Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a77ee587bb80330cf157ab95c0c6e0e9ba5f83ba5ba7f0bd2e62b0aecab4d55e
+oid sha256:d17f4ae20f9f992a27e6a1fa6cb56310739b4d9e112f20feed6499f8e80bdb75
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1702878219843e6e30236cdd122f897b8e8f456a427f854c5ffcf805d00ae1b6
+oid sha256:b092bb5f421e4613aec93ddde296b498489d2420e7c98850d80363bdeebccfc8
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a59b056016e351429f719aaf02cc6fa4544a2d92d2a3d69beeeb56674b12a1f2
+oid sha256:d880acef54d4eb61cf44bc2962e1f38bf44896cefc09a0303d9df0b77a1ae5c2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d586b09b70005491c0a1fb84efdfa30362af6101dc9bfbf32955ea051016a80
+oid sha256:b1e6ef080b2d27380abb32e34a8b58f3a1c18cafb574b45dd697ad5ba8ccc473
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.31849026679992676,
   "best_model_checkpoint": "mikhail_panzo/zlm_b128_le4_s8000/checkpoint-7000",
-  "epoch": 11.727748691099476,
+  "epoch": 12.565445026178011,
   "eval_steps": 500,
-  "global_step": 7000,
+  "global_step": 7500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1099,6 +1099,84 @@
       "eval_samples_per_second": 29.992,
       "eval_steps_per_second": 3.752,
       "step": 7000
+    },
+    {
+      "epoch": 11.81151832460733,
+      "grad_norm": 1.1094063520431519,
+      "learning_rate": 4.952e-05,
+      "loss": 0.346,
+      "step": 7050
+    },
+    {
+      "epoch": 11.895287958115183,
+      "grad_norm": 1.8263230323791504,
+      "learning_rate": 4.902e-05,
+      "loss": 0.3496,
+      "step": 7100
+    },
+    {
+      "epoch": 11.979057591623036,
+      "grad_norm": 1.4049593210220337,
+      "learning_rate": 4.852e-05,
+      "loss": 0.3433,
+      "step": 7150
+    },
+    {
+      "epoch": 12.06282722513089,
+      "grad_norm": 1.3455963134765625,
+      "learning_rate": 4.8030000000000006e-05,
+      "loss": 0.3518,
+      "step": 7200
+    },
+    {
+      "epoch": 12.146596858638743,
+      "grad_norm": 1.174660325050354,
+      "learning_rate": 4.753e-05,
+      "loss": 0.348,
+      "step": 7250
+    },
+    {
+      "epoch": 12.230366492146597,
+      "grad_norm": 1.2765902280807495,
+      "learning_rate": 4.703e-05,
+      "loss": 0.345,
+      "step": 7300
+    },
+    {
+      "epoch": 12.31413612565445,
+      "grad_norm": 1.419295072555542,
+      "learning_rate": 4.6530000000000003e-05,
+      "loss": 0.3436,
+      "step": 7350
+    },
+    {
+      "epoch": 12.397905759162304,
+      "grad_norm": 1.3437247276306152,
+      "learning_rate": 4.603e-05,
+      "loss": 0.3469,
+      "step": 7400
+    },
+    {
+      "epoch": 12.481675392670157,
+      "grad_norm": 1.6074751615524292,
+      "learning_rate": 4.553e-05,
+      "loss": 0.3461,
+      "step": 7450
+    },
+    {
+      "epoch": 12.565445026178011,
+      "grad_norm": 1.432062029838562,
+      "learning_rate": 4.503e-05,
+      "loss": 0.3441,
+      "step": 7500
+    },
+    {
+      "epoch": 12.565445026178011,
+      "eval_loss": 0.3222896158695221,
+      "eval_runtime": 282.6486,
+      "eval_samples_per_second": 30.034,
+      "eval_steps_per_second": 3.757,
+      "step": 7500
     }
   ],
   "logging_steps": 50,
@@ -1118,7 +1196,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2541009593096864e+17,
+  "total_flos": 1.3437364892618304e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null