Training in progress, step 5000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef1d1379820461412cf086748c060025c79dec8f2ffe2923b0063fbc235d650
+oid sha256:f669e1edaf809ee0b127b9819fd1f231d281115cbf44cb10938e4e60a2d53f62
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7c71d57a31b15e8daa76300ea1bd06abd3cfd13f046584be58e1f5707dc5789
+oid sha256:943f2614f294b9345e99d0909b80fc9febf29a6705251ef48ff3aef917e58d2e
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f01f528b91e8e9237bf04af3a09af7087c8db798408ae08e226a1c398cda90c3
+oid sha256:ab3632b412639e7ce8b5588ff8a7239c0f85ee0022719040327317447154761e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d9ea6ac8e84dcaff37314a282ec7aba7995babdb11261372593bc800ef835cf
+oid sha256:51ae9e871201b5140a75803631a3b447a66295ef984c1c9cd1719a8febdf7390
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.41326722502708435,
-  "best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-3500",
-  "epoch": 195.65217391304347,
+  "best_metric": 0.41126948595046997,
+  "best_model_checkpoint": "mikhail-panzo/fil_b64_le5_s8000/checkpoint-5000",
+  "epoch": 217.3913043478261,
   "eval_steps": 500,
-  "global_step": 4500,
+  "global_step": 5000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -709,6 +709,84 @@
       "eval_samples_per_second": 24.148,
       "eval_steps_per_second": 3.037,
       "step": 4500
+    },
+    {
+      "epoch": 197.82608695652175,
+      "grad_norm": 1.1709681749343872,
+      "learning_rate": 5.755000000000001e-06,
+      "loss": 0.4178,
+      "step": 4550
+    },
+    {
+      "epoch": 200.0,
+      "grad_norm": 3.5350754261016846,
+      "learning_rate": 5.671666666666668e-06,
+      "loss": 0.4211,
+      "step": 4600
+    },
+    {
+      "epoch": 202.17391304347825,
+      "grad_norm": 2.050933361053467,
+      "learning_rate": 5.588333333333334e-06,
+      "loss": 0.4266,
+      "step": 4650
+    },
+    {
+      "epoch": 204.34782608695653,
+      "grad_norm": 1.973078966140747,
+      "learning_rate": 5.505000000000001e-06,
+      "loss": 0.4187,
+      "step": 4700
+    },
+    {
+      "epoch": 206.52173913043478,
+      "grad_norm": 1.4094629287719727,
+      "learning_rate": 5.4216666666666676e-06,
+      "loss": 0.4294,
+      "step": 4750
+    },
+    {
+      "epoch": 208.69565217391303,
+      "grad_norm": 0.9872909188270569,
+      "learning_rate": 5.3383333333333345e-06,
+      "loss": 0.4239,
+      "step": 4800
+    },
+    {
+      "epoch": 210.8695652173913,
+      "grad_norm": 1.4357950687408447,
+      "learning_rate": 5.2550000000000005e-06,
+      "loss": 0.4117,
+      "step": 4850
+    },
+    {
+      "epoch": 213.04347826086956,
+      "grad_norm": 1.4760295152664185,
+      "learning_rate": 5.171666666666667e-06,
+      "loss": 0.4239,
+      "step": 4900
+    },
+    {
+      "epoch": 215.2173913043478,
+      "grad_norm": 0.9877930879592896,
+      "learning_rate": 5.088333333333334e-06,
+      "loss": 0.4151,
+      "step": 4950
+    },
+    {
+      "epoch": 217.3913043478261,
+      "grad_norm": 1.3829108476638794,
+      "learning_rate": 5.0049999999999995e-06,
+      "loss": 0.4223,
+      "step": 5000
+    },
+    {
+      "epoch": 217.3913043478261,
+      "eval_loss": 0.41126948595046997,
+      "eval_runtime": 6.7795,
+      "eval_samples_per_second": 23.453,
+      "eval_steps_per_second": 2.95,
+      "step": 5000
     }
   ],
   "logging_steps": 50,
@@ -728,7 +806,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.679500701272502e+16,
+  "total_flos": 7.422809573607754e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null