Training in progress, step 11000, checkpoint

last-checkpoint/adapter_config.json

@@ -30,15 +30,15 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "w3",
+    "o_proj",
     "w2",
+    "v_proj",
     "in_proj",
-    "q_proj",
-    "w1",
     "k_proj",
-    "v_proj",
-    "o_proj",
-    "out_proj",
-    "w3"
+    "w1",
+    "q_proj",
+    "out_proj"
   ],
   "target_parameters": null,
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d59a26df247a9b3bd089944c699df5332df994dda9c303c5de94dc6e76616eb9
+oid sha256:876bf2f546a16e66b1d5b81efcc3b757b40c90d136c0bdd643dee18ae72ba4c1
 size 88891320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca1ac60d2a733c3f6db08f04b7d8d4f6547bd586f287c155721433e984edc7db
+oid sha256:57b99207e2edc2d8b8d7f13efb8c11b63b5f6374a8be4b5b83167f67732aff8a
 size 177891851

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6b6744a57f42273e871a115e82b156c17e0c93e4839b3bac6dc6f53f8600e91
+oid sha256:935587dfa7e9695b710001cc4640f6932aff424723f73c2772e428b8fa162cd0
 size 14917

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79bfae6c501e0b8cd471ca11801529a5af1b0faa0b363fbd03730ca881075ee9
+oid sha256:b452a4dfd8c45345d4331e88276063f93624ba1c02b98958ef3acceab4b72552
 size 14917

