khowar-ocr-v0.1 — 500 more steps completed successfully

README.md

@@ -41,7 +41,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.05
-- training_steps: 400
+- training_steps: 500
 
 ### Training results
 

adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "DeepseekOCR2ForCausalLM",
     "parent_library": "transformers_modules.deepseek_ocr2.modeling_deepseekocr2"
   },
-  "base_model_name_or_path": "./deepseek_ocr2",
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-OCR-2",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,

checkpoint-300/adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "DeepseekOCR2ForCausalLM",
     "parent_library": "transformers_modules.deepseek_ocr2.modeling_deepseekocr2"
   },
-  "base_model_name_or_path": "./deepseek_ocr2",
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-OCR-2",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -26,12 +26,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "up_proj",
     "gate_proj",
+    "k_proj",
     "o_proj",
     "down_proj",
-    "k_proj",
-    "q_proj",
-    "up_proj",
     "v_proj"
   ],
   "task_type": null,

checkpoint-300/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49225bdfece2f60873c978dfb88841a9fce3e166480222724e92ca74c6b6c3c2
+oid sha256:5f7dbf98848d2336caaba98632684b174e1287c382d40af80627d3df0dd5100b
 size 345908528

checkpoint-300/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0c6c10682cb1ba21dc38d3754d30a6fcc92775de5f8e40f4a77b912ecbed7aa
+oid sha256:49d75fe089936fef213894e79d51a30727a7dff9665780855164f437cb484d86
 size 623793650

checkpoint-300/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88a9347a4cd2db511fcf2930375e7b4afd3d67449bc1459eccfeb525cf4e47d8
+oid sha256:0911d0de7ae88322b7c447d0f2a66e51b5eedf71f2272bb5085f64755fd768ff
 size 1064

