Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:613e8b957693fd895d45a1aadd1380ce1e8ac46c2c03a75469d28015fcada9b7
+oid sha256:2ecef8fa7e14960edc3ccb347ce6703af38091d30de79023cbc40dcabb86b7ca
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380df89f7bd835a0a20b0be597e5669cfa7385045b89cd3baa96620cdba84c82
-size 328468404
+oid sha256:c6a651078ad4ebf9db7dc0293881eb3b6c0fb0723fd137ffbf36a7b8cca221f2
+size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02ae481c8002fa1263f712f930a5df4f2c49037e33af7892692f742d795e7bee
+oid sha256:1889983b1ecda80870c997c8619834b2bf57d34e140454ca55a974593ecf251f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:180579b18c9e708a5cf9b411c96230bb3cb8d2c4c87c23004deaa70e5c990f72
+oid sha256:eb7fb5f22874147e56941b0c2b0e6e106f9317ff78b343462a5df511f2b8d1e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.150519847869873,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.17458100558659218,
+  "best_metric": 1.1186692714691162,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.20949720670391062,
   "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": 11.529,
       "eval_steps_per_second": 2.887,
       "step": 250
+    },
+    {
+      "epoch": 0.18156424581005587,
+      "grad_norm": 0.5020606517791748,
+      "learning_rate": 0.00011652775287473745,
+      "loss": 0.9043,
+      "step": 260
+    },
+    {
+      "epoch": 0.18854748603351956,
+      "grad_norm": 0.4165470004081726,
+      "learning_rate": 0.00010918189690211387,
+      "loss": 1.2468,
+      "step": 270
+    },
+    {
+      "epoch": 0.19553072625698323,
+      "grad_norm": 0.4466763138771057,
+      "learning_rate": 0.00010181810309788618,
+      "loss": 0.772,
+      "step": 280
+    },
+    {
+      "epoch": 0.20251396648044692,
+      "grad_norm": 0.5462682247161865,
+      "learning_rate": 9.447224712526258e-05,
+      "loss": 0.8108,
+      "step": 290
+    },
+    {
+      "epoch": 0.20949720670391062,
+      "grad_norm": 1.6482914686203003,
+      "learning_rate": 8.718011725613886e-05,
+      "loss": 1.9559,
+      "step": 300
+    },
+    {
+      "epoch": 0.20949720670391062,
+      "eval_loss": 1.1186692714691162,
+      "eval_runtime": 52.2511,
+      "eval_samples_per_second": 11.54,
+      "eval_steps_per_second": 2.89,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.06500940529664e+16,
+  "total_flos": 8.48689809063936e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null