Training in progress, step 600, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76fcf8d306caeb043a3cb5d43f6e62efae99a94cce586c3b5974df9a6d484fad
+oid sha256:63110badfdf85f0bb2550baf34aab56827181068f2ceaca717cc3f89eaf5b58c
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3bd42150e008a1bbddcb58353eb4002de8774a2318a9ec4f2b223079302a3f0
+oid sha256:8bc9044bf49f52ee3c858c16851b8e52412f1f2fd7397346a15167b588d87cf8
 size 75472244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecf4964b094cde4682dffbc3ccc495d200cbfb994a6a61f566d42b43aed8900d
+oid sha256:466b3954c2395356a44c2295ce049c71f33cd801d70afc6e9a63811d0adcbcc6
 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": 0.34923774003982544,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.6764374295377678,
+  "best_metric": 0.3471680283546448,
+  "best_model_checkpoint": "miner_id_24/checkpoint-600",
+  "epoch": 0.9019165727170236,
   "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": 31.637,
       "eval_steps_per_second": 7.931,
       "step": 450
+    },
+    {
+      "epoch": 0.6914693724163848,
+      "grad_norm": 0.1071515679359436,
+      "learning_rate": 2.6522584913693294e-05,
+      "loss": 0.3868,
+      "step": 460
+    },
+    {
+      "epoch": 0.7065013152950019,
+      "grad_norm": 0.12611959874629974,
+      "learning_rate": 2.301660165700936e-05,
+      "loss": 0.3711,
+      "step": 470
+    },
+    {
+      "epoch": 0.7215332581736189,
+      "grad_norm": 0.12682585418224335,
+      "learning_rate": 1.9728836206903656e-05,
+      "loss": 0.3507,
+      "step": 480
+    },
+    {
+      "epoch": 0.736565201052236,
+      "grad_norm": 0.1506437361240387,
+      "learning_rate": 1.6668608091748495e-05,
+      "loss": 0.342,
+      "step": 490
+    },
+    {
+      "epoch": 0.7515971439308531,
+      "grad_norm": 0.20785292983055115,
+      "learning_rate": 1.3844591860619383e-05,
+      "loss": 0.2928,
+      "step": 500
+    },
+    {
+      "epoch": 0.7515971439308531,
+      "eval_loss": 0.34627777338027954,
+      "eval_runtime": 35.2593,
+      "eval_samples_per_second": 31.793,
+      "eval_steps_per_second": 7.97,
+      "step": 500
+    },
+    {
+      "epoch": 0.7666290868094702,
+      "grad_norm": 0.11490298062562943,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 0.3752,
+      "step": 510
+    },
+    {
+      "epoch": 0.7816610296880872,
+      "grad_norm": 0.12073410302400589,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 0.3795,
+      "step": 520
+    },
+    {
+      "epoch": 0.7966929725667042,
+      "grad_norm": 0.11344490945339203,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 0.3594,
+      "step": 530
+    },
+    {
+      "epoch": 0.8117249154453213,
+      "grad_norm": 0.14574235677719116,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 0.3429,
+      "step": 540
+    },
+    {
+      "epoch": 0.8267568583239384,
+      "grad_norm": 0.2706868648529053,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 0.3157,
+      "step": 550
+    },
+    {
+      "epoch": 0.8267568583239384,
+      "eval_loss": 0.3458581268787384,
+      "eval_runtime": 35.1975,
+      "eval_samples_per_second": 31.849,
+      "eval_steps_per_second": 7.984,
+      "step": 550
+    },
+    {
+      "epoch": 0.8417888012025554,
+      "grad_norm": 0.1057230532169342,
+      "learning_rate": 2.259661018213333e-06,
+      "loss": 0.3975,
+      "step": 560
+    },
+    {
+      "epoch": 0.8568207440811725,
+      "grad_norm": 0.11743483692407608,
+      "learning_rate": 1.2731645278655445e-06,
+      "loss": 0.3814,
+      "step": 570
+    },
+    {
+      "epoch": 0.8718526869597896,
+      "grad_norm": 0.12397727370262146,
+      "learning_rate": 5.665199789862907e-07,
+      "loss": 0.3591,
+      "step": 580
+    },
+    {
+      "epoch": 0.8868846298384067,
+      "grad_norm": 0.14038552343845367,
+      "learning_rate": 1.4173043232380557e-07,
+      "loss": 0.3337,
+      "step": 590
+    },
+    {
+      "epoch": 0.9019165727170236,
+      "grad_norm": 0.2670811116695404,
+      "learning_rate": 0.0,
+      "loss": 0.321,
+      "step": 600
+    },
+    {
+      "epoch": 0.9019165727170236,
+      "eval_loss": 0.3471680283546448,
+      "eval_runtime": 35.4222,
+      "eval_samples_per_second": 31.647,
+      "eval_steps_per_second": 7.933,
+      "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": 1.24760405670101e+17,
+  "total_flos": 1.6628098653801677e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null