Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1168e5b8b1c52b89556c033ff67fd9831b3ca5251d9c2a2e62b2df28843d988
+oid sha256:5f983e7c66880ee98c81515a520726d30dd4b8a9596315f1fd5b4e14f654bd60
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a50c4599ed8d3f96a778732216801f188ce39983e30b56ba7f5aeb7742c90ac
+oid sha256:c913e77242d333f2e2aae912580d07bc70f85385b0b0cad97cad20f525fa68c5
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33e70537bf9ca12ee7c7d03210f07cbbed909aa7328895abf3cc4ad034759531
+oid sha256:1653c951f7583b8f259d5b4ec4d815208b4d0f7002c38b7d86a02261c520a5bf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9aefa5c0989fb1076f44dee5ec81119730caab480902e567590e4c3defecd81d
+oid sha256:4be7b38aa7a01f117ebb95bff4f596a12bcbebf1c53b704b1e44c42b56276682
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0811328887939453,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.12628540501533467,
+  "best_metric": 2.0443766117095947,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.14432617716038246,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 15.91,
       "eval_steps_per_second": 3.981,
       "step": 350
+    },
+    {
+      "epoch": 0.12989355944434422,
+      "grad_norm": 1.0652941465377808,
+      "learning_rate": 4.804797352168861e-05,
+      "loss": 2.1246,
+      "step": 360
+    },
+    {
+      "epoch": 0.13350171387335377,
+      "grad_norm": 1.3440688848495483,
+      "learning_rate": 4.189289918950325e-05,
+      "loss": 2.0742,
+      "step": 370
+    },
+    {
+      "epoch": 0.13710986830236335,
+      "grad_norm": 1.5741288661956787,
+      "learning_rate": 3.606476390688449e-05,
+      "loss": 2.0424,
+      "step": 380
+    },
+    {
+      "epoch": 0.1407180227313729,
+      "grad_norm": 1.601135492324829,
+      "learning_rate": 3.0591961763087043e-05,
+      "loss": 2.0331,
+      "step": 390
+    },
+    {
+      "epoch": 0.14432617716038246,
+      "grad_norm": 4.815340518951416,
+      "learning_rate": 2.550115570003141e-05,
+      "loss": 2.0085,
+      "step": 400
+    },
+    {
+      "epoch": 0.14432617716038246,
+      "eval_loss": 2.0443766117095947,
+      "eval_runtime": 73.424,
+      "eval_samples_per_second": 15.894,
+      "eval_steps_per_second": 3.977,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.826023943824998e+16,
+  "total_flos": 7.797129560142643e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null