Upload folder using huggingface_hub

systems_architecture/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: systems_architecture
 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 systems_architecture
 
-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

systems_architecture/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",
     "q_proj",
-    "k_proj"
+    "k_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

systems_architecture/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4ccde16ad0db5d86cd141e83c24cf4669a786b9c1bdbeee61725c6c1119b804
+oid sha256:090857790b746d64c757f8b97f7f906bfd56ffba42c2c494dd4bacd77333af1e
 size 27297544

systems_architecture/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

systems_architecture/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",
     "q_proj",
-    "k_proj"
+    "k_proj",
+    "v_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

systems_architecture/checkpoint-225/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4ccde16ad0db5d86cd141e83c24cf4669a786b9c1bdbeee61725c6c1119b804
+oid sha256:090857790b746d64c757f8b97f7f906bfd56ffba42c2c494dd4bacd77333af1e
 size 27297544

systems_architecture/checkpoint-225/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4f55b4841c53cc63f30ad5cdcd61986d01c604be841d8817fe290605bed0c26
+oid sha256:eec2f778b863f67e218724027f7896bf09feff22f901f34787616e7f10d652bc
 size 54745547

systems_architecture/checkpoint-225/scheduler.pt

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

systems_architecture/checkpoint-225/trainer_state.json

@@ -10,222 +10,222 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "entropy": 3.3168428897857667,
+      "entropy": 3.3974642395973205,
       "epoch": 0.13333333333333333,
-      "grad_norm": 0.703125,
-      "learning_rate": 0.0001981651376146789,
-      "loss": 3.7326873779296874,
-      "mean_token_accuracy": 0.4232572212815285,
+      "grad_norm": 0.45703125,
+      "learning_rate": 9.908256880733946e-05,
+      "loss": 3.9329238891601563,
+      "mean_token_accuracy": 0.4062759779393673,
       "num_tokens": 22402.0,
       "step": 10
     },
     {
-      "entropy": 1.6598962008953095,
+      "entropy": 2.6353378713130953,
       "epoch": 0.26666666666666666,
-      "grad_norm": 0.52734375,
-      "learning_rate": 0.0001889908256880734,
-      "loss": 1.474141788482666,
-      "mean_token_accuracy": 0.6977864518761635,
+      "grad_norm": 0.70703125,
+      "learning_rate": 9.44954128440367e-05,
+      "loss": 2.6810922622680664,
+      "mean_token_accuracy": 0.5217015318572521,
       "num_tokens": 44840.0,
       "step": 20
     },
     {
-      "entropy": 0.32826780080795287,
+      "entropy": 1.259584929049015,
       "epoch": 0.4,
-      "grad_norm": 0.2294921875,
-      "learning_rate": 0.0001798165137614679,
-      "loss": 0.2932713747024536,
-      "mean_token_accuracy": 0.9431452080607414,
+      "grad_norm": 0.91796875,
+      "learning_rate": 8.990825688073395e-05,
+      "loss": 1.0077041625976562,
+      "mean_token_accuracy": 0.7795652016997338,
       "num_tokens": 67271.0,
       "step": 30
     },
     {
-      "entropy": 0.20731838978827,
+      "entropy": 0.35907130502164364,
       "epoch": 0.5333333333333333,
-      "grad_norm": 0.130859375,
-      "learning_rate": 0.0001706422018348624,
-      "loss": 0.18721930980682372,
-      "mean_token_accuracy": 0.9637655198574067,
+      "grad_norm": 0.267578125,
+      "learning_rate": 8.53211009174312e-05,
+      "loss": 0.3161941051483154,
+      "mean_token_accuracy": 0.9379579409956932,
       "num_tokens": 89665.0,
       "step": 40
     },
     {
-      "entropy": 0.17729159593582153,
+      "entropy": 0.22622640170156955,
       "epoch": 0.6666666666666666,
-      "grad_norm": 0.1533203125,
-      "learning_rate": 0.00016146788990825688,
-      "loss": 0.15150076150894165,
-      "mean_token_accuracy": 0.9707357078790665,
+      "grad_norm": 0.19921875,
+      "learning_rate": 8.073394495412844e-05,
+      "loss": 0.20678904056549072,
+      "mean_token_accuracy": 0.9613258004188537,
       "num_tokens": 112054.0,
       "step": 50
     },
     {
-      "entropy": 0.15239670984447,
+      "entropy": 0.1823335137218237,
       "epoch": 0.8,
-      "grad_norm": 0.10107421875,
-      "learning_rate": 0.00015229357798165138,
