Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce55eae5143e44bedba21839a287fdaefe81d278047872f7b15f365c553baa33
+oid sha256:c6b7b374bccaa753c8998ccbefe4d5ea4bd82d8ce717af4cbde591e21261f3ff
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:068337dbbdc24c920314550b4d297f12930a9da549f71535723634dc8925ac56
+oid sha256:22e65d0405190cd72d8b0ecd23e5632449682712f04f3c76f8a82ddbc5518b47
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc1ac17452726e5cedfbf9cc2e40377e5a6129f49113fea151b529c4b6d68216
+oid sha256:3ec7fddaa93b8a5104562fd596c16565abf5deb95425dbc4839aa86c8fa34863
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:321b462a2538632d6d720f0cf198c8f471dee11f51db9b50cc50d1fa7f132bbe
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7966330051422119,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.02386634844868735,
+  "best_metric": 0.7479696273803711,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0477326968973747,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 1.99,
       "eval_steps_per_second": 1.0,
       "step": 10
+    },
+    {
+      "epoch": 0.026252983293556086,
+      "grad_norm": 1.3630088567733765,
+      "learning_rate": 0.0001999979446958366,
+      "loss": 0.8378,
+      "step": 11
+    },
+    {
+      "epoch": 0.028639618138424822,
+      "grad_norm": 0.4510791301727295,
+      "learning_rate": 0.00019999177886783194,
+      "loss": 0.8985,
+      "step": 12
+    },
+    {
+      "epoch": 0.031026252983293555,
+      "grad_norm": 0.5864933729171753,
+      "learning_rate": 0.00019998150276943902,
+      "loss": 0.6781,
+      "step": 13
+    },
+    {
+      "epoch": 0.03341288782816229,
+      "grad_norm": 0.423950731754303,
+      "learning_rate": 0.000199967116823068,
+      "loss": 0.5872,
+      "step": 14
+    },
+    {
+      "epoch": 0.03579952267303103,
+      "grad_norm": 0.5833825469017029,
+      "learning_rate": 0.0001999486216200688,
+      "loss": 0.7589,
+      "step": 15
+    },
+    {
+      "epoch": 0.03579952267303103,
+      "eval_loss": 0.7643417119979858,
+      "eval_runtime": 88.8878,
+      "eval_samples_per_second": 1.991,
+      "eval_steps_per_second": 1.001,
+      "step": 15
+    },
+    {
+      "epoch": 0.03818615751789976,
+      "grad_norm": 0.368539035320282,
+      "learning_rate": 0.00019992601792070679,
+      "loss": 0.684,
+      "step": 16
+    },
+    {
+      "epoch": 0.0405727923627685,
+      "grad_norm": 0.4044187664985657,
+      "learning_rate": 0.00019989930665413147,
+      "loss": 0.7617,
+      "step": 17
+    },
+    {
+      "epoch": 0.04295942720763723,
+      "grad_norm": 0.590376079082489,
+      "learning_rate": 0.00019986848891833845,
+      "loss": 0.7967,
+      "step": 18
+    },
+    {
+      "epoch": 0.045346062052505964,
+      "grad_norm": 0.3635483384132385,
+      "learning_rate": 0.0001998335659801241,
+      "loss": 0.5567,
+      "step": 19
+    },
+    {
+      "epoch": 0.0477326968973747,
+      "grad_norm": 0.5464037656784058,
+      "learning_rate": 0.00019979453927503364,
+      "loss": 0.6186,
+      "step": 20
+    },
+    {
+      "epoch": 0.0477326968973747,
+      "eval_loss": 0.7479696273803711,
+      "eval_runtime": 88.8942,
+      "eval_samples_per_second": 1.991,
+      "eval_steps_per_second": 1.001,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.492020904329216e+16,
+  "total_flos": 2.984041808658432e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null