Training in progress, step 1500, checkpoint

checkpoint-1500/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:705c4eaafb29cbb5c51ac3933aa81e407fa299f13dd388c6123fb1bfb647366f
+oid sha256:b68efd460b8ff422f4f39719caae36d6af76a96f24ab2ccca930129b9aa6200c
 size 4946584368

checkpoint-1500/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efb9dd60958c6c89dbf54d986b9dcac8bbd65bfb9fb82738c41c5f5a4c1ed366
+oid sha256:8acb1e88adbc3b7cb06eb5fe90db343a10921f77935197a71c14e311970f2082
 size 134284024

checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ad9b6906773bd85392d2fc5b12c2920068c7a288fe880254f58637438bddda5
+oid sha256:02f9b037a9ddc1f12dcd8790517e603db38562073a3e1726c7835cc5abae052e
 size 10161845830

checkpoint-1500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62a765712f30ca74b80df76a0e77f1d7c7fa15a41c313f05758bad43cfe28e07
+oid sha256:b4936b7b17383c8e52ded932a969e732dfed216eb11523f8b74c5fd790d9c10e
 size 1064

checkpoint-1500/trainer_state.json

@@ -1,7 +1,7 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7858546168958742,
+  "epoch": 0.7367387033398821,
   "eval_steps": 500,
   "global_step": 1500,
   "is_hyper_param_search": false,
@@ -9,216 +9,216 @@
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 0.03,
-      "learning_rate": 8.984758762730497e-06,
-      "loss": 0.7048,
+      "epoch": 0.02,
+      "learning_rate": 8.999464304375242e-06,
+      "loss": 0.7019,
       "step": 50
     },
     {
       "epoch": 0.05,
-      "learning_rate": 8.939138293283543e-06,
-      "loss": 0.676,
+      "learning_rate": 8.997857345043108e-06,
+      "loss": 0.6739,
       "step": 100
     },
     {
-      "epoch": 0.08,
-      "learning_rate": 8.863447619392112e-06,
-      "loss": 0.6622,
+      "epoch": 0.07,
+      "learning_rate": 8.99517950459963e-06,
+      "loss": 0.6677,
       "step": 150
     },
     {
       "epoch": 0.1,
-      "learning_rate": 8.758199460842813e-06,
-      "loss": 0.6612,
+      "learning_rate": 8.99143142060366e-06,
+      "loss": 0.6625,
       "step": 200
     },
     {
-      "epoch": 0.13,
-      "learning_rate": 8.62410675637192e-06,
-      "loss": 0.6619,
+      "epoch": 0.12,
+      "learning_rate": 8.98661398542506e-06,
+      "loss": 0.6649,
       "step": 250
     },
     {
-      "epoch": 0.16,
-      "learning_rate": 8.462077834301639e-06,
-      "loss": 0.6494,
+      "epoch": 0.15,
+      "learning_rate": 8.980728346032255e-06,
+      "loss": 0.6528,
       "step": 300
     },
     {
-      "epoch": 0.18,
-      "learning_rate": 8.2732102596301e-06,
-      "loss": 0.6349,
+      "epoch": 0.17,
+      "learning_rate": 8.973775903719142e-06,
+      "loss": 0.6442,
       "step": 350
     },
     {
-      "epoch": 0.21,
-      "learning_rate": 8.058783399254226e-06,
-      "loss": 0.6307,
+      "epoch": 0.2,
+      "learning_rate": 8.965758313771466e-06,
+      "loss": 0.6375,
       "step": 400
     },
     {
-      "epoch": 0.24,
-      "learning_rate": 7.820249755687773e-06,
-      "loss": 0.6398,
+      "epoch": 0.22,
+      "learning_rate": 8.956677485072722e-06,
+      "loss": 0.6303,
       "step": 450
     },
     {
-      "epoch": 0.26,
-      "learning_rate": 7.559225127978898e-06,
-      "loss": 0.6248,
+      "epoch": 0.25,
+      "learning_rate": 8.946535579649664e-06,
+      "loss": 0.634,
       "step": 500
     },
     {
-      "epoch": 0.26,
+      "epoch": 0.25,
       "eval_accuracy": 0.0,
-      "eval_loss": 0.6433030366897583,
-      "eval_runtime": 137.5224,
-      "eval_samples_per_second": 98.704,
-      "eval_steps_per_second": 12.34,
+      "eval_loss": 0.6457224488258362,
+      "eval_runtime": 154.2695,
+      "eval_samples_per_second": 87.989,
+      "eval_steps_per_second": 14.669,
       "step": 500
     },
     {
-      "epoch": 0.29,
-      "learning_rate": 7.277477666476089e-06,
-      "loss": 0.627,
+      "epoch": 0.27,
+      "learning_rate": 8.935335012157564e-06,
+      "loss": 0.6236,
       "step": 550
     },
     {
-      "epoch": 0.31,
-      "learning_rate": 6.976915895584163e-06,
-      "loss": 0.6281,
+      "epoch": 0.29,
+      "learning_rate": 8.92307844930531e-06,
+      "loss": 0.6235,
       "step": 600
     },
     {
-      "epoch": 0.34,
-      "learning_rate": 6.6595757856428145e-06,
-      "loss": 0.627,
+      "epoch": 0.32,
+      "learning_rate": 8.909768809220503e-06,
+      "loss": 0.6301,
       "step": 650
     },
     {
-      "epoch": 0.37,
-      "learning_rate": 6.32760696150126e-06,
-      "loss": 0.624,
+      "epoch": 0.34,
+      "learning_rate": 8.895409260754679e-06,
+      "loss": 0.6227,
       "step": 700
     },
     {
-      "epoch": 0.39,
