Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f3fc86f2c61c685d86292237dbde5254df1b82d6856775897d7c7269a5eb51a3
+oid sha256:b5caabcbb20b18cddbc5232d33998a0090db2d010c7305f28e6c0cdbe33c0793
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d423327a6a441a655092b6c53bcefcd888bffa8880b1ca354f6cc783b1c8ee
+oid sha256:317068638c37dd22186c008dc81092262d677ca89c8767b8475821097d3f7d50
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:542da8d551e0c417e013011b8706e763ab5b1bc78b1362718ff9c733b64229b8
+oid sha256:34dd8fce3e6b1676652d98ecfdce8d505350e79db15ba965f80fca277ae52abc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e4a64d71eed58bad723d1496b310be4dbd45cd96d8ef2f7cd1e195fe59bff7c
+oid sha256:bc179f00b2227acaa3346fbc12b482f11319c504cfa09741eaad17d644154679
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.118581533432007,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.29027576197387517,
+  "best_metric": 2.0795581340789795,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.36284470246734396,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 11.664,
       "eval_steps_per_second": 2.936,
       "step": 200
+    },
+    {
+      "epoch": 0.3047895500725689,
+      "grad_norm": 1.1066410541534424,
+      "learning_rate": 0.0001488714136926695,
+      "loss": 2.1385,
+      "step": 210
+    },
+    {
+      "epoch": 0.3193033381712627,
+      "grad_norm": 1.1471424102783203,
+      "learning_rate": 0.0001422717824185469,
+      "loss": 2.0349,
+      "step": 220
+    },
+    {
+      "epoch": 0.33381712626995647,
+      "grad_norm": 1.2833964824676514,
+      "learning_rate": 0.00013548325891780705,
+      "loss": 2.0561,
+      "step": 230
+    },
+    {
+      "epoch": 0.3483309143686502,
+      "grad_norm": 1.6310219764709473,
+      "learning_rate": 0.0001285389161945656,
+      "loss": 2.0573,
+      "step": 240
+    },
+    {
+      "epoch": 0.36284470246734396,
+      "grad_norm": 2.8112406730651855,
+      "learning_rate": 0.0001214725863885273,
+      "loss": 2.0216,
+      "step": 250
+    },
+    {
+      "epoch": 0.36284470246734396,
+      "eval_loss": 2.0795581340789795,
+      "eval_runtime": 24.4537,
+      "eval_samples_per_second": 11.859,
+      "eval_steps_per_second": 2.985,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.157230797337395e+16,
+  "total_flos": 6.467751968872858e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null