Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:403cfbffc7ee4007065e4824a75bc209469efb1d3eaf4b78bdcdc4b8e425ae79
+oid sha256:3bc7aeae14173576a0aebd29e684e90ad24f0513c8e659f4277017c800274d58
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f82a7c0b927ee4293785e8b97633d22c4746dbad1b0c92376ee3f5578e79116
+oid sha256:e262c67abf09f51a6988d2779ae3bb916ffc4796bf41409d1a4cf45d6e527474
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:795fe76cfd6ac22612e53f90e3708fe6447c8d1c969f78a57978bb17493086b1
+oid sha256:b1a0bdb5e52391cb330bbf26b7de42f02e891fbc6b02cd43250006d07b1a1b82
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef84ad524da6dbaaadb8576fa258a66ac5d4b080583a172fefc45887ff84f46
+oid sha256:053e3e9faa016c771f1e612410ff8471cd7862add0ff2bcd59dd7177245c9618
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.41427454352378845,
   "best_model_checkpoint": "mikhail_panzo/ceb_b128_le3_s8000/checkpoint-500",
-  "epoch": 588.2352941176471,
+  "epoch": 627.4509803921569,
   "eval_steps": 500,
-  "global_step": 7500,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1177,6 +1177,84 @@
       "eval_samples_per_second": 26.734,
       "eval_steps_per_second": 3.416,
       "step": 7500
+    },
+    {
+      "epoch": 592.156862745098,
+      "grad_norm": 0.027007540687918663,
+      "learning_rate": 7.533333333333334e-05,
+      "loss": 1.4173,
+      "step": 7550
+    },
+    {
+      "epoch": 596.0784313725491,
+      "grad_norm": 0.04154467582702637,
+      "learning_rate": 6.7e-05,
+      "loss": 1.4186,
+      "step": 7600
+    },
+    {
+      "epoch": 600.0,
+      "grad_norm": 0.10418181121349335,
+      "learning_rate": 5.8666666666666665e-05,
+      "loss": 1.4187,
+      "step": 7650
+    },
+    {
+      "epoch": 603.9215686274509,
+      "grad_norm": 0.041870325803756714,
+      "learning_rate": 5.0333333333333335e-05,
+      "loss": 1.4188,
+      "step": 7700
+    },
+    {
+      "epoch": 607.843137254902,
+      "grad_norm": 0.08349625766277313,
+      "learning_rate": 4.2000000000000004e-05,
+      "loss": 1.4191,
+      "step": 7750
+    },
+    {
+      "epoch": 611.7647058823529,
+      "grad_norm": 0.08984719216823578,
+      "learning_rate": 3.366666666666667e-05,
+      "loss": 1.4174,
+      "step": 7800
+    },
+    {
+      "epoch": 615.6862745098039,
+      "grad_norm": 0.028009561821818352,
+      "learning_rate": 2.5333333333333334e-05,
+      "loss": 1.4203,
+      "step": 7850
+    },
+    {
+      "epoch": 619.6078431372549,
+      "grad_norm": 0.025170741602778435,
+      "learning_rate": 1.7000000000000003e-05,
+      "loss": 1.4183,
+      "step": 7900
+    },
+    {
+      "epoch": 623.5294117647059,
+      "grad_norm": 0.08974526822566986,
+      "learning_rate": 8.666666666666666e-06,
+      "loss": 1.4177,
+      "step": 7950
+    },
+    {
+      "epoch": 627.4509803921569,
+      "grad_norm": 0.023904943838715553,
+      "learning_rate": 3.3333333333333335e-07,
+      "loss": 1.4184,
+      "step": 8000
+    },
+    {
+      "epoch": 627.4509803921569,
+      "eval_loss": 1.4349356889724731,
+      "eval_runtime": 6.7417,
+      "eval_samples_per_second": 26.7,
+      "eval_steps_per_second": 3.412,
+      "step": 8000
     }
   ],
   "logging_steps": 50,
@@ -1191,12 +1269,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.631701918768069e+17,
+  "total_flos": 1.7404667537759085e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null