Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2016ba667e54d0f0e7d2c4cf299c1ca7515b88863882a80947957f8d260a3700
+oid sha256:41aa631956fd0f486c70fae4cf4ae7010ebd3c876fde174591501b1052b4ee1e
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f2b83c2f990438f3ee1cf4f36575203d1a09199b67a7a523e4ae8a2be26aa1c
+oid sha256:3310c65127d5c2068f76af858b5986e1dd0ab97898456d8a43511cc5ff7e468b
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cde923dd25d49a18608ad2195296261a163ab1cd44e1c0838d6b8c98ee7e817b
+oid sha256:816d3dcd846bbb1512c6f699d7f36d19cded480aab305ca1682baa5c562bfc28
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd10496d8a5f7e45002ec724483dbe1d4186b3c7101bd21f93cd0629ecfe77be
+oid sha256:7e883b7b3f89fde3f0f981a15cfeb8504571510ffa0b99f735bed98a1fe00478
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1180486679077148,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.03682563063892469,
+  "best_metric": 1.0143712759017944,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.05523844595838704,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 10.89,
       "eval_steps_per_second": 2.722,
       "step": 100
+    },
+    {
+      "epoch": 0.040508193702817163,
+      "grad_norm": 1.1839851140975952,
+      "learning_rate": 0.00019422486395072398,
+      "loss": 2.1824,
+      "step": 110
+    },
+    {
+      "epoch": 0.04419075676670963,
+      "grad_norm": 1.347690224647522,
+      "learning_rate": 0.0001911191806751811,
+      "loss": 2.1568,
+      "step": 120
+    },
+    {
+      "epoch": 0.0478733198306021,
+      "grad_norm": 1.2591941356658936,
+      "learning_rate": 0.00018757688175987723,
+      "loss": 2.142,
+      "step": 130
+    },
+    {
+      "epoch": 0.051555882894494566,
+      "grad_norm": 1.2574785947799683,
+      "learning_rate": 0.00018361522492905716,
+      "loss": 2.0817,
+      "step": 140
+    },
+    {
+      "epoch": 0.05523844595838704,
+      "grad_norm": 1.4502058029174805,
+      "learning_rate": 0.00017925351097657625,
+      "loss": 1.9292,
+      "step": 150
+    },
+    {
+      "epoch": 0.05523844595838704,
+      "eval_loss": 1.0143712759017944,
+      "eval_runtime": 105.2365,
+      "eval_samples_per_second": 10.871,
+      "eval_steps_per_second": 2.718,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.026877886444339e+16,
+  "total_flos": 4.523685632488243e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null