checkpoint-300/trainer_state.json

@@ -10,217 +10,217 @@
   "log_history": [
     {
       "epoch": 0.005009078955607038,
-      "grad_norm": 1.5533589124679565,
-      "learning_rate": 5e-05,
-      "loss": 0.95,
+      "grad_norm": 2.341935634613037,
+      "learning_rate": 4e-05,
+      "loss": 0.713,
       "step": 10
     },
     {
       "epoch": 0.010018157911214076,
-      "grad_norm": 1.021743893623352,
-      "learning_rate": 0.0001,
-      "loss": 0.9669,
+      "grad_norm": 1.1017119884490967,
+      "learning_rate": 8e-05,
+      "loss": 0.6786,
       "step": 20
     },
     {
       "epoch": 0.015027236866821113,
-      "grad_norm": 1.259873390197754,
-      "learning_rate": 9.98292246503335e-05,
-      "loss": 0.6369,
+      "grad_norm": 1.0087612867355347,
+      "learning_rate": 9.997266286704631e-05,
+      "loss": 0.3887,
       "step": 30
     },
     {
       "epoch": 0.020036315822428152,
-      "grad_norm": 1.4768264293670654,
-      "learning_rate": 9.931806517013612e-05,
-      "loss": 0.6555,
+      "grad_norm": 1.560015320777893,
+      "learning_rate": 9.975414512725057e-05,
+      "loss": 0.3912,
       "step": 40
     },
     {
       "epoch": 0.02504539477803519,
-      "grad_norm": 1.2998743057250977,
-      "learning_rate": 9.847001329696653e-05,
-      "loss": 0.6878,
+      "grad_norm": 1.2603834867477417,
+      "learning_rate": 9.931806517013612e-05,
+      "loss": 0.4354,
       "step": 50
     },
     {
       "epoch": 0.030054473733642225,
-      "grad_norm": 1.6125634908676147,
-      "learning_rate": 9.729086208503174e-05,
-      "loss": 0.6729,
+      "grad_norm": 1.7070958614349365,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 0.4049,
       "step": 60
     },
     {
       "epoch": 0.03506355268924927,
-      "grad_norm": 1.060158133506775,
-      "learning_rate": 9.578866633275288e-05,
-      "loss": 0.6526,
+      "grad_norm": 0.9318763017654419,
+      "learning_rate": 9.780178907671789e-05,
+      "loss": 0.4252,
       "step": 70
     },
     {
       "epoch": 0.040072631644856305,
-      "grad_norm": 1.2780332565307617,
-      "learning_rate": 9.397368756032445e-05,
-      "loss": 0.6077,
+      "grad_norm": 1.4212697744369507,
+      "learning_rate": 9.672822322997305e-05,
+      "loss": 0.3939,
       "step": 80
     },
     {
       "epoch": 0.04508171060046334,
-      "grad_norm": 1.7625467777252197,
-      "learning_rate": 9.185832391312644e-05,
-      "loss": 0.6803,
+      "grad_norm": 1.7951005697250366,
+      "learning_rate": 9.545032675245813e-05,
+      "loss": 0.4386,
       "step": 90
     },
     {
       "epoch": 0.05009078955607038,
-      "grad_norm": 1.5264769792556763,
-      "learning_rate": 8.945702546981969e-05,
-      "loss": 0.7137,
+      "grad_norm": 1.7150332927703857,
+      "learning_rate": 9.397368756032445e-05,
+      "loss": 0.4666,
       "step": 100
     },
     {
       "epoch": 0.05509986851167741,
-      "grad_norm": 1.1182994842529297,
-      "learning_rate": 8.678619553365659e-05,
-      "loss": 0.4694,
+      "grad_norm": 1.0535022020339966,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": 0.2831,
       "step": 110
     },
     {
       "epoch": 0.06010894746728445,
-      "grad_norm": 1.0322476625442505,
-      "learning_rate": 8.386407858128706e-05,
-      "loss": 0.6061,
+      "grad_norm": 0.8590908646583557,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.3978,
       "step": 120
     },
     {
       "epoch": 0.0651180264228915,
-      "grad_norm": 1.7920445203781128,
-      "learning_rate": 8.07106356344834e-05,
-      "loss": 0.5934,
+      "grad_norm": 1.7438238859176636,
+      "learning_rate": 8.842005554284296e-05,
+      "loss": 0.3853,
       "step": 130
     },
     {
       "epoch": 0.07012710537849853,
-      "grad_norm": 1.217824935913086,
-      "learning_rate": 7.734740790612136e-05,
-      "loss": 0.535,
+      "grad_norm": 1.194357991218567,
+      "learning_rate": 8.622126023955446e-05,
+      "loss": 0.3562,
       "step": 140
     },
     {
       "epoch": 0.07513618433410557,
-      "grad_norm": 0.7182851433753967,
-      "learning_rate": 7.379736965185368e-05,
-      "loss": 0.4449,
+      "grad_norm": 0.38158440589904785,
+      "learning_rate": 8.386407858128706e-05,
+      "loss": 0.2916,
       "step": 150
     },
     {
       "epoch": 0.08014526328971261,
-      "grad_norm": 1.2497895956039429,
-      "learning_rate": 7.008477123264848e-05,
-      "loss": 0.6418,
+      "grad_norm": 1.50730299949646,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 0.4716,
       "step": 160
     },
     {
       "epoch": 0.08515434224531965,
-      "grad_norm": 1.510805368423462,
-      "learning_rate": 6.623497346023418e-05,
-      "loss": 0.5713,
+      "grad_norm": 1.3868156671524048,
+      "learning_rate": 7.871643313414718e-05,
+      "loss": 0.4079,
       "step": 170
     },
     {
       "epoch": 0.09016342120092669,
-      "grad_norm": 1.4163625240325928,
-      "learning_rate": 6.227427435703997e-05,
-      "loss": 0.6913,
+      "grad_norm": 1.6041864156723022,
+      "learning_rate": 7.594847868906076e-05,
+      "loss": 0.5112,
       "step": 180
     },
     {
       "epoch": 0.09517250015653372,
-      "grad_norm": 1.3737024068832397,
-      "learning_rate": 5.8229729514036705e-05,
-      "loss": 0.6378,
+      "grad_norm": 1.4465718269348145,
+      "learning_rate": 7.30670581489344e-05,
+      "loss": 0.441,
       "step": 190
     },
     {
       "epoch": 0.10018157911214076,
-      "grad_norm": 1.7208032608032227,
-      "learning_rate": 5.4128967273616625e-05,
-      "loss": 0.6681,
+      "grad_norm": 1.8322057723999023,
+      "learning_rate": 7.008477123264848e-05,
+      "loss": 0.5155,
       "step": 200
     },
     {
       "epoch": 0.1051906580677478,
-      "grad_norm": 0.9851288795471191,
-      "learning_rate": 5e-05,
-      "loss": 0.3379,
+      "grad_norm": 0.9172443151473999,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 0.2214,
       "step": 210
     },
     {
       "epoch": 0.11019973702335482,
-      "grad_norm": 1.9492233991622925,
-      "learning_rate": 4.5871032726383386e-05,
-      "loss": 0.837,
+      "grad_norm": 2.0696191787719727,
+      "learning_rate": 6.387014543809223e-05,
+      "loss": 0.6761,
       "step": 220
     },
     {
       "epoch": 0.11520881597896186,
-      "grad_norm": 1.1744173765182495,
-      "learning_rate": 4.17702704859633e-05,
-      "loss": 0.7048,
+      "grad_norm": 1.1835525035858154,
+      "learning_rate": 6.066498153718735e-05,
+      "loss": 0.562,
       "step": 230
     },
     {
       "epoch": 0.1202178949345689,
-      "grad_norm": 1.6242769956588745,
-      "learning_rate": 3.772572564296005e-05,
-      "loss": 0.6228,
+      "grad_norm": 1.725269079208374,
+      "learning_rate": 5.74131823855921e-05,
+      "loss": 0.4634,
       "step": 240
     },
     {
       "epoch": 0.12522697389017595,
-      "grad_norm": 1.6513652801513672,
-      "learning_rate": 3.3765026539765834e-05,
-      "loss": 0.7581,
+      "grad_norm": 1.6001545190811157,
+      "learning_rate": 5.4128967273616625e-05,
+      "loss": 0.5877,
       "step": 250
     },
     {
       "epoch": 0.130236052845783,
-      "grad_norm": 2.13556170463562,
-      "learning_rate": 2.991522876735154e-05,
-      "loss": 0.85,
+      "grad_norm": 2.0318245887756348,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": 0.7427,
       "step": 260
     },
     {
       "epoch": 0.13524513180139003,
-      "grad_norm": 1.3880395889282227,
-      "learning_rate": 2.6202630348146324e-05,
-      "loss": 0.8701,
+      "grad_norm": 1.5611522197723389,
+      "learning_rate": 4.7520812266338885e-05,
+      "loss": 0.7619,
       "step": 270
     },
     {
       "epoch": 0.14025421075699707,
-      "grad_norm": 1.7061687707901,
-      "learning_rate": 2.2652592093878666e-05,
-      "loss": 0.822,
+      "grad_norm": 2.1413509845733643,
+      "learning_rate": 4.4225768151520694e-05,
+      "loss": 0.7148,
       "step": 280
     },
     {
       "epoch": 0.1452632897126041,
-      "grad_norm": 1.5672444105148315,
-      "learning_rate": 1.928936436551661e-05,
-      "loss": 0.5852,
+      "grad_norm": 1.696409821510315,
+      "learning_rate": 4.095597328339452e-05,
+      "loss": 0.5038,
       "step": 290
     },
     {
       "epoch": 0.15027236866821114,
-      "grad_norm": 1.853024959564209,
-      "learning_rate": 1.6135921418712956e-05,
-      "loss": 1.0337,
+      "grad_norm": 2.206345796585083,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 0.932,
       "step": 300
     }
   ],
   "logging_steps": 10,
-  "max_steps": 400,
+  "max_steps": 500,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,

