Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db639cbefc69a6e9eee3c62e74c56e20ad0abb19f10d41978d561ff2a27025c0
+oid sha256:bbc2fdf0e9feaed1943b49d51ef5fae3a170423c7db6afdb779aae68d58da16c
 size 217931936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f9c222822217fd80af6fcf84174adf879fcdb48a0ef0ab569413c4a4ba6193
-size 111412180
+oid sha256:47d33b9ca058ae34badce8aad1e740c5dadfa1d15f68a53a933deb73af2964c4
+size 111412820

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f802683501bce406335b3a99def0a3f58dad7df659475b0f2619337af902eed9
+oid sha256:33156baafc8ae76aed543720307b35f7895cc923a1a513ab85c16775d2e95270
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e4a8d9505ab5e0891e71b89f41010a5997ec96d8f1c5ec4c12ce973f5bf2fa
+oid sha256:a8d9346c4fcc90fb1ec8546736583b76a4fae6bc25cb93181337c187d15da94a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.155815839767456,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.16331863465621427,
+  "best_metric": 1.1323291063308716,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.19598236158745713,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 18.81,
       "eval_steps_per_second": 4.706,
       "step": 250
+    },
+    {
+      "epoch": 0.16985138004246284,
+      "grad_norm": 0.2267913520336151,
+      "learning_rate": 0.0001237326699871115,
+      "loss": 0.8876,
+      "step": 260
+    },
+    {
+      "epoch": 0.1763841254287114,
+      "grad_norm": 0.3093341886997223,
+      "learning_rate": 0.00011852887240871145,
+      "loss": 0.9403,
+      "step": 270
+    },
+    {
+      "epoch": 0.18291687081496,
+      "grad_norm": 0.43315809965133667,
+      "learning_rate": 0.00011327255272837221,
+      "loss": 0.9982,
+      "step": 280
+    },
+    {
+      "epoch": 0.18944961620120856,
+      "grad_norm": 0.8610518574714661,
+      "learning_rate": 0.00010797861055530831,
+      "loss": 1.1578,
+      "step": 290
+    },
+    {
+      "epoch": 0.19598236158745713,
+      "grad_norm": 3.0702617168426514,
+      "learning_rate": 0.00010266205214377748,
+      "loss": 1.3948,
+      "step": 300
+    },
+    {
+      "epoch": 0.19598236158745713,
+      "eval_loss": 1.1323291063308716,
+      "eval_runtime": 136.8684,
+      "eval_samples_per_second": 18.836,
+      "eval_steps_per_second": 4.713,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.1824410478444544e+17,
+  "total_flos": 2.6189292574133453e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null