Training in progress, step 8000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edf345f4a3e27a4cec4b72cd6af0fa7fa4858493f48d1ba748ecbc6aefd06c07
+oid sha256:19d39dd9b619e7904c8275e5a7874baf72c3427e4b764352c5067cc1dc59a128
 size 577789320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed2cac3253f5b08fe26579efe91ac53d8ff0449bd135c02868dafd16cbabb683
+oid sha256:8a1a37f6fef4cd1464be2db04f3bc671ccf5a3e73428f31b9491f9b4dc67ed18
 size 1155772233

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:365d91d890037cfbeac60120c074da46ad74cccfd1e677fb9dcd524589ceea77
+oid sha256:f45a2e53597446c67d3516e0bd9849a98838c2b4c8578d3fd4ef0a27339ff153
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c124d5873e6dde5040a6a31973ca68127e3dfe277695e3cb113af8a1a01ff662
+oid sha256:0aef1303f298e810b9c563fac5650fcaebc5d5e2a568db30104db374f503c826
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.402925044298172,
   "best_model_checkpoint": "mikhail-panzo/fil_b128_le5_s8000/checkpoint-4500",
-  "epoch": 652.1739130434783,
+  "epoch": 695.6521739130435,
   "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": 12.215,
       "eval_steps_per_second": 1.593,
       "step": 7500
+    },
+    {
+      "epoch": 656.5217391304348,
+      "grad_norm": 0.6540374159812927,
+      "learning_rate": 7.550000000000001e-07,
+      "loss": 0.4029,
+      "step": 7550
+    },
+    {
+      "epoch": 660.8695652173913,
+      "grad_norm": 0.618146538734436,
+      "learning_rate": 6.716666666666668e-07,
+      "loss": 0.4018,
+      "step": 7600
+    },
+    {
+      "epoch": 665.2173913043479,
+      "grad_norm": 0.7216867804527283,
+      "learning_rate": 5.883333333333333e-07,
+      "loss": 0.4012,
+      "step": 7650
+    },
+    {
+      "epoch": 669.5652173913044,
+      "grad_norm": 0.6385495662689209,
+      "learning_rate": 5.05e-07,
+      "loss": 0.4028,
+      "step": 7700
+    },
+    {
+      "epoch": 673.9130434782609,
+      "grad_norm": 0.7671997547149658,
+      "learning_rate": 4.2166666666666667e-07,
+      "loss": 0.4028,
+      "step": 7750
+    },
+    {
+      "epoch": 678.2608695652174,
+      "grad_norm": 0.6697407960891724,
+      "learning_rate": 3.3833333333333336e-07,
+      "loss": 0.4024,
+      "step": 7800
+    },
+    {
+      "epoch": 682.6086956521739,
+      "grad_norm": 0.6977794170379639,
+      "learning_rate": 2.55e-07,
+      "loss": 0.3988,
+      "step": 7850
+    },
+    {
+      "epoch": 686.9565217391304,
+      "grad_norm": 0.6256734132766724,
+      "learning_rate": 1.7166666666666668e-07,
+      "loss": 0.3989,
+      "step": 7900
+    },
+    {
+      "epoch": 691.304347826087,
+      "grad_norm": 0.7186506390571594,
+      "learning_rate": 8.833333333333334e-08,
+      "loss": 0.4027,
+      "step": 7950
+    },
+    {
+      "epoch": 695.6521739130435,
+      "grad_norm": 0.7653046250343323,
+      "learning_rate": 5e-09,
+      "loss": 0.4042,
+      "step": 8000
+    },
+    {
+      "epoch": 695.6521739130435,
+      "eval_loss": 0.4052514135837555,
+      "eval_runtime": 13.2988,
+      "eval_samples_per_second": 12.106,
+      "eval_steps_per_second": 1.579,
+      "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": 1.817971026659378e+17,
+  "total_flos": 1.9390598333064925e+17,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": null