887636184,
       "epoch": 0.5333333333333333,
-      "grad_norm": 0.10400390625,
-      "learning_rate": 0.0001706422018348624,
-      "loss": 0.15834593772888184,
-      "mean_token_accuracy": 0.9698517322540283,
+      "grad_norm": 0.1953125,
+      "learning_rate": 8.53211009174312e-05,
+      "loss": 0.23441579341888427,
+      "mean_token_accuracy": 0.9539701744914055,
       "num_tokens": 102498.0,
       "step": 40
     },
     {
-      "entropy": 0.150449451059103,
+      "entropy": 0.19497511722147465,
       "epoch": 0.6666666666666666,
-      "grad_norm": 0.115234375,
-      "learning_rate": 0.00016146788990825688,
-      "loss": 0.12726666927337646,
-      "mean_token_accuracy": 0.9755061268806458,
+      "grad_norm": 0.1962890625,
+      "learning_rate": 8.073394495412844e-05,
+      "loss": 0.17294132709503174,
+      "mean_token_accuracy": 0.9675838366150856,
       "num_tokens": 128211.0,
       "step": 50
     },
     {
-      "entropy": 0.13086459934711456,
+      "entropy": 0.16434485837817192,
       "epoch": 0.8,
-      "grad_norm": 0.09765625,
-      "learning_rate": 0.00015229357798165138,
-      "loss": 0.10074326992034913,
-      "mean_token_accuracy": 0.9805575668811798,
+      "grad_norm": 0.12060546875,
+      "learning_rate": 7.614678899082569e-05,
+      "loss": 0.14781221151351928,
+      "mean_token_accuracy": 0.971477971971035,
       "num_tokens": 153895.0,
       "step": 60
     },
     {
-      "entropy": 0.08929065894335508,
+      "entropy": 0.14736841414123775,
       "epoch": 0.9333333333333333,
-      "grad_norm": 0.1025390625,
-      "learning_rate": 0.0001431192660550459,
-      "loss": 0.07399526834487916,
-      "mean_token_accuracy": 0.9826277583837509,
+      "grad_norm": 0.169921875,
+      "learning_rate": 7.155963302752295e-05,
+      "loss": 0.1276508927345276,
+      "mean_token_accuracy": 0.9748700320720672,
       "num_tokens": 179649.0,
       "step": 70
     },
     {
-      "entropy": 0.08783094771206379,
+      "entropy": 0.14000136777758598,
       "epoch": 1.0666666666666667,
-      "grad_norm": 0.0810546875,
-      "learning_rate": 0.00013394495412844036,
-      "loss": 0.06318077445030212,
-      "mean_token_accuracy": 0.9826931029558181,
+      "grad_norm": 0.10888671875,
+      "learning_rate": 6.697247706422018e-05,
+      "loss": 0.11548733711242676,
+      "mean_token_accuracy": 0.9769446536898613,
       "num_tokens": 205347.0,
       "step": 80
     },
     {
-      "entropy": 0.07573890537023545,
+      "entropy": 0.12713013775646687,
       "epoch": 1.2,
-      "grad_norm": 0.078125,
-      "learning_rate": 0.00012477064220183488,
-      "loss": 0.04915967583656311,
-      "mean_token_accuracy": 0.9834711134433747,
+      "grad_norm": 0.10791015625,
+      "learning_rate": 6.238532110091744e-05,
+      "loss": 0.10261231660842896,
+      "mean_token_accuracy": 0.9786922246217727,
       "num_tokens": 231039.0,
       "step": 90
     },
     {
-      "entropy": 0.06236284449696541,
+      "entropy": 0.12289925683289767,
       "epoch": 1.3333333333333333,
-      "grad_norm": 0.0478515625,
-      "learning_rate": 0.00011559633027522936,
-      "loss": 0.04472715854644775,
-      "mean_token_accuracy": 0.983341871201992,
+      "grad_norm": 0.1025390625,
+      "learning_rate": 5.779816513761468e-05,
+      "loss": 0.09635450839996337,
+      "mean_token_accuracy": 0.9823385506868363,
       "num_tokens": 256844.0,
       "step": 100
     },
     {
-      "entropy": 0.05544539717957377,
+      "entropy": 0.1156039472669363,
       "epoch": 1.4666666666666668,
-      "grad_norm": 0.064453125,
-      "learning_rate": 0.00010642201834862387,
-      "loss": 0.041876214742660525,
-      "mean_token_accuracy": 0.9832384318113327,
+      "grad_norm": 0.1357421875,
+      "learning_rate": 5.3211009174311934e-05,
+      "loss": 0.09175726771354675,
+      "mean_token_accuracy": 0.9818408191204071,
       "num_tokens": 282538.0,
       "step": 110
     },
     {
-      "entropy": 0.04832997312769294,
+      "entropy": 0.1169380746781826,
       "epoch": 1.6,
-      "grad_norm": 0.046875,
-      "learning_rate": 9.724770642201836e-05,
-      "loss": 0.03997953236103058,
-      "mean_token_accuracy": 0.9840096086263657,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 4.862385321100918e-05,
+      "loss": 0.08704986572265624,
+      "mean_token_accuracy": 0.9828749150037766,
       "num_tokens": 308150.0,
       "step": 120
     },
     {
-      "entropy": 0.045895603485405445,
+      "entropy": 0.09940632618963718,
       "epoch": 1.7333333333333334,
-      "grad_norm": 0.056640625,
-      "learning_rate": 8.807339449541285e-05,
-      "loss": 0.03943218886852264,
-      "mean_token_accuracy": 0.9836909219622612,
+      "grad_norm": 0.11572265625,
+      "learning_rate": 4.403669724770643e-05,
+      "loss": 0.07630330324172974,
+      "mean_token_accuracy": 0.9824694961309433,