checkpoint-300/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a6f41d46c71a1956b46016e3c3993fde308ca40074b3445bf05e27716633acf
+oid sha256:103ad17e257df3fbfb9f1d8f7c2491e0328e0b3d2ad7c52dba2ad40e1f41572e
 size 5304

checkpoint-400/adapter_config.json

@@ -4,7 +4,7 @@
     "base_model_class": "DeepseekOCR2ForCausalLM",
     "parent_library": "transformers_modules.deepseek_ocr2.modeling_deepseekocr2"
   },
-  "base_model_name_or_path": "./deepseek_ocr2",
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-OCR-2",
   "bias": "none",
   "eva_config": null,
   "exclude_modules": null,
@@ -26,12 +26,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
+    "up_proj",
     "gate_proj",
+    "k_proj",
     "o_proj",
     "down_proj",
-    "k_proj",
-    "q_proj",
-    "up_proj",
     "v_proj"
   ],
   "task_type": null,

checkpoint-400/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e802832c88ab0dce2fe774ad959e8706aa7583135171f389a8828126bee74bce
+oid sha256:ed9ab1dd85a38f7e17f44ce49367aaa04d8d9cdfa8c66cdb0414bcecb0a23650
 size 345908528

checkpoint-400/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e31da65a7c8ab75d9128ea0cfa7a0e9660ce0ca4db8cb17c86e3c11386a3ffd6
+oid sha256:eed25658354ac14b8ad7b2f2e61c5dfec746d7d5b29b4716624404aa687f0558
 size 623793650

checkpoint-400/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:705cabf5cbc3a6ab0feb67c77b9b453d59efcc939ce90d310af96e621810f990
+oid sha256:398dc3015f2bdf08ffe15c09b8a80236e704782ceee3d091b17a55a38c21ed1e
 size 1064

