Training in progress, step 1500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b3bd15ad5f6e246b6e337225788c69c49a21df6eeb262d2b1b1897cf5cf6146
+oid sha256:f48d4e3b236d8f6efbf06705c5921fc52712f6cbe83333940faee84b86dc9b95
 size 4523108832

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ecf8f056195b0098a8274b3035e24672255ff4c10ed92a0717c3ca84f2c7426
+oid sha256:890a01f7b0ed19d87aa41af9bd25032b9358906ea2c970f07da2b1cfdf970382
 size 2911851147

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8e2011629d8bed3ef560fa11175cac55684c4e12a72634bb24abf767b6c7399
+oid sha256:01f9a0f7843a37be87edd23f4e88aa93b38b95cc2c07503eeb1cf2e4632453a2
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
+oid sha256:ca372268f4fa9335030c0cb7aedb6cdba75f457da50e7a4034abb1a2d0843689
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92235ff997c3a5622fba1c344122ccffab641b57d7443401a19efb448a747750
+oid sha256:d87adb2ba2eff80e48f285a6c3b50b12e8fa43fde329e8b0d491370e73a397d0
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1000,
   "best_metric": 0.988082230091095,
   "best_model_checkpoint": "./sft-out/checkpoint-1000",
-  "epoch": 1.7673352118901597,
+  "epoch": 2.6506436819713795,
   "eval_steps": 500,
-  "global_step": 1000,
+  "global_step": 1500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -164,6 +164,84 @@
       "eval_samples_per_second": 18.28,
       "eval_steps_per_second": 2.303,
       "step": 1000
+    },
+    {
+      "epoch": 1.8557378860710536,
+      "grad_norm": 2.1198668479919434,
+      "learning_rate": 1.5164817945522343e-05,
+      "loss": 0.7200093078613281,
+      "step": 1050
+    },
+    {
+      "epoch": 1.9441405602519475,
+      "grad_norm": 2.416775703430176,
+      "learning_rate": 1.4693652811602635e-05,
+      "loss": 0.7036862182617187,
+      "step": 1100
+    },
+    {
+      "epoch": 2.0318249627051217,
+      "grad_norm": 2.5851995944976807,
+      "learning_rate": 1.4208720385280673e-05,
+      "loss": 0.5860164260864258,
+      "step": 1150
+    },
+    {
+      "epoch": 2.120227636886016,
+      "grad_norm": 1.8049288988113403,
+      "learning_rate": 1.3711443056915611e-05,
+      "loss": 0.354575080871582,
+      "step": 1200
+    },
+    {
+      "epoch": 2.20863031106691,
+      "grad_norm": 2.2025763988494873,
+      "learning_rate": 1.3203279426591329e-05,
+      "loss": 0.3392633819580078,
+      "step": 1250
+    },
+    {
+      "epoch": 2.297032985247804,
+      "grad_norm": 2.0318801403045654,
+      "learning_rate": 1.2685720025791004e-05,
+      "loss": 0.33905509948730467,
+      "step": 1300
+    },
+    {
+      "epoch": 2.3854356594286976,
+      "grad_norm": 2.0977327823638916,
+      "learning_rate": 1.2160282945411513e-05,
+      "loss": 0.34515163421630857,
+      "step": 1350
+    },
+    {
+      "epoch": 2.4738383336095917,
+      "grad_norm": 2.108346462249756,
+      "learning_rate": 1.1628509382941232e-05,
+      "loss": 0.35274150848388675,
+      "step": 1400
+    },
+    {
+      "epoch": 2.562241007790486,
+      "grad_norm": 2.778698682785034,
+      "learning_rate": 1.1091959121862279e-05,
+      "loss": 0.3534046173095703,
+      "step": 1450
+    },
+    {
+      "epoch": 2.6506436819713795,
+      "grad_norm": 2.0644469261169434,
+      "learning_rate": 1.0552205956536803e-05,
+      "loss": 0.34923103332519534,
+      "step": 1500
+    },
+    {
+      "epoch": 2.6506436819713795,
+      "eval_loss": 1.0509159564971924,
+      "eval_runtime": 27.3535,
+      "eval_samples_per_second": 18.279,
+      "eval_steps_per_second": 2.303,
+      "step": 1500
     }
   ],
   "logging_steps": 50,
@@ -183,7 +261,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.876769443016704e+16,
+  "total_flos": 5.822502544962355e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null