Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:454f3274b145d17cadea3470ce753691d6aad3964cb68202452ed9de78a09ca0
+oid sha256:96b0f673d934bce426e5518cba6336dfa721175d6061da6b1d10238d976944cc
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf23d039687488ae25ee7c01bab34847197ca990d264d3d4e0bf7ec427931140
+oid sha256:9af6b529d72f1efa88c07f35348154e953ccc72a49b0850bbb5eab6b4d8e3d6f
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:222b56b9f8df0f0e53f193b41fb7b31d9e4883bc8c3809d0e1455a3588234cfb
+oid sha256:d2f8d836fc74ab1dcd19c00e141e586a98256bb27f2b43f2fea9ac75779943de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e231c2c515a5ff10f1e544b2aa46a8eaae94bd71a11db0123cabe0d1726bb1ba
+oid sha256:80e3c543dd881d7b92b58f753c91bcd488f8269b3e4ffd67623431c55e782209
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.3279521465301514,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.14513788098693758,
+  "best_metric": 2.181504249572754,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.21770682148040638,
   "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": 11.901,
       "eval_steps_per_second": 2.996,
       "step": 100
+    },
+    {
+      "epoch": 0.15965166908563136,
+      "grad_norm": 1.2206093072891235,
+      "learning_rate": 0.00019805195486600916,
+      "loss": 2.1955,
+      "step": 110
+    },
+    {
+      "epoch": 0.1741654571843251,
+      "grad_norm": 1.1765705347061157,
+      "learning_rate": 0.00019488507586089894,
+      "loss": 2.1238,
+      "step": 120
+    },
+    {
+      "epoch": 0.18867924528301888,
+      "grad_norm": 1.411720871925354,
+      "learning_rate": 0.00019127297795219008,
+      "loss": 2.1084,
+      "step": 130
+    },
+    {
+      "epoch": 0.20319303338171263,
+      "grad_norm": 1.5477889776229858,
+      "learning_rate": 0.00018723325891780706,
+      "loss": 2.1483,
+      "step": 140
+    },
+    {
+      "epoch": 0.21770682148040638,
+      "grad_norm": 3.5689947605133057,
+      "learning_rate": 0.0001827855998628142,
+      "loss": 2.0485,
+      "step": 150
+    },
+    {
+      "epoch": 0.21770682148040638,
+      "eval_loss": 2.181504249572754,
+      "eval_runtime": 24.6073,
+      "eval_samples_per_second": 11.785,
+      "eval_steps_per_second": 2.967,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.611614133203763e+16,
+  "total_flos": 3.874994255403418e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null