checkpoint-400/trainer_state.json

@@ -10,287 +10,287 @@
   "log_history": [
     {
       "epoch": 0.005009078955607038,
-      "grad_norm": 1.5533589124679565,
-      "learning_rate": 5e-05,
-      "loss": 0.95,
+      "grad_norm": 2.341935634613037,
+      "learning_rate": 4e-05,
+      "loss": 0.713,
       "step": 10
     },
     {
       "epoch": 0.010018157911214076,
-      "grad_norm": 1.021743893623352,
-      "learning_rate": 0.0001,
-      "loss": 0.9669,
+      "grad_norm": 1.1017119884490967,
+      "learning_rate": 8e-05,
+      "loss": 0.6786,
       "step": 20
     },
     {
       "epoch": 0.015027236866821113,
-      "grad_norm": 1.259873390197754,
-      "learning_rate": 9.98292246503335e-05,
-      "loss": 0.6369,
+      "grad_norm": 1.0087612867355347,
+      "learning_rate": 9.997266286704631e-05,
+      "loss": 0.3887,
       "step": 30
     },
     {
       "epoch": 0.020036315822428152,
-      "grad_norm": 1.4768264293670654,
-      "learning_rate": 9.931806517013612e-05,
-      "loss": 0.6555,
+      "grad_norm": 1.560015320777893,
+      "learning_rate": 9.975414512725057e-05,
+      "loss": 0.3912,
       "step": 40
     },
     {
       "epoch": 0.02504539477803519,
-      "grad_norm": 1.2998743057250977,
-      "learning_rate": 9.847001329696653e-05,
-      "loss": 0.6878,
+      "grad_norm": 1.2603834867477417,
+      "learning_rate": 9.931806517013612e-05,
+      "loss": 0.4354,
       "step": 50
     },
     {
       "epoch": 0.030054473733642225,
-      "grad_norm": 1.6125634908676147,
-      "learning_rate": 9.729086208503174e-05,
-      "loss": 0.6729,
+      "grad_norm": 1.7070958614349365,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 0.4049,
       "step": 60
     },
     {
       "epoch": 0.03506355268924927,
-      "grad_norm": 1.060158133506775,
-      "learning_rate": 9.578866633275288e-05,
-      "loss": 0.6526,
+      "grad_norm": 0.9318763017654419,
+      "learning_rate": 9.780178907671789e-05,
+      "loss": 0.4252,
       "step": 70
     },
     {
       "epoch": 0.040072631644856305,
-      "grad_norm": 1.2780332565307617,
-      "learning_rate": 9.397368756032445e-05,
-      "loss": 0.6077,
+      "grad_norm": 1.4212697744369507,
+      "learning_rate": 9.672822322997305e-05,
+      "loss": 0.3939,
       "step": 80
     },
     {
       "epoch": 0.04508171060046334,
-      "grad_norm": 1.7625467777252197,
-      "learning_rate": 9.185832391312644e-05,
-      "loss": 0.6803,
+      "grad_norm": 1.7951005697250366,
+      "learning_rate": 9.545032675245813e-05,
+      "loss": 0.4386,
       "step": 90
     },
     {
       "epoch": 0.05009078955607038,
-      "grad_norm": 1.5264769792556763,
-      "learning_rate": 8.945702546981969e-05,
-      "loss": 0.7137,
+      "grad_norm": 1.7150332927703857,
+      "learning_rate": 9.397368756032445e-05,
+      "loss": 0.4666,
       "step": 100
     },
     {
       "epoch": 0.05509986851167741,
-      "grad_norm": 1.1182994842529297,
-      "learning_rate": 8.678619553365659e-05,
-      "loss": 0.4694,
+      "grad_norm": 1.0535022020339966,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": 0.2831,
       "step": 110
     },
     {
       "epoch": 0.06010894746728445,
-      "grad_norm": 1.0322476625442505,
-      "learning_rate": 8.386407858128706e-05,
-      "loss": 0.6061,
+      "grad_norm": 0.8590908646583557,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.3978,
       "step": 120
     },
     {
       "epoch": 0.0651180264228915,
-      "grad_norm": 1.7920445203781128,
-      "learning_rate": 8.07106356344834e-05,
-      "loss": 0.5934,
+      "grad_norm": 1.7438238859176636,
+      "learning_rate": 8.842005554284296e-05,
+      "loss": 0.3853,
       "step": 130
     },
     {
       "epoch": 0.07012710537849853,
-      "grad_norm": 1.217824935913086,
-      "learning_rate": 7.734740790612136e-05,
-      "loss": 0.535,
+      "grad_norm": 1.194357991218567,
+      "learning_rate": 8.622126023955446e-05,
+      "loss": 0.3562,
       "step": 140
     },
     {
       "epoch": 0.07513618433410557,
-      "grad_norm": 0.7182851433753967,
-      "learning_rate": 7.379736965185368e-05,
-      "loss": 0.4449,
+      "grad_norm": 0.38158440589904785,
+      "learning_rate": 8.386407858128706e-05,
+      "loss": 0.2916,
       "step": 150
     },
     {
       "epoch": 0.08014526328971261,
-      "grad_norm": 1.2497895956039429,
-      "learning_rate": 7.008477123264848e-05,
-      "loss": 0.6418,
+      "grad_norm": 1.50730299949646,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 0.4716,
       "step": 160
     },
     {
       "epoch": 0.08515434224531965,
-      "grad_norm": 1.510805368423462,
-      "learning_rate": 6.623497346023418e-05,
-      "loss": 0.5713,
+      "grad_norm": 1.3868156671524048,
+      "learning_rate": 7.871643313414718e-05,
+      "loss": 0.4079,
       "step": 170
     },
     {
       "epoch": 0.09016342120092669,
-      "grad_norm": 1.4163625240325928,
-      "learning_rate": 6.227427435703997e-05,
-      "loss": 0.6913,
+      "grad_norm": 1.6041864156723022,
+      "learning_rate": 7.594847868906076e-05,
+      "loss": 0.5112,
       "step": 180
     },
     {
       "epoch": 0.09517250015653372,
-      "grad_norm": 1.3737024068832397,
-      "learning_rate": 5.8229729514036705e-05,
-      "loss": 0.6378,
+      "grad_norm": 1.4465718269348145,
+      "learning_rate": 7.30670581489344e-05,
+      "loss": 0.441,
       "step": 190
     },
     {
       "epoch": 0.10018157911214076,
-      "grad_norm": 1.7208032608032227,
-      "learning_rate": 5.4128967273616625e-05,
-      "loss": 0.6681,
+      "grad_norm": 1.8322057723999023,
+      "learning_rate": 7.008477123264848e-05,
+      "loss": 0.5155,
       "step": 200
     },
     {
       "epoch": 0.1051906580677478,