-      "learning_rate": 5.983258141210536e-06,
-      "loss": 0.627,
+      "epoch": 0.37,
+      "learning_rate": 8.880003222728855e-06,
+      "loss": 0.6187,
       "step": 750
     },
     {
-      "epoch": 0.42,
-      "learning_rate": 5.628861903469983e-06,
-      "loss": 0.612,
+      "epoch": 0.39,
+      "learning_rate": 8.863554363119547e-06,
+      "loss": 0.6201,
       "step": 800
     },
     {
-      "epoch": 0.45,
-      "learning_rate": 5.266818887011524e-06,
-      "loss": 0.6069,
+      "epoch": 0.42,
+      "learning_rate": 8.846066598185479e-06,
+      "loss": 0.614,
       "step": 850
     },
     {
-      "epoch": 0.47,
-      "learning_rate": 4.899581528953207e-06,
-      "loss": 0.6208,
+      "epoch": 0.44,
+      "learning_rate": 8.827544091535166e-06,
+      "loss": 0.607,
       "step": 900
     },
     {
-      "epoch": 0.5,
-      "learning_rate": 4.52963745227654e-06,
-      "loss": 0.6069,
+      "epoch": 0.47,
+      "learning_rate": 8.80799125313562e-06,
+      "loss": 0.6176,
       "step": 950
     },
     {
-      "epoch": 0.52,
-      "learning_rate": 4.1594926149588915e-06,
-      "loss": 0.6114,
+      "epoch": 0.49,
+      "learning_rate": 8.787412738262386e-06,
+      "loss": 0.5999,
       "step": 1000
     },
     {
-      "epoch": 0.52,
+      "epoch": 0.49,
       "eval_accuracy": 0.0,
-      "eval_loss": 0.6329867243766785,
-      "eval_runtime": 138.3676,
-      "eval_samples_per_second": 98.101,
-      "eval_steps_per_second": 12.264,
+      "eval_loss": 0.6475000977516174,
+      "eval_runtime": 154.4877,
+      "eval_samples_per_second": 87.865,
+      "eval_steps_per_second": 14.648,
       "step": 1000
     },
     {
-      "epoch": 0.55,
-      "learning_rate": 3.7916543349067668e-06,
-      "loss": 0.61,
+      "epoch": 0.52,
+      "learning_rate": 8.765813446391192e-06,
+      "loss": 0.6055,
       "step": 1050
     },
     {
-      "epoch": 0.58,
-      "learning_rate": 3.428614305677092e-06,
-      "loss": 0.6095,
+      "epoch": 0.54,
+      "learning_rate": 8.743198520031437e-06,
+      "loss": 0.6142,
       "step": 1100
     },
     {
-      "epoch": 0.6,
-      "learning_rate": 3.0728317180360054e-06,
-      "loss": 0.5989,
+      "epoch": 0.56,
+      "learning_rate": 8.719573343501835e-06,
+      "loss": 0.6006,
       "step": 1150
     },
     {
-      "epoch": 0.63,
-      "learning_rate": 2.726716601687775e-06,
-      "loss": 0.5886,
+      "epoch": 0.59,
+      "learning_rate": 8.694943541648477e-06,
+      "loss": 0.5965,
       "step": 1200
     },
     {
-      "epoch": 0.65,
-      "learning_rate": 2.392613500014987e-06,
-      "loss": 0.5775,
+      "epoch": 0.61,
+      "learning_rate": 8.669314978505624e-06,
+      "loss": 0.5951,
       "step": 1250
     },
     {
-      "epoch": 0.68,
-      "learning_rate": 2.0727855884154554e-06,
-      "loss": 0.5781,
+      "epoch": 0.64,
+      "learning_rate": 8.642693755899563e-06,
+      "loss": 0.5695,
       "step": 1300
     },
     {
-      "epoch": 0.71,
-      "learning_rate": 1.7693993438163312e-06,
-      "loss": 0.5924,
+      "epoch": 0.66,
+      "learning_rate": 8.615086211995838e-06,
+      "loss": 0.5758,
       "step": 1350
     },
     {
-      "epoch": 0.73,
-      "learning_rate": 1.4845098692123864e-06,
-      "loss": 0.5879,
+      "epoch": 0.69,
+      "learning_rate": 8.586498919790219e-06,
+      "loss": 0.5733,
       "step": 1400
     },
     {
-      "epoch": 0.76,
-      "learning_rate": 1.2200469726383015e-06,
-      "loss": 0.5877,
+      "epoch": 0.71,
+      "learning_rate": 8.556938685543754e-06,
+      "loss": 0.5728,
       "step": 1450
     },
     {
-      "epoch": 0.79,
-      "learning_rate": 9.778020948743709e-07,
-      "loss": 0.5908,
+      "epoch": 0.74,
+      "learning_rate": 8.526412547162289e-06,
+      "loss": 0.5616,
       "step": 1500
     },
     {
-      "epoch": 0.79,
+      "epoch": 0.74,
       "eval_accuracy": 0.0,
-      "eval_loss": 0.6373098492622375,
-      "eval_runtime": 138.3673,
-      "eval_samples_per_second": 98.101,
-      "eval_steps_per_second": 12.264,
+      "eval_loss": 0.6478520035743713,
+      "eval_runtime": 154.2746,
+      "eval_samples_per_second": 87.986,
+      "eval_steps_per_second": 14.669,
       "step": 1500
     }
   ],
   "logging_steps": 50,
-  "max_steps": 1908,
-  "num_train_epochs": 1,
+  "max_steps": 10180,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "total_flos": 0.0,
   "trial_name": null,

checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e1679a4ba8385bd7dd8d63d11037eaecb596b5582e81d808d9f0a459b868354
+oid sha256:675ad7baaf7ffa742fe1cbe33421593cfc3ecc39b8591506637a3cfb1a79ff8b
 size 4664