Initial upload of fine‑tuned Gemma + custom tokenizer

model-00001-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b4985a44b48184c143af3be5ef245eb45ecbb681e2ec90a4cba5ffe6f095f1b
+oid sha256:482be2455e637e399de5e4c8afaec5d2675ec11f89137e526362b82b23cedb4b
 size 4979902192

model-00002-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7b2e6c318860d148d9bea44b00483547b2ea9dd51e5b1214e833c256e5246ff
+oid sha256:43f80968dd4e284d30ed74416856e65c7344cb8ed822d3f833e711249692160e
 size 4931296592

model-00003-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615d3804cc1fd49aa251b169db0ecb27ca6a6a7c35a47cea5b3d3b384302ee97
+oid sha256:0eb6398002e8b6604cef8459094542dcccbfd027bacd105d4a9c82f95ea16192
 size 4931296656

model-00004-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b048f3a29f3dddc0fbbe3e90ecff68d76073458a01befffaa93289bca652f80
+oid sha256:3c9e1e56ed4e0108727c4c549ee28ec2af3da9f48369c8fad1527a2978d19e20
 size 4931296656

model-00005-of-00005.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b7e987800cdca2218c8a4d14167ddb87ee3396cef0b40a282557ec708e92f2c
+oid sha256:48f435f220bcf30ac3f7e864f113cdf55f1c2d86b35674047ab703a957ec75a5
 size 4601000928

scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f614219902f7ff2c52abf6315720ed82231175199ef520d9eb861fdd96b6edb8
+oid sha256:81e125f2538e139197e1ffe42d2e924ff12ed600a2b3c103b6ba772812143b1d
 size 1465