-      "grad_norm": 0.9851288795471191,
-      "learning_rate": 5e-05,
-      "loss": 0.3379,
+      "grad_norm": 0.9172443151473999,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 0.2214,
       "step": 210
     },
     {
       "epoch": 0.11019973702335482,
-      "grad_norm": 1.9492233991622925,
-      "learning_rate": 4.5871032726383386e-05,
-      "loss": 0.837,
+      "grad_norm": 2.0696191787719727,
+      "learning_rate": 6.387014543809223e-05,
+      "loss": 0.6761,
       "step": 220
     },
     {
       "epoch": 0.11520881597896186,
-      "grad_norm": 1.1744173765182495,
-      "learning_rate": 4.17702704859633e-05,
-      "loss": 0.7048,
+      "grad_norm": 1.1835525035858154,
+      "learning_rate": 6.066498153718735e-05,
+      "loss": 0.562,
       "step": 230
     },
     {
       "epoch": 0.1202178949345689,
-      "grad_norm": 1.6242769956588745,
-      "learning_rate": 3.772572564296005e-05,
-      "loss": 0.6228,
+      "grad_norm": 1.725269079208374,
+      "learning_rate": 5.74131823855921e-05,
+      "loss": 0.4634,
       "step": 240
     },
     {
       "epoch": 0.12522697389017595,
-      "grad_norm": 1.6513652801513672,
-      "learning_rate": 3.3765026539765834e-05,
-      "loss": 0.7581,
+      "grad_norm": 1.6001545190811157,
+      "learning_rate": 5.4128967273616625e-05,
+      "loss": 0.5877,
       "step": 250
     },
     {
       "epoch": 0.130236052845783,
-      "grad_norm": 2.13556170463562,
-      "learning_rate": 2.991522876735154e-05,
-      "loss": 0.85,
+      "grad_norm": 2.0318245887756348,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": 0.7427,
       "step": 260
     },
     {
       "epoch": 0.13524513180139003,
-      "grad_norm": 1.3880395889282227,
-      "learning_rate": 2.6202630348146324e-05,
-      "loss": 0.8701,
+      "grad_norm": 1.5611522197723389,
+      "learning_rate": 4.7520812266338885e-05,
+      "loss": 0.7619,
       "step": 270
     },
     {
       "epoch": 0.14025421075699707,
-      "grad_norm": 1.7061687707901,
-      "learning_rate": 2.2652592093878666e-05,
-      "loss": 0.822,
+      "grad_norm": 2.1413509845733643,
+      "learning_rate": 4.4225768151520694e-05,
+      "loss": 0.7148,
       "step": 280
     },
     {
       "epoch": 0.1452632897126041,
-      "grad_norm": 1.5672444105148315,
-      "learning_rate": 1.928936436551661e-05,
-      "loss": 0.5852,
+      "grad_norm": 1.696409821510315,
+      "learning_rate": 4.095597328339452e-05,
+      "loss": 0.5038,
       "step": 290
     },
     {
       "epoch": 0.15027236866821114,
-      "grad_norm": 1.853024959564209,
-      "learning_rate": 1.6135921418712956e-05,
-      "loss": 1.0337,
+      "grad_norm": 2.206345796585083,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 0.932,
       "step": 300
     },
     {
       "epoch": 0.15528144762381818,
-      "grad_norm": 2.182626247406006,
-      "learning_rate": 1.3213804466343421e-05,
-      "loss": 0.9183,
+      "grad_norm": 2.31558895111084,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.8383,
       "step": 310
     },
     {
       "epoch": 0.16029052657942522,
-      "grad_norm": 1.6492085456848145,
-      "learning_rate": 1.0542974530180327e-05,
-      "loss": 0.7493,
+      "grad_norm": 1.9436874389648438,
+      "learning_rate": 3.144013755408895e-05,
+      "loss": 0.6804,
       "step": 320
     },
     {
       "epoch": 0.16529960553503226,
-      "grad_norm": 1.4577345848083496,
-      "learning_rate": 8.141676086873572e-06,
-      "loss": 0.8607,
+      "grad_norm": 1.5017071962356567,
+      "learning_rate": 2.8412282383075363e-05,
+      "loss": 0.7921,
       "step": 330
     },
     {
       "epoch": 0.1703086844906393,
-      "grad_norm": 1.6489531993865967,
-      "learning_rate": 6.026312439675552e-06,
-      "loss": 0.8546,
+      "grad_norm": 1.8890794515609741,
+      "learning_rate": 2.547882480847461e-05,
+      "loss": 0.798,
       "step": 340
     },
     {
       "epoch": 0.17531776344624633,
-      "grad_norm": 1.781812071800232,
-      "learning_rate": 4.2113336672471245e-06,
-      "loss": 0.7326,
+      "grad_norm": 1.8801709413528442,
+      "learning_rate": 2.2652592093878666e-05,
+      "loss": 0.6709,
       "step": 350
     },
     {
       "epoch": 0.18032684240185337,
-      "grad_norm": 1.5029524564743042,
-      "learning_rate": 2.7091379149682685e-06,
-      "loss": 0.7797,
+      "grad_norm": 1.6866966485977173,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 0.7196,
       "step": 360
     },
     {
       "epoch": 0.1853359213574604,
-      "grad_norm": 2.3753981590270996,
-      "learning_rate": 1.5299867030334814e-06,
-      "loss": 0.8289,
+      "grad_norm": 2.674154043197632,
+      "learning_rate": 1.7370711923791567e-05,
+      "loss": 0.7524,
       "step": 370
     },
     {
       "epoch": 0.19034500031306745,
-      "grad_norm": 1.7231950759887695,
-      "learning_rate": 6.819348298638839e-07,
-      "loss": 0.913,
+      "grad_norm": 1.852797031402588,
+      "learning_rate": 1.4938160786375572e-05,
+      "loss": 0.8305,
       "step": 380
     },
     {
       "epoch": 0.19535407926867449,
-      "grad_norm": 2.040560722351074,
-      "learning_rate": 1.7077534966650766e-07,
-      "loss": 0.6932,
+      "grad_norm": 2.2271463871002197,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 0.6159,
       "step": 390
     },
     {
       "epoch": 0.20036315822428152,
-      "grad_norm": 1.462962031364441,
-      "learning_rate": 0.0,
-      "loss": 0.7412,
+      "grad_norm": 1.205451250076294,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 0.6024,
       "step": 400
     }
   ],
   "logging_steps": 10,
-  "max_steps": 400,
+  "max_steps": 500,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
@@ -301,7 +301,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }

