Training in progress, step 6000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fb3c1f0ffd677dd1e18b0a0cd845e96b87f7fdf03c822cec02fa8667483f911
+oid sha256:ca211865df7db29fab6f53bfc838fb86f8410bbfb713bd45c3ce78f125101ac3
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f254b61c4507b59e81032985a4cb0722628542ccd373ac84e92ea094ff02541
+oid sha256:cf90b1f9716540d6e9884a2c814067a4c113532119080993f0c9fe1f9c2146e4
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efed929dee4a1aac0c5831e57885f78fe28ba54e8eb45766e963ce584357222a
+oid sha256:a26ae993c7b9ca74fb56780a08ca2dd23ac79600652bf66d8ac15ec961ff769d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f4ebc94f219234dc117648ea36b52869f5ad7c506a78e36de2ec35324b116e9
+oid sha256:cdc16f96a129b2f8ebddb713f251b55486ac014357ce4aedef1d542306c34e74
 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": 239.1304347826087,
+  "epoch": 260.8695652173913,
   "eval_steps": 500,
-  "global_step": 5500,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -865,6 +865,84 @@
       "eval_samples_per_second": 23.521,
       "eval_steps_per_second": 2.959,
       "step": 5500
+    },
+    {
+      "epoch": 241.30434782608697,
+      "grad_norm": 0.9192537665367126,
+      "learning_rate": 4.088333333333334e-06,
+      "loss": 0.4105,
+      "step": 5550
+    },
+    {
+      "epoch": 243.47826086956522,
+      "grad_norm": 1.0816397666931152,
+      "learning_rate": 4.005000000000001e-06,
+      "loss": 0.4116,
+      "step": 5600
+    },
+    {
+      "epoch": 245.65217391304347,
+      "grad_norm": 1.2673571109771729,
+      "learning_rate": 3.921666666666667e-06,
+      "loss": 0.4122,
+      "step": 5650
+    },
+    {
+      "epoch": 247.82608695652175,
+      "grad_norm": 1.131993055343628,
+      "learning_rate": 3.8383333333333336e-06,
+      "loss": 0.4097,
+      "step": 5700
+    },
+    {
+      "epoch": 250.0,
+      "grad_norm": 2.051192283630371,
+      "learning_rate": 3.7550000000000005e-06,
+      "loss": 0.4075,
+      "step": 5750
+    },
+    {
+      "epoch": 252.17391304347825,
+      "grad_norm": 0.8863391280174255,
+      "learning_rate": 3.6716666666666665e-06,
+      "loss": 0.4077,
+      "step": 5800
+    },
+    {
+      "epoch": 254.34782608695653,
+      "grad_norm": 0.8587177395820618,
+      "learning_rate": 3.588333333333334e-06,
+      "loss": 0.4047,
+      "step": 5850
+    },
+    {
+      "epoch": 256.5217391304348,
+      "grad_norm": 1.0080711841583252,
+      "learning_rate": 3.505e-06,
+      "loss": 0.4093,
+      "step": 5900
+    },
+    {
+      "epoch": 258.69565217391306,
+      "grad_norm": 1.022581934928894,
+      "learning_rate": 3.4216666666666672e-06,
+      "loss": 0.4069,
+      "step": 5950
+    },
+    {
+      "epoch": 260.8695652173913,
+      "grad_norm": 1.0036355257034302,
+      "learning_rate": 3.3383333333333333e-06,
+      "loss": 0.4192,
+      "step": 6000
+    },
+    {
+      "epoch": 260.8695652173913,
+      "eval_loss": 0.41063958406448364,
+      "eval_runtime": 6.6166,
+      "eval_samples_per_second": 24.031,
+      "eval_steps_per_second": 3.023,
+      "step": 6000
     }
   ],
   "logging_steps": 50,
@@ -884,7 +962,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.163798006962506e+16,
+  "total_flos": 8.907761646343613e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null