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb1f23b3450b5ea7f3c2c09c828367f5357644ec38f3b3af648f0d2bda902fef
+oid sha256:a773e06d1e48e9106de4ef1143ab58f5c3fbab6375b9b2d8da7aebd76ee5f3e4
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 10750,
-  "best_metric": 0.28601643443107605,
-  "best_model_checkpoint": "./lfm25-kodcode-lora/checkpoint-10750",
-  "epoch": 0.8144093638137085,
+  "best_global_step": 11000,
+  "best_metric": 0.28569018840789795,
+  "best_model_checkpoint": "./lfm25-kodcode-lora/checkpoint-11000",
+  "epoch": 0.833349116460539,
   "eval_steps": 250,
-  "global_step": 10750,
+  "global_step": 11000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11231,6 +11231,267 @@
       "eval_samples_per_second": 5.851,
       "eval_steps_per_second": 1.464,
       "step": 10750
+    },
+    {
+      "entropy": 0.2615930700674653,
+      "epoch": 0.8151669539195818,
+      "grad_norm": 0.4948700964450836,
+      "learning_rate": 8.70287588830654e-06,
+      "loss": 0.30023128986358644,
+      "mean_token_accuracy": 0.9172126367688179,
+      "num_tokens": 95394.0,
+      "step": 10760
+    },
+    {
+      "entropy": 0.26154228337109087,
+      "epoch": 0.815924544025455,
+      "grad_norm": 0.3987369239330292,
+      "learning_rate": 8.633838805669543e-06,
+      "loss": 0.3083802223205566,
+      "mean_token_accuracy": 0.916927844285965,
+      "num_tokens": 198965.0,
+      "step": 10770
+    },
+    {
+      "entropy": 0.29399398546665906,
+      "epoch": 0.8166821341313283,
+      "grad_norm": 0.4157302677631378,
+      "learning_rate": 8.565050754034847e-06,
+      "loss": 0.330983567237854,
+      "mean_token_accuracy": 0.907181803882122,
+      "num_tokens": 300936.0,
+      "step": 10780
+    },
+    {
+      "entropy": 0.2811663061380386,
+      "epoch": 0.8174397242372015,
+      "grad_norm": 0.41286197304725647,
+      "learning_rate": 8.496512147517688e-06,
+      "loss": 0.3124821662902832,
+      "mean_token_accuracy": 0.9098848760128021,
+      "num_tokens": 407545.0,
+      "step": 10790
+    },
+    {
+      "entropy": 0.29347006008028986,
+      "epoch": 0.8181973143430746,
+      "grad_norm": 0.4638175666332245,
+      "learning_rate": 8.428223398731588e-06,
+      "loss": 0.32779746055603026,
+      "mean_token_accuracy": 0.9062278017401695,
+      "num_tokens": 511306.0,
+      "step": 10800
+    },
+    {
+      "entropy": 0.3169729994609952,
+      "epoch": 0.8189549044489479,
+      "grad_norm": 0.6172231435775757,
+      "learning_rate": 8.360184918785902e-06,
+      "loss": 0.3641566038131714,
+      "mean_token_accuracy": 0.8966098591685295,
+      "num_tokens": 615936.0,
+      "step": 10810
+    },
+    {
+      "entropy": 0.28694524206221106,
+      "epoch": 0.8197124945548211,
+      "grad_norm": 0.5250155925750732,
+      "learning_rate": 8.292397117283318e-06,
+      "loss": 0.3268028974533081,
+      "mean_token_accuracy": 0.9117160573601722,
+      "num_tokens": 707912.0,
+      "step": 10820
+    },
+    {
+      "entropy": 0.2993797710165381,
+      "epoch": 0.8204700846606944,
+      "grad_norm": 0.450602650642395,
+      "learning_rate": 8.224860402317398e-06,
+      "loss": 0.3751563549041748,
+      "mean_token_accuracy": 0.9021484076976776,
+      "num_tokens": 797927.0,
+      "step": 10830
+    },
+    {
+      "entropy": 0.2887501694262028,
+      "epoch": 0.8212276747665676,
+      "grad_norm": 0.3982142210006714,
+      "learning_rate": 8.157575180470139e-06,
+      "loss": 0.3479593276977539,
+      "mean_token_accuracy": 0.9077468276023865,
+      "num_tokens": 904264.0,
+      "step": 10840
+    },
+    {
+      "entropy": 0.30117298644036056,
+      "epoch": 0.8219852648724407,
+      "grad_norm": 0.4184916913509369,
+      "learning_rate": 8.090541856809465e-06,
+      "loss": 0.33893485069274903,
+      "mean_token_accuracy": 0.9050878256559372,
+      "num_tokens": 1007433.0,
+      "step": 10850
+    },
+    {
+      "entropy": 0.30625202376395466,
+      "epoch": 0.822742854978314,
+      "grad_norm": 0.43937817215919495,
+      "learning_rate": 8.02376083488688e-06,
+      "loss": 0.34802818298339844,
+      "mean_token_accuracy": 0.9029570311307907,
+      "num_tokens": 1106432.0,
+      "step": 10860
+    },
+    {
+      "entropy": 0.29251224398612974,
+      "epoch": 0.8235004450841872,
+      "grad_norm": 0.4894697964191437,
+      "learning_rate": 7.957232516734963e-06,
+      "loss": 0.35279672145843505,
+      "mean_token_accuracy": 0.9066073164343834,
+      "num_tokens": 1204980.0,
+      "step": 10870
+    },
+    {
+      "entropy": 0.3121814550831914,