checkpoint-400/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a6f41d46c71a1956b46016e3c3993fde308ca40074b3445bf05e27716633acf
+oid sha256:103ad17e257df3fbfb9f1d8f7c2491e0328e0b3d2ad7c52dba2ad40e1f41572e
 size 5304

checkpoint-500/README.md

@@ -0,0 +1,202 @@
+---
+base_model: ./deepseek_ocr2
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- 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. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+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).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0

checkpoint-500/adapter_config.json

@@ -0,0 +1,40 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "DeepseekOCR2ForCausalLM",
+    "parent_library": "transformers_modules.deepseek_ocr2.modeling_deepseekocr2"
+  },
+  "base_model_name_or_path": "deepseek-ai/DeepSeek-OCR-2",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "task_type": null,
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-500/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70355edfcc035672f3f590f938de44321bb8d943dc553e79f16a5b22c4337775
+size 345908528

checkpoint-500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae2a8a41e146620ecaae1bf2b5eac7d55f033805eff94516a5f63cff6bb9ac6c
+size 623793650

checkpoint-500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d9cd6a0487226e5bd30d1846894c82af483733ab4381b75bae9c0745e05d405
+size 14244

checkpoint-500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe1d153de177b356f9e3a70d6e4ec979560b0c300994e71ca4cb89afc74c5b3a
+size 1064

checkpoint-500/special_tokens_map.json

@@ -0,0 +1,27 @@
+{
+  "additional_special_tokens": [
+    "<|User|>",
+    "<|Assistant|>"
+  ],
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜▁pad▁｜>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-500/trainer_state.json

