Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ac0dd6470aeaf933119e8adec87506edd50e34ef244bc4be2bc111bafac7fe9
+oid sha256:3cec2f4fff3db703dbc5020dd2309d9b6d627b43f4a3b5ad0329687d8dfd377d
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9c939c62a6f8d89ae3405aac942cc155a4f3278dc1f16cf465b01365351d91d
+oid sha256:3a4e84620efe0237372039f1ccad6bca43de1c5d2d26d727510a9b3b37d24904
 size 162933844

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff1d9539e09b7c36cf6b054c8fcfced3ce1a861812d8feb865f087854f471e3c
+oid sha256:c3d9d1f3e3b592eb13d0589dee0f79cefba71d5df0c62fae2d7fda0fb4167c6a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70f0f789b56065211b8c0b1a5e2a97dd0b5b08a816bbbe288fb6f9c677282af9
+oid sha256:5ad54995b081fae25638228c5d9c8f38ca277e5c5ad00bc3e49897b543f84405
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.725193440914154,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.0896548289087015,
+  "best_metric": 0.7226464152336121,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 0.11953977187826867,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,135 @@
       "eval_samples_per_second": 13.989,
       "eval_steps_per_second": 3.498,
       "step": 450
+    },
+    {
+      "epoch": 0.09164715844000598,
+      "grad_norm": 0.3175693452358246,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 0.6855,
+      "step": 460
+    },
+    {
+      "epoch": 0.09363948797131046,
+      "grad_norm": 0.28028416633605957,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 0.6913,
+      "step": 470
+    },
+    {
+      "epoch": 0.09563181750261493,
+      "grad_norm": 0.26005247235298157,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 0.6725,
+      "step": 480
+    },
+    {
+      "epoch": 0.0976241470339194,
+      "grad_norm": 0.2885555624961853,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 0.7315,
+      "step": 490
+    },
+    {
+      "epoch": 0.09961647656522389,
+      "grad_norm": 0.3878602385520935,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 0.7605,
+      "step": 500
+    },
+    {
+      "epoch": 0.09961647656522389,
+      "eval_loss": 0.7219599485397339,
+      "eval_runtime": 605.6943,
+      "eval_samples_per_second": 13.958,
+      "eval_steps_per_second": 3.49,
+      "step": 500
+    },
+    {
+      "epoch": 0.10160880609652836,
+      "grad_norm": 0.3010750710964203,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 0.6475,
+      "step": 510
+    },
+    {
+      "epoch": 0.10360113562783284,
+      "grad_norm": 0.2743396461009979,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 0.6809,
+      "step": 520
+    },
+    {
+      "epoch": 0.10559346515913733,
+      "grad_norm": 0.3698458969593048,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 0.7357,
+      "step": 530
+    },
+    {
+      "epoch": 0.1075857946904418,
+      "grad_norm": 0.2824854552745819,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 0.7327,
+      "step": 540
+    },
+    {
+      "epoch": 0.10957812422174627,
+      "grad_norm": 0.3766637444496155,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 0.7644,
+      "step": 550
+    },
+    {
+      "epoch": 0.10957812422174627,
+      "eval_loss": 0.7227113246917725,
+      "eval_runtime": 606.1455,
+      "eval_samples_per_second": 13.947,
+      "eval_steps_per_second": 3.488,
+      "step": 550
+    },
+    {
+      "epoch": 0.11157045375305076,
+      "grad_norm": 0.2523180842399597,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 0.6927,
+      "step": 560
+    },
+    {
+      "epoch": 0.11356278328435523,
+      "grad_norm": 0.3261297643184662,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 0.7312,
+      "step": 570
+    },
+    {
+      "epoch": 0.11555511281565971,
+      "grad_norm": 0.3216928541660309,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 0.7011,
+      "step": 580
+    },
+    {
+      "epoch": 0.11754744234696418,
+      "grad_norm": 0.33191266655921936,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 0.7112,
+      "step": 590
+    },
+    {
+      "epoch": 0.11953977187826867,
+      "grad_norm": 0.3486833870410919,
+      "learning_rate": 0.0,
+      "loss": 0.7377,
+      "step": 600
+    },
+    {
+      "epoch": 0.11953977187826867,
+      "eval_loss": 0.7226464152336121,
+      "eval_runtime": 604.8428,
+      "eval_samples_per_second": 13.977,
+      "eval_steps_per_second": 3.495,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -425,12 +554,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.946133609143337e+17,
+  "total_flos": 7.928178145524449e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null