tokenizer_config.json

@@ -1107,7 +1107,7 @@
       "special": false
     },
     "138": {
-      "content": "\u2581\u2581",
+      "content": "▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1115,7 +1115,7 @@
       "special": false
     },
     "139": {
-      "content": "\u2581\u2581\u2581",
+      "content": "▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1123,7 +1123,7 @@
       "special": false
     },
     "140": {
-      "content": "\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1131,7 +1131,7 @@
       "special": false
     },
     "141": {
-      "content": "\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1139,7 +1139,7 @@
       "special": false
     },
     "142": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1147,7 +1147,7 @@
       "special": false
     },
     "143": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1155,7 +1155,7 @@
       "special": false
     },
     "144": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1163,7 +1163,7 @@
       "special": false
     },
     "145": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1171,7 +1171,7 @@
       "special": false
     },
     "146": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1179,7 +1179,7 @@
       "special": false
     },
     "147": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1187,7 +1187,7 @@
       "special": false
     },
     "148": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1195,7 +1195,7 @@
       "special": false
     },
     "149": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1203,7 +1203,7 @@
       "special": false
     },
     "150": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1211,7 +1211,7 @@
       "special": false
     },
     "151": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1219,7 +1219,7 @@
       "special": false
     },
     "152": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1227,7 +1227,7 @@
       "special": false
     },
     "153": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1235,7 +1235,7 @@
       "special": false
     },
     "154": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1243,7 +1243,7 @@
       "special": false
     },
     "155": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1251,7 +1251,7 @@
       "special": false
     },
     "156": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1259,7 +1259,7 @@
       "special": false
     },
     "157": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1267,7 +1267,7 @@
       "special": false
     },
     "158": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1275,7 +1275,7 @@
       "special": false
     },
     "159": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1283,7 +1283,7 @@
       "special": false
     },
     "160": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1291,7 +1291,7 @@
       "special": false
     },
     "161": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1299,7 +1299,7 @@
       "special": false
     },
     "162": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1307,7 +1307,7 @@
       "special": false
     },
     "163": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1315,7 +1315,7 @@
       "special": false
     },
     "164": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1323,7 +1323,7 @@
       "special": false
     },
     "165": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1331,7 +1331,7 @@
       "special": false
     },
     "166": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -1339,7 +1339,7 @@
       "special": false
     },
     "167": {
-      "content": "\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581\u2581",
+      "content": "▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁▁",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -51326,7 +51326,6 @@
   "boi_token": "<start_of_image>",
   "bos_token": "<bos>",
   "clean_up_tokenization_spaces": false,
-  "end_string": "<end_of_turn>",
   "eoi_token": "<end_of_image>",
   "eos_token": "<eos>",
   "extra_special_tokens": {
@@ -51337,16 +51336,10 @@
   "image_token": "<image_soft_token>",
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
+  "processor_class": "Gemma3Processor",
   "sp_model_kwargs": null,
   "spaces_between_special_tokens": false,
-  "start_string": "<start_of_turn>",
-  "tokenizer_class": "GemmaSpecialTokenizer",
+  "tokenizer_class": "GemmaTokenizerFast",
   "unk_token": "<unk>",
-  "use_default_system_prompt": false,
-  "auto_map": {
-    "AutoTokenizer": [
-      "gemma_special_tokenizer.GemmaSpecialTokenizer",
-      "gemma_special_tokenizer.GemmaSpecialTokenizer"
-    ]
-  }
-}
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -2,7 +2,7 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.1959058733499139,
+  "epoch": 0.5877457310948486,
   "eval_steps": 32,
   "global_step": 8,
   "is_hyper_param_search": false,
@@ -10,80 +10,80 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.02448823416873924,
-      "grad_norm": 29817.93994076611,
+      "epoch": 0.07346821638685608,
+      "grad_norm": 52224.03643740955,
       "learning_rate": 3e-06,
-      "loss": 604.7336,
-      "mean_token_accuracy": 0.5841934891068377,
-      "num_tokens": 834003.0,
+      "loss": 1232.5903,
+      "mean_token_accuracy": 0.5698598268500064,
+      "num_tokens": 2439700.0,
       "step": 1
     },
     {
-      "epoch": 0.04897646833747848,
-      "grad_norm": 13378.067339306495,
-      "learning_rate": 2.925e-06,
-      "loss": 501.2048,
-      "mean_token_accuracy": 0.5982158905826509,
-      "num_tokens": 1643975.0,
+      "epoch": 0.14693643277371216,
+      "grad_norm": 24564.28249818258,
+      "learning_rate": 2.7692307692307693e-06,
+      "loss": 1012.342,
+      "mean_token_accuracy": 0.5935460063046776,
+      "num_tokens": 4818537.0,
       "step": 2
     },
     {
-      "epoch": 0.07346470250621771,
-      "grad_norm": 4566.448298220422,
-      "learning_rate": 2.85e-06,
-      "loss": 375.0333,
-      "mean_token_accuracy": 0.6305847020121291,
-      "num_tokens": 2439700.0,
+      "epoch": 0.22040464916056823,
+      "grad_norm": 10030.685256076777,
+      "learning_rate": 2.5384615384615385e-06,
+      "loss": 771.7506,
+      "mean_token_accuracy": 0.6206552012590691,
+      "num_tokens": 7222999.0,
       "step": 3
     },
     {
-      "epoch": 0.09795293667495696,
-      "grad_norm": 6019.372015429163,
-      "learning_rate": 2.775e-06,
-      "loss": 369.5743,
-      "mean_token_accuracy": 0.6201298969099298,
-      "num_tokens": 3224139.0,
+      "epoch": 0.2938728655474243,
+      "grad_norm": 9797.578497343955,
+      "learning_rate": 2.307692307692308e-06,
+      "loss": 673.8949,
+      "mean_token_accuracy": 0.6229124862584285,
+      "num_tokens": 9603627.0,
       "step": 4
     },
     {
-      "epoch": 0.1224411708436962,
-      "grad_norm": 5316.727220921461,
-      "learning_rate": 2.7e-06,
-      "loss": 353.3683,
-      "mean_token_accuracy": 0.6273049607407302,
-      "num_tokens": 4025450.0,
+      "epoch": 0.3673410819342804,
+      "grad_norm": 6906.536059477202,
+      "learning_rate": 2.076923076923077e-06,
+      "loss": 647.7118,
+      "mean_token_accuracy": 0.6252844646223821,
+      "num_tokens": 12031078.0,
       "step": 5
     },
     {
-      "epoch": 0.14692940501243543,
-      "grad_norm": 2361.5776737530314,
-      "learning_rate": 2.6250000000000003e-06,
-      "loss": 315.4971,
-      "mean_token_accuracy": 0.6325392066501081,
-      "num_tokens": 4818537.0,
+      "epoch": 0.44080929832113647,
+      "grad_norm": 4121.501080449312,
+      "learning_rate": 1.8461538461538462e-06,
+      "loss": 616.8495,
+      "mean_token_accuracy": 0.6341593922115862,
+      "num_tokens": 14403431.0,
       "step": 6
     },
     {
-      "epoch": 0.17141763918117467,
-      "grad_norm": 1222.350631373476,
-      "learning_rate": 2.55e-06,
-      "loss": 290.5888,
-      "mean_token_accuracy": 0.6436414200579748,
-      "num_tokens": 5621502.0,
+      "epoch": 0.5142775147079925,
+      "grad_norm": 2026.657249791317,
+      "learning_rate": 1.6153846153846154e-06,
+      "loss": 601.5251,
+      "mean_token_accuracy": 0.6352307246997952,
+      "num_tokens": 16811979.0,
       "step": 7
     },
     {
-      "epoch": 0.1959058733499139,
-      "grad_norm": 1481.1270011064446,
-      "learning_rate": 2.475e-06,
-      "loss": 304.7263,
-      "mean_token_accuracy": 0.6306580123491585,
-      "num_tokens": 6419957.0,
+      "epoch": 0.5877457310948486,
+      "grad_norm": 1892.3110141436696,
+      "learning_rate": 1.3846153846153846e-06,
+      "loss": 577.3281,
+      "mean_token_accuracy": 0.6342741788248532,
+      "num_tokens": 19217660.0,
       "step": 8
     }
   ],
   "logging_steps": 1,
-  "max_steps": 40,
+  "max_steps": 13,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 8,
@@ -99,7 +99,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 42919320092672.0,
+  "total_flos": 128626689310720.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:120fb2dbabf3988fbddcfbd028d63dc7696d4bdf2d232abaed0310ab85177cb1
+oid sha256:1e21928f1882517a4b05718e3914cb90eb7110650d66245962ef389df1995890
 size 7377