@@ -0,0 +1,383 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2504539477803519,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005009078955607038,
+      "grad_norm": 2.341935634613037,
+      "learning_rate": 4e-05,
+      "loss": 0.713,
+      "step": 10
+    },
+    {
+      "epoch": 0.010018157911214076,
+      "grad_norm": 1.1017119884490967,
+      "learning_rate": 8e-05,
+      "loss": 0.6786,
+      "step": 20
+    },
+    {
+      "epoch": 0.015027236866821113,
+      "grad_norm": 1.0087612867355347,
+      "learning_rate": 9.997266286704631e-05,
+      "loss": 0.3887,
+      "step": 30
+    },
+    {
+      "epoch": 0.020036315822428152,
+      "grad_norm": 1.560015320777893,
+      "learning_rate": 9.975414512725057e-05,
+      "loss": 0.3912,
+      "step": 40
+    },
+    {
+      "epoch": 0.02504539477803519,
+      "grad_norm": 1.2603834867477417,
+      "learning_rate": 9.931806517013612e-05,
+      "loss": 0.4354,
+      "step": 50
+    },
+    {
+      "epoch": 0.030054473733642225,
+      "grad_norm": 1.7070958614349365,
+      "learning_rate": 9.86663298624003e-05,
+      "loss": 0.4049,
+      "step": 60
+    },
+    {
+      "epoch": 0.03506355268924927,
+      "grad_norm": 0.9318763017654419,
+      "learning_rate": 9.780178907671789e-05,
+      "loss": 0.4252,
+      "step": 70
+    },
+    {
+      "epoch": 0.040072631644856305,
+      "grad_norm": 1.4212697744369507,
+      "learning_rate": 9.672822322997305e-05,
+      "loss": 0.3939,
+      "step": 80
+    },
+    {
+      "epoch": 0.04508171060046334,
+      "grad_norm": 1.7951005697250366,
+      "learning_rate": 9.545032675245813e-05,
+      "loss": 0.4386,
+      "step": 90
+    },
+    {
+      "epoch": 0.05009078955607038,
+      "grad_norm": 1.7150332927703857,
+      "learning_rate": 9.397368756032445e-05,
+      "loss": 0.4666,
+      "step": 100
+    },
+    {
+      "epoch": 0.05509986851167741,
+      "grad_norm": 1.0535022020339966,
+      "learning_rate": 9.230476262104677e-05,
+      "loss": 0.2831,
+      "step": 110
+    },
+    {
+      "epoch": 0.06010894746728445,
+      "grad_norm": 0.8590908646583557,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 0.3978,
+      "step": 120
+    },
+    {
+      "epoch": 0.0651180264228915,
+      "grad_norm": 1.7438238859176636,
+      "learning_rate": 8.842005554284296e-05,
+      "loss": 0.3853,
+      "step": 130
+    },
+    {
+      "epoch": 0.07012710537849853,
+      "grad_norm": 1.194357991218567,
+      "learning_rate": 8.622126023955446e-05,
+      "loss": 0.3562,
+      "step": 140
+    },
+    {
+      "epoch": 0.07513618433410557,
+      "grad_norm": 0.38158440589904785,
+      "learning_rate": 8.386407858128706e-05,
+      "loss": 0.2916,
+      "step": 150
+    },
+    {
+      "epoch": 0.08014526328971261,
+      "grad_norm": 1.50730299949646,
+      "learning_rate": 8.135881792367686e-05,
+      "loss": 0.4716,
+      "step": 160
+    },
+    {
+      "epoch": 0.08515434224531965,
+      "grad_norm": 1.3868156671524048,
+      "learning_rate": 7.871643313414718e-05,
+      "loss": 0.4079,
+      "step": 170
+    },
+    {
+      "epoch": 0.09016342120092669,
+      "grad_norm": 1.6041864156723022,
+      "learning_rate": 7.594847868906076e-05,
+      "loss": 0.5112,
+      "step": 180
+    },
+    {
+      "epoch": 0.09517250015653372,
+      "grad_norm": 1.4465718269348145,
+      "learning_rate": 7.30670581489344e-05,
+      "loss": 0.441,
+      "step": 190
+    },
+    {
+      "epoch": 0.10018157911214076,
+      "grad_norm": 1.8322057723999023,
+      "learning_rate": 7.008477123264848e-05,
+      "loss": 0.5155,
+      "step": 200
+    },
+    {
+      "epoch": 0.1051906580677478,
+      "grad_norm": 0.9172443151473999,
+      "learning_rate": 6.701465872208216e-05,
+      "loss": 0.2214,
+      "step": 210
+    },
+    {
+      "epoch": 0.11019973702335482,
+      "grad_norm": 2.0696191787719727,
+      "learning_rate": 6.387014543809223e-05,
+      "loss": 0.6761,
+      "step": 220
+    },
+    {
+      "epoch": 0.11520881597896186,
+      "grad_norm": 1.1835525035858154,
+      "learning_rate": 6.066498153718735e-05,
+      "loss": 0.562,
+      "step": 230
+    },
+    {
+      "epoch": 0.1202178949345689,
+      "grad_norm": 1.725269079208374,
+      "learning_rate": 5.74131823855921e-05,
+      "loss": 0.4634,
+      "step": 240
+    },
+    {
+      "epoch": 0.12522697389017595,
+      "grad_norm": 1.6001545190811157,
+      "learning_rate": 5.4128967273616625e-05,
+      "loss": 0.5877,
+      "step": 250
+    },
+    {
+      "epoch": 0.130236052845783,