+      "epoch": 0.8242580351900605,
+      "grad_norm": 0.451427698135376,
+      "learning_rate": 7.890957302865e-06,
+      "loss": 0.37927200794219973,
+      "mean_token_accuracy": 0.8981422513723374,
+      "num_tokens": 1305202.0,
+      "step": 10880
+    },
+    {
+      "entropy": 0.29268699828535316,
+      "epoch": 0.8250156252959336,
+      "grad_norm": 0.3992355465888977,
+      "learning_rate": 7.82493559226451e-06,
+      "loss": 0.3250342607498169,
+      "mean_token_accuracy": 0.9062216132879257,
+      "num_tokens": 1407868.0,
+      "step": 10890
+    },
+    {
+      "entropy": 0.36002040691673753,
+      "epoch": 0.8257732154018068,
+      "grad_norm": 0.4525466561317444,
+      "learning_rate": 7.759167782394916e-06,
+      "loss": 0.4119568824768066,
+      "mean_token_accuracy": 0.8839563131332397,
+      "num_tokens": 1513950.0,
+      "step": 10900
+    },
+    {
+      "entropy": 0.30947884283959864,
+      "epoch": 0.8265308055076801,
+      "grad_norm": 0.4585402309894562,
+      "learning_rate": 7.69365426918911e-06,
+      "loss": 0.3610663414001465,
+      "mean_token_accuracy": 0.9016437903046608,
+      "num_tokens": 1613270.0,
+      "step": 10910
+    },
+    {
+      "entropy": 0.29806773774325845,
+      "epoch": 0.8272883956135533,
+      "grad_norm": 0.43951550126075745,
+      "learning_rate": 7.628395447049058e-06,
+      "loss": 0.34964966773986816,
+      "mean_token_accuracy": 0.9043863728642464,
+      "num_tokens": 1710564.0,
+      "step": 10920
+    },
+    {
+      "entropy": 0.27706831842660906,
+      "epoch": 0.8280459857194266,
+      "grad_norm": 0.43634042143821716,
+      "learning_rate": 7.563391708843465e-06,
+      "loss": 0.31148567199707033,
+      "mean_token_accuracy": 0.9122755557298661,
+      "num_tokens": 1804996.0,
+      "step": 10930
+    },
+    {
+      "entropy": 0.33176610227674247,
+      "epoch": 0.8288035758252997,
+      "grad_norm": 0.39294061064720154,
+      "learning_rate": 7.498643445905385e-06,
+      "loss": 0.37499704360961916,
+      "mean_token_accuracy": 0.8953326553106308,
+      "num_tokens": 1914019.0,
+      "step": 10940
+    },
+    {
+      "entropy": 0.2956154864281416,
+      "epoch": 0.8295611659311729,
+      "grad_norm": 0.4650717079639435,
+      "learning_rate": 7.434151048029858e-06,
+      "loss": 0.3409877777099609,
+      "mean_token_accuracy": 0.9076192870736122,
+      "num_tokens": 2009215.0,
+      "step": 10950
+    },
+    {
+      "entropy": 0.30589213948696853,
+      "epoch": 0.8303187560370462,
+      "grad_norm": 0.422702819108963,
+      "learning_rate": 7.369914903471592e-06,
+      "loss": 0.3454046487808228,
+      "mean_token_accuracy": 0.9033974334597588,
+      "num_tokens": 2113318.0,
+      "step": 10960
+    },
+    {
+      "entropy": 0.2733181806281209,
+      "epoch": 0.8310763461429194,
+      "grad_norm": 0.47341540455818176,
+      "learning_rate": 7.305935398942598e-06,
+      "loss": 0.3034660816192627,
+      "mean_token_accuracy": 0.9125015497207641,
+      "num_tokens": 2212212.0,
+      "step": 10970
+    },
+    {
+      "entropy": 0.32005896270275114,
+      "epoch": 0.8318339362487925,
+      "grad_norm": 0.4640633761882782,
+      "learning_rate": 7.2422129196098695e-06,
+      "loss": 0.3682070255279541,
+      "mean_token_accuracy": 0.8993272170424461,
+      "num_tokens": 2309913.0,
+      "step": 10980
+    },
+    {
+      "entropy": 0.29598398655653,
+      "epoch": 0.8325915263546658,
+      "grad_norm": 0.43602728843688965,
+      "learning_rate": 7.178747849093093e-06,
+      "loss": 0.34798197746276854,
+      "mean_token_accuracy": 0.9048758611083031,
+      "num_tokens": 2406011.0,
+      "step": 10990
+    },
+    {
+      "entropy": 0.2882571941241622,
+      "epoch": 0.833349116460539,
+      "grad_norm": 0.3429960608482361,
+      "learning_rate": 7.115540569462254e-06,
+      "loss": 0.31615209579467773,
+      "mean_token_accuracy": 0.9083688676357269,
+      "num_tokens": 2498979.0,
+      "step": 11000
+    },
+    {
+      "epoch": 0.833349116460539,
+      "eval_entropy": 0.2886375365185827,
+      "eval_loss": 0.28569018840789795,
+      "eval_mean_token_accuracy": 0.9073382049017631,
+      "eval_num_tokens": 2498979.0,
+      "eval_runtime": 363.4037,
+      "eval_samples_per_second": 5.872,
+      "eval_steps_per_second": 1.469,
+      "step": 11000
     }
   ],
   "logging_steps": 10,
@@ -11250,7 +11511,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.324210024475525e+17,
+  "total_flos": 9.542564066665431e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null