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:a056528e3369fa588ba5485412dcea22ede8ce6ebed426c58f9cf73017c3361b
+oid sha256:9d944d1b19afe35ffe04d298b35a088edfa78c34538a0de4754d65f9a109cdbb
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba9f251e2cf712cdd6616a697ab9f56ae08c4751d91572425ea1b18397c0cc21
-size 85723284
+oid sha256:e9e8e817b9004431641af0dad99debabd1a9e77e47f09ac303c2f912ffcd3e25
+size 85723732

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:281caa622fe5ee40089263a143d1925da983656dcfe2430d50bd0d2112cb7921
+oid sha256:caaf30335ff5d41c24939218bc867f610adfabf7518ea645fd6efcb991b24d7c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7e4a8d9505ab5e0891e71b89f41010a5997ec96d8f1c5ec4c12ce973f5bf2fa
+oid sha256:a8d9346c4fcc90fb1ec8546736583b76a4fae6bc25cb93181337c187d15da94a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.0528900623321533,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.06826404532732609,
+  "best_metric": 2.002148151397705,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.08191685439279131,
   "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": 25.168,
       "eval_steps_per_second": 6.292,
       "step": 250
+    },
+    {
+      "epoch": 0.07099460714041914,
+      "grad_norm": 11.75592041015625,
+      "learning_rate": 0.0001237326699871115,
+      "loss": 7.8156,
+      "step": 260
+    },
+    {
+      "epoch": 0.07372516895351218,
+      "grad_norm": 10.208357810974121,
+      "learning_rate": 0.00011852887240871145,
+      "loss": 7.9382,
+      "step": 270
+    },
+    {
+      "epoch": 0.07645573076660522,
+      "grad_norm": 12.978534698486328,
+      "learning_rate": 0.00011327255272837221,
+      "loss": 7.6911,
+      "step": 280
+    },
+    {
+      "epoch": 0.07918629257969827,
+      "grad_norm": 15.648476600646973,
+      "learning_rate": 0.00010797861055530831,
+      "loss": 7.5699,
+      "step": 290
+    },
+    {
+      "epoch": 0.08191685439279131,
+      "grad_norm": 31.975311279296875,
+      "learning_rate": 0.00010266205214377748,
+      "loss": 8.2882,
+      "step": 300
+    },
+    {
+      "epoch": 0.08191685439279131,
+      "eval_loss": 2.002148151397705,
+      "eval_runtime": 245.0084,
+      "eval_samples_per_second": 25.175,
+      "eval_steps_per_second": 6.294,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.75782374670336e+17,
+  "total_flos": 2.109388496044032e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null