Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3aa94ece7f7c47c5b684fbfb60fe0fd9bfbdf64ed5cb737f3d4618a769438ad
+oid sha256:aeb4c70d0eb54db30135f9e1181d3f60ef363e7554f594d3aff36f5332327f77
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a420f9495ce9945bd903a46170b45dfbca0a2861bfb304aa84460493f6e3f421
+oid sha256:12ce5ff0caf4b3c5b30e1697d042e35909ab085e1846099cf7133e73c04fb15f
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b60307a8384f8d4e62ca6a0bde4b4018d9c22875125249ce3404f126cd927cc
+oid sha256:fad1d524fc47db40541de4bb31ebd2dbf7fbe2adb11e5083bb2c6cc16b4b3293
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0585a94ca770852d904d0a057ee7d0f13731dc026d439d9add35f155aff77fb2
+oid sha256:7a29a98d7724cf179d3beb2d49a34c568e23cf47a86cb77f3cd39efdcdbcc2de
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.2177441269159317,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.0637890708058686,
+  "best_metric": 0.20021717250347137,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.0850520944078248,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 13.671,
       "eval_steps_per_second": 3.425,
       "step": 150
+    },
+    {
+      "epoch": 0.06804167552625984,
+      "grad_norm": 0.3854157626628876,
+      "learning_rate": 0.00018310968873606635,
+      "loss": 0.1658,
+      "step": 160
+    },
+    {
+      "epoch": 0.07229428024665108,
+      "grad_norm": 0.4845024049282074,
+      "learning_rate": 0.0001777624095772184,
+      "loss": 0.1831,
+      "step": 170
+    },
+    {
+      "epoch": 0.07654688496704232,
+      "grad_norm": 0.9749467968940735,
+      "learning_rate": 0.0001720679471221826,
+      "loss": 0.1933,
+      "step": 180
+    },
+    {
+      "epoch": 0.08079948968743356,
+      "grad_norm": 0.8443153500556946,
+      "learning_rate": 0.00016605404421963453,
+      "loss": 0.2047,
+      "step": 190
+    },
+    {
+      "epoch": 0.0850520944078248,
+      "grad_norm": 1.4500705003738403,
+      "learning_rate": 0.00015975,
+      "loss": 0.2931,
+      "step": 200
+    },
+    {
+      "epoch": 0.0850520944078248,
+      "eval_loss": 0.20021717250347137,
+      "eval_runtime": 72.6074,
+      "eval_samples_per_second": 13.635,
+      "eval_steps_per_second": 3.416,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -172,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.3564427127095296e+16,
+  "total_flos": 4.47839968690176e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null