+      "grad_norm": 2.0318245887756348,
+      "learning_rate": 5.0826697238317935e-05,
+      "loss": 0.7427,
+      "step": 260
+    },
+    {
+      "epoch": 0.13524513180139003,
+      "grad_norm": 1.5611522197723389,
+      "learning_rate": 4.7520812266338885e-05,
+      "loss": 0.7619,
+      "step": 270
+    },
+    {
+      "epoch": 0.14025421075699707,
+      "grad_norm": 2.1413509845733643,
+      "learning_rate": 4.4225768151520694e-05,
+      "loss": 0.7148,
+      "step": 280
+    },
+    {
+      "epoch": 0.1452632897126041,
+      "grad_norm": 1.696409821510315,
+      "learning_rate": 4.095597328339452e-05,
+      "loss": 0.5038,
+      "step": 290
+    },
+    {
+      "epoch": 0.15027236866821114,
+      "grad_norm": 2.206345796585083,
+      "learning_rate": 3.772572564296005e-05,
+      "loss": 0.932,
+      "step": 300
+    },
+    {
+      "epoch": 0.15528144762381818,
+      "grad_norm": 2.31558895111084,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.8383,
+      "step": 310
+    },
+    {
+      "epoch": 0.16029052657942522,
+      "grad_norm": 1.9436874389648438,
+      "learning_rate": 3.144013755408895e-05,
+      "loss": 0.6804,
+      "step": 320
+    },
+    {
+      "epoch": 0.16529960553503226,
+      "grad_norm": 1.5017071962356567,
+      "learning_rate": 2.8412282383075363e-05,
+      "loss": 0.7921,
+      "step": 330
+    },
+    {
+      "epoch": 0.1703086844906393,
+      "grad_norm": 1.8890794515609741,
+      "learning_rate": 2.547882480847461e-05,
+      "loss": 0.798,
+      "step": 340
+    },
+    {
+      "epoch": 0.17531776344624633,
+      "grad_norm": 1.8801709413528442,
+      "learning_rate": 2.2652592093878666e-05,
+      "loss": 0.6709,
+      "step": 350
+    },
+    {
+      "epoch": 0.18032684240185337,
+      "grad_norm": 1.6866966485977173,
+      "learning_rate": 1.9945942635848748e-05,
+      "loss": 0.7196,
+      "step": 360
+    },
+    {
+      "epoch": 0.1853359213574604,
+      "grad_norm": 2.674154043197632,
+      "learning_rate": 1.7370711923791567e-05,
+      "loss": 0.7524,
+      "step": 370
+    },
+    {
+      "epoch": 0.19034500031306745,
+      "grad_norm": 1.852797031402588,
+      "learning_rate": 1.4938160786375572e-05,
+      "loss": 0.8305,
+      "step": 380
+    },
+    {
+      "epoch": 0.19535407926867449,
+      "grad_norm": 2.2271463871002197,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 0.6159,
+      "step": 390
+    },
+    {
+      "epoch": 0.20036315822428152,
+      "grad_norm": 1.205451250076294,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 0.6024,
+      "step": 400
+    },
+    {
+      "epoch": 0.20537223717988856,
+      "grad_norm": 2.6344316005706787,
+      "learning_rate": 8.599558442598998e-06,
+      "loss": 0.7015,
+      "step": 410
+    },
+    {
+      "epoch": 0.2103813161354956,
+      "grad_norm": 2.149989128112793,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 0.5937,
+      "step": 420
+    },
+    {
+      "epoch": 0.2153903950911026,
+      "grad_norm": 2.170044183731079,
+      "learning_rate": 5.263533508961827e-06,
+      "loss": 0.6649,
+      "step": 430
+    },
+    {
+      "epoch": 0.22039947404670965,
+      "grad_norm": 1.7175828218460083,
+      "learning_rate": 3.885512251130763e-06,
+      "loss": 0.6745,
+      "step": 440
+    },
+    {
+      "epoch": 0.22540855300231669,
+      "grad_norm": 1.6916513442993164,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 0.6637,
+      "step": 450
+    },
+    {
+      "epoch": 0.23041763195792372,
+      "grad_norm": 1.7230230569839478,
+      "learning_rate": 1.7395544861325718e-06,
+      "loss": 0.6543,
+      "step": 460
+    },
+    {
+      "epoch": 0.23542671091353076,
+      "grad_norm": 2.5141735076904297,
+      "learning_rate": 9.810017062595322e-07,
+      "loss": 0.8597,
+      "step": 470
+    },
+    {
+      "epoch": 0.2404357898691378,
+      "grad_norm": 1.7556586265563965,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 0.7871,
+      "step": 480
+    },
+    {
+      "epoch": 0.24544486882474484,
+      "grad_norm": 1.4900270700454712,
+      "learning_rate": 1.0931863906127327e-07,
+      "loss": 0.64,
+      "step": 490
+    },
+    {
+      "epoch": 0.2504539477803519,
+      "grad_norm": 1.4064934253692627,
+      "learning_rate": 0.0,
+      "loss": 0.6043,
+      "step": 500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 500,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 9.13229907461568e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:103ad17e257df3fbfb9f1d8f7c2491e0328e0b3d2ad7c52dba2ad40e1f41572e
+size 5304