-      "loss": 0.12725087404251098,
-      "mean_token_accuracy": 0.9726672366261482,
+      "grad_norm": 0.2041015625,
+      "learning_rate": 7.614678899082569e-05,
+      "loss": 0.1693696618080139,
+      "mean_token_accuracy": 0.9662279039621353,
       "num_tokens": 134487.0,
       "step": 60
     },
     {
-      "entropy": 0.1229453705251217,
+      "entropy": 0.16445379257202147,
       "epoch": 0.9333333333333333,
-      "grad_norm": 0.1962890625,
-      "learning_rate": 0.0001431192660550459,
-      "loss": 0.1012193202972412,
-      "mean_token_accuracy": 0.9769004106521606,
+      "grad_norm": 0.146484375,
+      "learning_rate": 7.155963302752295e-05,
+      "loss": 0.15260846614837648,
+      "mean_token_accuracy": 0.9692898988723755,
       "num_tokens": 156897.0,
       "step": 70
     },
     {
-      "entropy": 0.08543421998620034,
+      "entropy": 0.16030707024037838,
       "epoch": 1.0666666666666667,
-      "grad_norm": 0.08447265625,
-      "learning_rate": 0.00013394495412844036,
-      "loss": 0.08416919708251953,
-      "mean_token_accuracy": 0.979321151971817,
+      "grad_norm": 0.1650390625,
+      "learning_rate": 6.697247706422018e-05,
+      "loss": 0.14007102251052855,
+      "mean_token_accuracy": 0.9711064517498016,
       "num_tokens": 179260.0,
       "step": 80
     },
     {
-      "entropy": 0.08846638891845941,
+      "entropy": 0.14983807913959027,
       "epoch": 1.2,
-      "grad_norm": 0.09375,
-      "learning_rate": 0.00012477064220183488,
-      "loss": 0.07037656307220459,
-      "mean_token_accuracy": 0.9801889300346375,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 6.238532110091744e-05,
+      "loss": 0.1279125452041626,
+      "mean_token_accuracy": 0.9731644049286843,
       "num_tokens": 201692.0,
       "step": 90
     },
     {
-      "entropy": 0.08574241194874048,
+      "entropy": 0.1436021264642477,
       "epoch": 1.3333333333333333,
-      "grad_norm": 0.08544921875,
-      "learning_rate": 0.00011559633027522936,
-      "loss": 0.05919719934463501,
-      "mean_token_accuracy": 0.980514743924141,
+      "grad_norm": 0.1435546875,
+      "learning_rate": 5.779816513761468e-05,
+      "loss": 0.11760237216949462,
+      "mean_token_accuracy": 0.9774747937917709,
       "num_tokens": 224049.0,
       "step": 100
     },
     {
-      "entropy": 0.08276224136352539,
+      "entropy": 0.1345849795266986,
       "epoch": 1.4666666666666668,
-      "grad_norm": 0.09912109375,
-      "learning_rate": 0.00010642201834862387,
-      "loss": 0.05210116505622864,
-      "mean_token_accuracy": 0.9806599587202072,
+      "grad_norm": 0.16796875,
+      "learning_rate": 5.3211009174311934e-05,
+      "loss": 0.11276495456695557,
+      "mean_token_accuracy": 0.9773114666342735,
       "num_tokens": 246511.0,
       "step": 110
     },
     {
-      "entropy": 0.07124831397086381,
+      "entropy": 0.13258265592157842,
       "epoch": 1.6,
-      "grad_norm": 0.05517578125,
-      "learning_rate": 9.724770642201836e-05,
-      "loss": 0.04895032346248627,
-      "mean_token_accuracy": 0.9810128688812256,
+      "grad_norm": 0.1357421875,
+      "learning_rate": 4.862385321100918e-05,
+      "loss": 0.10859922170639039,
+      "mean_token_accuracy": 0.9765869408845902,
       "num_tokens": 268928.0,
       "step": 120
     },
     {
-      "entropy": 0.06570714842528105,
+      "entropy": 0.1305014956742525,
       "epoch": 1.7333333333333334,
-      "grad_norm": 0.09130859375,
-      "learning_rate": 8.807339449541285e-05,
-      "loss": 0.04789784550666809,
-      "mean_token_accuracy": 0.9804875090718269,
+      "grad_norm": 0.294921875,
+      "learning_rate": 4.403669724770643e-05,
+      "loss": 0.10547425746917724,
+      "mean_token_accuracy": 0.978062030673027,
       "num_tokens": 291299.0,
       "step": 130
     },
     {
-      "entropy": 0.05858572842553258,
+      "entropy": 0.1275184964761138,
       "epoch": 1.8666666666666667,
-      "grad_norm": 0.064453125,
-      "learning_rate": 7.889908256880735e-05,
-      "loss": 0.04485383927822113,
-      "mean_token_accuracy": 0.9811065629124641,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 3.944954128440367e-05,
+      "loss": 0.09215458631515502,
+      "mean_token_accuracy": 0.980167718231678,
       "num_tokens": 313720.0,
