Training in progress, step 6500, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca211865df7db29fab6f53bfc838fb86f8410bbfb713bd45c3ce78f125101ac3
+oid sha256:5c29a21f15225581fbb70a7d721f8157ec0c65b1f2548f53bcd908f348e9b6ec
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf90b1f9716540d6e9884a2c814067a4c113532119080993f0c9fe1f9c2146e4
+oid sha256:9d61955690a0b31f077effc736b8ee15682b32c1efbd678ac49286e5a9a9b91b
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a26ae993c7b9ca74fb56780a08ca2dd23ac79600652bf66d8ac15ec961ff769d
+oid sha256:6ef9fc3da0d0a80b7fc1708d427165ee696af2ea29d5ff732e5ecb806ccbe22e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdc16f96a129b2f8ebddb713f251b55486ac014357ce4aedef1d542306c34e74
+oid sha256:935e716e26427b50d58301a89c5ac51882cf7f1f1087c9e92a9aedc9583a88dd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.40983906388282776,
   "best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-5500",
-  "epoch": 260.8695652173913,
+  "epoch": 282.60869565217394,
   "eval_steps": 500,
-  "global_step": 6000,
+  "global_step": 6500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -943,6 +943,84 @@
       "eval_samples_per_second": 24.031,
       "eval_steps_per_second": 3.023,
       "step": 6000
+    },
+    {
+      "epoch": 263.04347826086956,
+      "grad_norm": 1.1398719549179077,
+      "learning_rate": 3.255e-06,
+      "loss": 0.4187,
+      "step": 6050
+    },
+    {
+      "epoch": 265.2173913043478,
+      "grad_norm": 0.8705397248268127,
+      "learning_rate": 3.1716666666666667e-06,
+      "loss": 0.4189,
+      "step": 6100
+    },
+    {
+      "epoch": 267.39130434782606,
+      "grad_norm": 1.1828796863555908,
+      "learning_rate": 3.0883333333333336e-06,
+      "loss": 0.412,
+      "step": 6150
+    },
+    {
+      "epoch": 269.5652173913044,
+      "grad_norm": 1.2808082103729248,
+      "learning_rate": 3.005e-06,
+      "loss": 0.4135,
+      "step": 6200
+    },
+    {
+      "epoch": 271.7391304347826,
+      "grad_norm": 1.2082769870758057,
+      "learning_rate": 2.921666666666667e-06,
+      "loss": 0.4163,
+      "step": 6250
+    },
+    {
+      "epoch": 273.9130434782609,
+      "grad_norm": 1.2765779495239258,
+      "learning_rate": 2.8383333333333334e-06,
+      "loss": 0.409,
+      "step": 6300
+    },
+    {
+      "epoch": 276.0869565217391,
+      "grad_norm": 1.0085750818252563,
+      "learning_rate": 2.7550000000000003e-06,
+      "loss": 0.4168,
+      "step": 6350
+    },
+    {
+      "epoch": 278.2608695652174,
+      "grad_norm": 1.2481540441513062,
+      "learning_rate": 2.6716666666666668e-06,
+      "loss": 0.4163,
+      "step": 6400
+    },
+    {
+      "epoch": 280.4347826086956,
+      "grad_norm": 1.0520100593566895,
+      "learning_rate": 2.5883333333333337e-06,
+      "loss": 0.4165,
+      "step": 6450
+    },
+    {
+      "epoch": 282.60869565217394,
+      "grad_norm": 1.2364658117294312,
+      "learning_rate": 2.505e-06,
+      "loss": 0.4089,
+      "step": 6500
+    },
+    {
+      "epoch": 282.60869565217394,
+      "eval_loss": 0.4121515154838562,
+      "eval_runtime": 6.5878,
+      "eval_samples_per_second": 24.136,
+      "eval_steps_per_second": 3.036,
+      "step": 6500
     }
   ],
   "logging_steps": 50,
@@ -962,7 +1040,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.907761646343613e+16,
+  "total_flos": 9.648731372068483e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null