       "num_tokens": 333667.0,
       "step": 130
     },
     {
-      "entropy": 0.04643201977014542,
+      "entropy": 0.08718891032040119,
       "epoch": 1.8666666666666667,
-      "grad_norm": 0.04150390625,
-      "learning_rate": 7.889908256880735e-05,
-      "loss": 0.03834928572177887,
-      "mean_token_accuracy": 0.9840005829930305,
+      "grad_norm": 0.083984375,
+      "learning_rate": 3.944954128440367e-05,
+      "loss": 0.0656226098537445,
+      "mean_token_accuracy": 0.9828264027833938,
       "num_tokens": 359316.0,
       "step": 140
     },
     {
-      "entropy": 0.043987272400408985,
+      "entropy": 0.08509592972695827,
       "epoch": 2.0,
-      "grad_norm": 0.04443359375,
-      "learning_rate": 6.972477064220184e-05,
-      "loss": 0.03939533829689026,
-      "mean_token_accuracy": 0.9839684382081032,
+      "grad_norm": 0.0810546875,
+      "learning_rate": 3.486238532110092e-05,
+      "loss": 0.06278945207595825,
+      "mean_token_accuracy": 0.9833807483315468,
       "num_tokens": 384954.0,
       "step": 150
     },
     {
-      "entropy": 0.044071390945464375,
+      "entropy": 0.08264607302844525,
       "epoch": 2.1333333333333333,
-      "grad_norm": 0.045654296875,
-      "learning_rate": 6.055045871559634e-05,
-      "loss": 0.037768739461898806,
-      "mean_token_accuracy": 0.9840289205312729,
+      "grad_norm": 0.09033203125,
+      "learning_rate": 3.027522935779817e-05,
+      "loss": 0.05660240054130554,
+      "mean_token_accuracy": 0.9836767122149468,
       "num_tokens": 410721.0,
       "step": 160
     },
     {
-      "entropy": 0.04337463155388832,
+      "entropy": 0.07673053964972495,
       "epoch": 2.2666666666666666,
-      "grad_norm": 0.046142578125,
-      "learning_rate": 5.137614678899083e-05,
-      "loss": 0.0383589506149292,
-      "mean_token_accuracy": 0.9839346766471863,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 2.5688073394495416e-05,
+      "loss": 0.05474412441253662,
+      "mean_token_accuracy": 0.9835502341389656,
       "num_tokens": 436221.0,
       "step": 170
     },
     {
-      "entropy": 0.043406504299491645,
+      "entropy": 0.07836972028017045,
       "epoch": 2.4,
-      "grad_norm": 0.04150390625,
-      "learning_rate": 4.2201834862385324e-05,
-      "loss": 0.03746289014816284,
-      "mean_token_accuracy": 0.9843998417258263,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 2.1100917431192662e-05,
+      "loss": 0.053261357545852664,
+      "mean_token_accuracy": 0.9844754293560982,
       "num_tokens": 461847.0,
       "step": 180
     },
     {
-      "entropy": 0.04338826853781939,
+      "entropy": 0.07646545991301537,
       "epoch": 2.533333333333333,
-      "grad_norm": 0.044189453125,
-      "learning_rate": 3.302752293577982e-05,
-      "loss": 0.03752565681934357,
-      "mean_token_accuracy": 0.984215758740902,
+      "grad_norm": 0.0986328125,
+      "learning_rate": 1.651376146788991e-05,
+      "loss": 0.05093311071395874,
+      "mean_token_accuracy": 0.9836635038256645,
       "num_tokens": 487546.0,
       "step": 190
     },
     {
-      "entropy": 0.04311536066234112,
+      "entropy": 0.07722862288355828,
       "epoch": 2.6666666666666665,
-      "grad_norm": 0.045654296875,
-      "learning_rate": 2.3853211009174313e-05,
-      "loss": 0.036645838618278505,
-      "mean_token_accuracy": 0.9840914025902748,
+      "grad_norm": 0.08544921875,
+      "learning_rate": 1.1926605504587156e-05,
+      "loss": 0.049432185292243955,
+      "mean_token_accuracy": 0.9839463278651237,
       "num_tokens": 513261.0,
       "step": 200
     },
     {
-      "entropy": 0.04328469494357705,
+      "entropy": 0.07615550812333823,
       "epoch": 2.8,
-      "grad_norm": 0.0419921875,
-      "learning_rate": 1.4678899082568809e-05,
-      "loss": 0.03693516850471497,
-      "mean_token_accuracy": 0.9834129944443702,
+      "grad_norm": 0.08984375,
+      "learning_rate": 7.3394495412844045e-06,
+      "loss": 0.05010167360305786,
+      "mean_token_accuracy": 0.9834628850221634,
       "num_tokens": 538986.0,
       "step": 210
     },
     {
-      "entropy": 0.04334631953388453,
+      "entropy": 0.07667050138115883,
       "epoch": 2.9333333333333336,
-      "grad_norm": 0.049072265625,
-      "learning_rate": 5.504587155963303e-06,
-      "loss": 0.03686155676841736,
-      "mean_token_accuracy": 0.9838820740580558,
+      "grad_norm": 0.09912109375,
+      "learning_rate": 2.7522935779816517e-06,
+      "loss": 0.04939607977867126,
+      "mean_token_accuracy": 0.9840436264872551,
       "num_tokens": 564571.0,
       "step": 220
     }

multi_perspective/checkpoint-225/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b553d221b8edba7787dfe0b6e2e263fd0dab651c55b646b7b9ab1f23a8f3e85b
+oid sha256:74640a2c630b255a3e835c99d1cfb5387b18dad71910ce6a46e078a1ff2aaf18
 size 5649