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:effa36ec01fc35606330efc854335fdd912eaf2b9a7562abb0cd3d042bfbd1d6
+oid sha256:a686aac1d540667b502c3b20b1be4f49bd66708cb4b7816c89ed0b61fd4036bc
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a53eaf3d65244d77fcef989810876e56fec74cd5b6251f34943c5bdb0d13eea
+oid sha256:1f3646303145c2a1800bab7f44542d99f5210d0001c0a19b5e63efa71324d389
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddb61b72a196ab6a9d75786e3ab5de4dea10fe6a918c927e06d0139699ee4bce
+oid sha256:ce88b1f42b6165f180f38aacd5861af89f182ebc1eee94b3d2b4c5d06cd24c69
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08c6d9b93a9a31eb6ebeb3ab3dc09ba23202435e453d5c3be3fefb3bbf21d637
+oid sha256:c727edfddfd92ab332879741bf9980e3d74d4772eeea66b51338d361717f69dc
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.2151694297790527,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.1137009664582149,
+  "best_metric": 2.101684093475342,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.14212620807276863,
   "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": 15.688,
       "eval_steps_per_second": 3.938,
       "step": 200
+    },
+    {
+      "epoch": 0.11938601478112564,
+      "grad_norm": 1.8511581420898438,
+      "learning_rate": 0.0001467138569724859,
+      "loss": 2.2388,
+      "step": 210
+    },
+    {
+      "epoch": 0.12507106310403637,
+      "grad_norm": 2.840690851211548,
+      "learning_rate": 0.00014020987252842305,
+      "loss": 2.0782,
+      "step": 220
+    },
+    {
+      "epoch": 0.13075611142694712,
+      "grad_norm": 3.4517576694488525,
+      "learning_rate": 0.00013351973342624464,
+      "loss": 1.8506,
+      "step": 230
+    },
+    {
+      "epoch": 0.13644115974985788,
+      "grad_norm": 3.9618589878082275,
+      "learning_rate": 0.00012667603335116609,
+      "loss": 1.7965,
+      "step": 240
+    },
+    {
+      "epoch": 0.14212620807276863,
+      "grad_norm": 14.236225128173828,
+      "learning_rate": 0.00011971211412202691,
+      "loss": 2.114,
+      "step": 250
+    },
+    {
+      "epoch": 0.14212620807276863,
+      "eval_loss": 2.101684093475342,
+      "eval_runtime": 47.3607,
+      "eval_samples_per_second": 15.646,
+      "eval_steps_per_second": 3.927,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.865566045536256e+16,
+  "total_flos": 4.827243451986739e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null