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:b7e855a35f141b5253607d53f94522c7f284d2be9cc5e3dabbea324b5352af47
+oid sha256:a568b508e9355a47048e3a8a97449028695d12fa2733dc3f0b827ab748d1f60f
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a4a41ac6a3b5f191aab5d435dfc2db58bb3d9f5b72d19929c40bcb83c6a7c4e
-size 341314196
+oid sha256:6f8af1dce93ad0109737df42af8c775242a4d902e6b217d23390637c67f88c77
+size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b37d25a32f33a65385df3a85085a9aa67a364c56de5b730154339b363ed6b6ad
+oid sha256:31b90a2658a91fd2095b78f4edf43108110add2d1bb7198edca067b5374f45b9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5245962b37abe5debb29d3c0771306ab720257c32ca897672f6c78751ec6642f
+oid sha256:4e3407292f65425c0593f095883f5f3c050baccb28fc15b3c1ad88090d6c23ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.196916341781616,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.09020386072523905,
+  "best_metric": 2.1419291496276855,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.10824463287028685,
   "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": 15.966,
       "eval_steps_per_second": 3.995,
       "step": 250
+    },
+    {
+      "epoch": 0.0938120151542486,
+      "grad_norm": 1.4615882635116577,
+      "learning_rate": 0.00012039360249617425,
+      "loss": 2.2424,
+      "step": 260
+    },
+    {
+      "epoch": 0.09742016958325816,
+      "grad_norm": 1.7726435661315918,
+      "learning_rate": 0.00011280404514057264,
+      "loss": 2.147,
+      "step": 270
+    },
+    {
+      "epoch": 0.10102832401226773,
+      "grad_norm": 1.9420199394226074,
+      "learning_rate": 0.00010519595485942743,
+      "loss": 2.157,
+      "step": 280
+    },
+    {
+      "epoch": 0.10463647844127728,
+      "grad_norm": 2.1413962841033936,
+      "learning_rate": 9.76063975038258e-05,
+      "loss": 1.9894,
+      "step": 290
+    },
+    {
+      "epoch": 0.10824463287028685,
+      "grad_norm": 5.385281562805176,
+      "learning_rate": 9.00723486343046e-05,
+      "loss": 2.0386,
+      "step": 300
+    },
+    {
+      "epoch": 0.10824463287028685,
+      "eval_loss": 2.1419291496276855,
+      "eval_runtime": 73.4196,
+      "eval_samples_per_second": 15.895,
+      "eval_steps_per_second": 3.977,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.864956291455386e+16,
+  "total_flos": 5.845490117640192e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null