Training in progress, step 7500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d76fb25ac74cbe823a725be4343d2b07424a8edf844909a7000abe7d69111912
+oid sha256:63511d44cdc914119f5c885f1c739e0023041a9ad236fc9a57f6ff9c0333eb16
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f7c629776fb459ffe00693d1167430337e7d74e730089d7e33ee908588b005f
+oid sha256:bcd67f665ee333d5cacfa0b6159c217e72831fae2f2d447f9381dc2659128ce4
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0b694d3ca006a86a8090922c7030bb02dd33e4641d640c040f8086a25b51174
+oid sha256:3395cc0c92099e3a41f5095fd540270dd8b496efba101003c928717ffc8eedfe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a56375003d29c70f770a5d9b0b3090653def3595de353abeabbdb559dcca8724
+oid sha256:b5cdfe5ed4f14bdadfee62402701e9c3c91a7e1b8246c7c7f0be536b67574fb3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.4066200256347656,
   "best_model_checkpoint": "mikhail_panzo/fil_b32_le4_s8000/checkpoint-5500",
-  "epoch": 153.84615384615384,
+  "epoch": 164.83516483516485,
   "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": 12.259,
       "eval_steps_per_second": 1.599,
       "step": 7000
+    },
+    {
+      "epoch": 154.94505494505495,
+      "grad_norm": 0.9426752328872681,
+      "learning_rate": 1.5883333333333334e-05,
+      "loss": 0.3567,
+      "step": 7050
+    },
+    {
+      "epoch": 156.04395604395606,
+      "grad_norm": 1.0722122192382812,
+      "learning_rate": 1.505e-05,
+      "loss": 0.3559,
+      "step": 7100
+    },
+    {
+      "epoch": 157.14285714285714,
+      "grad_norm": 1.1290276050567627,
+      "learning_rate": 1.4216666666666667e-05,
+      "loss": 0.3654,
+      "step": 7150
+    },
+    {
+      "epoch": 158.24175824175825,
+      "grad_norm": 1.0128904581069946,
+      "learning_rate": 1.3383333333333335e-05,
+      "loss": 0.357,
+      "step": 7200
+    },
+    {
+      "epoch": 159.34065934065933,
+      "grad_norm": 1.2913401126861572,
+      "learning_rate": 1.255e-05,
+      "loss": 0.3556,
+      "step": 7250
+    },
+    {
+      "epoch": 160.43956043956044,
+      "grad_norm": 1.0247690677642822,
+      "learning_rate": 1.1716666666666667e-05,
+      "loss": 0.3512,
+      "step": 7300
+    },
+    {
+      "epoch": 161.53846153846155,
+      "grad_norm": 1.1389926671981812,
+      "learning_rate": 1.0883333333333335e-05,
+      "loss": 0.3553,
+      "step": 7350
+    },
+    {
+      "epoch": 162.63736263736263,
+      "grad_norm": 0.853523850440979,
+      "learning_rate": 1.005e-05,
+      "loss": 0.357,
+      "step": 7400
+    },
+    {
+      "epoch": 163.73626373626374,
+      "grad_norm": 0.8105210065841675,
+      "learning_rate": 9.216666666666666e-06,
+      "loss": 0.3512,
+      "step": 7450
+    },
+    {
+      "epoch": 164.83516483516485,
+      "grad_norm": 0.891890287399292,
+      "learning_rate": 8.383333333333333e-06,
+      "loss": 0.3581,
+      "step": 7500
+    },
+    {
+      "epoch": 164.83516483516485,
+      "eval_loss": 0.4096794128417969,
+      "eval_runtime": 12.3085,
+      "eval_samples_per_second": 13.08,
+      "eval_steps_per_second": 1.706,
+      "step": 7500
     }
   ],
   "logging_steps": 50,
@@ -1118,7 +1196,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.150908851832547e+16,
+  "total_flos": 4.446529244284723e+16,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null