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:d005130bbd79f63ed3576d1fb5bde54f18c3f8002c2569b44bdd45c4dfa32a2e
+oid sha256:30e0cb6ca157786b2058acb6b1da7388a56a9164e337b0b4d73cf5ab8f4ad128
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88148e0e8f3d7719ea166dae64c36638701c6fcf4624688705dc0786ae94a247
+oid sha256:297360bdfcf9bc9fe14cc2c4461c053957550b632eb612612d95a4a4172f5385
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bec849e25acd8dd93c6dc0cc1f78247dec56dc50df0766dc1fb28a024ff6966
+oid sha256:4a2f91a9adecb736a3d86f510d1bafffdf38a5f23dcfd6f932d7096c9b8c1973
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d48e757787bf7fc889c741def8f67efb8c383ce859146812f7dbd958398696a3
+oid sha256:0faaff1eaeb01ac673cde04e45352a5ca536ee1dfd9544b36554717d21724b65
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4766067862510681,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.04243681629573746,
+  "best_metric": 0.4729672074317932,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 0.05658242172764994,
   "eval_steps": 150,
-  "global_step": 450,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -354,6 +354,119 @@
       "eval_samples_per_second": 23.871,
       "eval_steps_per_second": 5.976,
       "step": 450
+    },
+    {
+      "epoch": 0.04337985665786496,
+      "grad_norm": 1.4336448907852173,
+      "learning_rate": 6.902683966887863e-06,
+      "loss": 0.4743,
+      "step": 460
+    },
+    {
+      "epoch": 0.04432289701999246,
+      "grad_norm": 1.0714585781097412,
+      "learning_rate": 5.997779885392928e-06,
+      "loss": 0.4757,
+      "step": 470
+    },
+    {
+      "epoch": 0.04526593738211995,
+      "grad_norm": 1.258355975151062,
+      "learning_rate": 5.147022251382486e-06,
+      "loss": 0.4376,
+      "step": 480
+    },
+    {
+      "epoch": 0.046208977744247454,
+      "grad_norm": 0.9438008666038513,
+      "learning_rate": 4.3532897593890356e-06,
+      "loss": 0.483,
+      "step": 490
+    },
+    {
+      "epoch": 0.047152018106374954,
+      "grad_norm": 1.3534599542617798,
+      "learning_rate": 3.619268148915402e-06,
+      "loss": 0.4502,
+      "step": 500
+    },
+    {
+      "epoch": 0.048095058468502455,
+      "grad_norm": 1.6557931900024414,
+      "learning_rate": 2.947441116742348e-06,
+      "loss": 0.5207,
+      "step": 510
+    },
+    {
+      "epoch": 0.04903809883062995,
+      "grad_norm": 1.548148512840271,
+      "learning_rate": 2.3400819128849325e-06,
+      "loss": 0.4162,
+      "step": 520
+    },
+    {
+      "epoch": 0.04998113919275745,
+      "grad_norm": 1.4258723258972168,
+      "learning_rate": 1.7992456486339744e-06,
+      "loss": 0.4655,
+      "step": 530
+    },
+    {
+      "epoch": 0.05092417955488495,
+      "grad_norm": 1.1291389465332031,
+      "learning_rate": 1.326762342710017e-06,
+      "loss": 0.4796,
+      "step": 540
+    },
+    {
+      "epoch": 0.05186721991701245,
+      "grad_norm": 1.4239860773086548,
+      "learning_rate": 9.242307290592442e-07,
+      "loss": 0.4622,
+      "step": 550
+    },
+    {
+      "epoch": 0.052810260279139945,
+      "grad_norm": 1.2388654947280884,
+      "learning_rate": 5.930128472438762e-07,
+      "loss": 0.5011,
+      "step": 560
+    },
+    {
+      "epoch": 0.053753300641267446,
+      "grad_norm": 1.3684238195419312,
+      "learning_rate": 3.3422943373142354e-07,
+      "loss": 0.446,
+      "step": 570
+    },
+    {
+      "epoch": 0.05469634100339495,
+      "grad_norm": 1.4726179838180542,
+      "learning_rate": 1.4875612967725348e-07,
+      "loss": 0.4642,
+      "step": 580
+    },
+    {
+      "epoch": 0.05563938136552245,
+      "grad_norm": 1.8181157112121582,
+      "learning_rate": 3.722051803210014e-08,
+      "loss": 0.4721,
+      "step": 590
+    },
+    {
+      "epoch": 0.05658242172764994,
+      "grad_norm": 1.503574252128601,
+      "learning_rate": 0.0,
+      "loss": 0.4171,
+      "step": 600
+    },
+    {
+      "epoch": 0.05658242172764994,
+      "eval_loss": 0.4729672074317932,
+      "eval_runtime": 93.8663,
+      "eval_samples_per_second": 23.789,
+      "eval_steps_per_second": 5.955,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -377,12 +490,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.834345877929984e+16,
+  "total_flos": 5.12347940585472e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null