       "step": 140
     },
     {
-      "entropy": 0.05700928270816803,
+      "entropy": 0.10470381081104278,
       "epoch": 2.0,
-      "grad_norm": 0.050537109375,
-      "learning_rate": 6.972477064220184e-05,
-      "loss": 0.04462524354457855,
-      "mean_token_accuracy": 0.9801488563418388,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 3.486238532110092e-05,
+      "loss": 0.0803648591041565,
+      "mean_token_accuracy": 0.9798836871981621,
       "num_tokens": 336120.0,
       "step": 150
     },
     {
-      "entropy": 0.053518883883953094,
+      "entropy": 0.09639436881989241,
       "epoch": 2.1333333333333333,
-      "grad_norm": 0.049560546875,
-      "learning_rate": 6.055045871559634e-05,
-      "loss": 0.043404501676559445,
-      "mean_token_accuracy": 0.9804914385080338,
+      "grad_norm": 0.126953125,
+      "learning_rate": 3.027522935779817e-05,
+      "loss": 0.07193467020988464,
+      "mean_token_accuracy": 0.9803527981042862,
       "num_tokens": 358557.0,
       "step": 160
     },
     {
-      "entropy": 0.05389656974002719,
+      "entropy": 0.090707191452384,
       "epoch": 2.2666666666666666,
-      "grad_norm": 0.07373046875,
-      "learning_rate": 5.137614678899083e-05,
-      "loss": 0.042660146951675415,
-      "mean_token_accuracy": 0.9813649311661721,
+      "grad_norm": 0.162109375,
+      "learning_rate": 2.5688073394495416e-05,
+      "loss": 0.06692627668380738,
+      "mean_token_accuracy": 0.9809125855565071,
       "num_tokens": 380965.0,
       "step": 170
     },
     {
-      "entropy": 0.05118206962943077,
+      "entropy": 0.09282380174845457,
       "epoch": 2.4,
-      "grad_norm": 0.06982421875,
-      "learning_rate": 4.2201834862385324e-05,
-      "loss": 0.043095368146896365,
-      "mean_token_accuracy": 0.9810103073716163,
+      "grad_norm": 0.1259765625,
+      "learning_rate": 2.1100917431192662e-05,
+      "loss": 0.06534491777420044,
+      "mean_token_accuracy": 0.9811898991465569,
       "num_tokens": 403375.0,
       "step": 180
     },
     {
-      "entropy": 0.05230644857510924,
+      "entropy": 0.09065835271030664,
       "epoch": 2.533333333333333,
-      "grad_norm": 0.060302734375,
-      "learning_rate": 3.302752293577982e-05,
-      "loss": 0.04297981262207031,
-      "mean_token_accuracy": 0.9805112361907959,
+      "grad_norm": 0.13671875,
+      "learning_rate": 1.651376146788991e-05,
+      "loss": 0.06384796500205994,
+      "mean_token_accuracy": 0.9804614961147309,
       "num_tokens": 425827.0,
       "step": 190
     },
     {
-      "entropy": 0.05161624262109399,
+      "entropy": 0.09005609489977359,
       "epoch": 2.6666666666666665,
-      "grad_norm": 0.06298828125,
-      "learning_rate": 2.3853211009174313e-05,
-      "loss": 0.04285256862640381,
-      "mean_token_accuracy": 0.9807584524154663,
+      "grad_norm": 0.115234375,
+      "learning_rate": 1.1926605504587156e-05,
+      "loss": 0.06266740560531617,
+      "mean_token_accuracy": 0.9807602107524872,
       "num_tokens": 448146.0,
       "step": 200
     },
     {
-      "entropy": 0.052343995217233895,
+      "entropy": 0.09147516060620546,
       "epoch": 2.8,
-      "grad_norm": 0.0537109375,
-      "learning_rate": 1.4678899082568809e-05,
-      "loss": 0.04282132387161255,
-      "mean_token_accuracy": 0.9799860909581184,
+      "grad_norm": 0.1162109375,
+      "learning_rate": 7.3394495412844045e-06,
+      "loss": 0.06145778894424438,
+      "mean_token_accuracy": 0.980523382127285,
       "num_tokens": 470550.0,
       "step": 210
     },
     {
-      "entropy": 0.05234320750460029,
+      "entropy": 0.0895681083202362,
       "epoch": 2.9333333333333336,
-      "grad_norm": 0.06640625,
-      "learning_rate": 5.504587155963303e-06,
-      "loss": 0.042635363340377805,
-      "mean_token_accuracy": 0.9812853425741196,
+      "grad_norm": 0.146484375,
+      "learning_rate": 2.7522935779816517e-06,
+      "loss": 0.06185387372970581,
+      "mean_token_accuracy": 0.9815465867519378,
       "num_tokens": 492952.0,
       "step": 220
     }

systems_architecture/checkpoint-225/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7adf5366e1f3a3d177f0801d84e2b0efb8b20382389e4d5d492b16ad5565e16
+oid sha256:e89ffd6706997547e92f8e96a78362609b8425c713339ec6f652edb11a0286eb
 size 5649