Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e6ba3b6faf4c1f3e3e8609684969ad2b0d323a8f392e9f06c720aa12b2ba0eb
+oid sha256:a056528e3369fa588ba5485412dcea22ede8ce6ebed426c58f9cf73017c3361b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b353c711bd613e42ee15c87b4b4e9b4a6f99263b60c857c0f206c2c804d52ce
+oid sha256:ba9f251e2cf712cdd6616a697ab9f56ae08c4751d91572425ea1b18397c0cc21
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdf5305789d6ebecb96d6be885a9f3663bb8ec35160cd9fb1ba3c4b58b48d8cc
+oid sha256:281caa622fe5ee40089263a143d1925da983656dcfe2430d50bd0d2112cb7921
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10d0fa96665f6b4af4824faec3d1d9f4e8b4343723a14d86cab932da6ce3225
+oid sha256:e7e4a8d9505ab5e0891e71b89f41010a5997ec96d8f1c5ec4c12ce973f5bf2fa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.1126017570495605,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.05461123626186088,
+  "best_metric": 2.0528900623321533,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.06826404532732609,
   "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": 25.191,
       "eval_steps_per_second": 6.298,
       "step": 200
+    },
+    {
+      "epoch": 0.057341798074953924,
+      "grad_norm": 11.671783447265625,
+      "learning_rate": 0.00014845508703326504,
+      "loss": 8.1613,
+      "step": 210
+    },
+    {
+      "epoch": 0.06007235988804697,
+      "grad_norm": 11.406132698059082,
+      "learning_rate": 0.00014373073204588556,
+      "loss": 7.8322,
+      "step": 220
+    },
+    {
+      "epoch": 0.06280292170114,
+      "grad_norm": 11.966191291809082,
+      "learning_rate": 0.00013888241754733208,
+      "loss": 7.5859,
+      "step": 230
+    },
+    {
+      "epoch": 0.06553348351423305,
+      "grad_norm": 14.312826156616211,
+      "learning_rate": 0.00013392388661180303,
+      "loss": 8.059,
+      "step": 240
+    },
+    {
+      "epoch": 0.06826404532732609,
+      "grad_norm": 26.518217086791992,
+      "learning_rate": 0.0001288691947339621,
+      "loss": 7.8758,
+      "step": 250
+    },
+    {
+      "epoch": 0.06826404532732609,
+      "eval_loss": 2.0528900623321533,
+      "eval_runtime": 245.0717,
+      "eval_samples_per_second": 25.168,
+      "eval_steps_per_second": 6.292,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.406258997362688e+17,
+  "total_flos": 1.75782374670336e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null