Training in progress, step 1650, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2436728f82aa4949abbbd0eb1a6a832a2bcc84241a1c8d50f4a85aee88f4ed2
+oid sha256:12dd6337fff44ebfc4e7e1f6faec086a74126aed257725a219090db632ba1030
 size 39131224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b97c4097242b845374e8cda7310f7388079dacabc54c6fd4bd420325b61d051
+oid sha256:4678aae90eb9fa309f5a4a27ba89b7a9b22d8a4eec881787c8813398426c1d77
 size 78510334

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74c141c60220302a6e2d4f05b7f65149392bf2b0c2708ca84f4fa67ea3c279a4
+oid sha256:220f636333a5625ead2a747eab34ed7373b77b6069afb40aaf422414ec699f94
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:befb5de8641401f08357d93e09a6b263a413b6c62f0e4dc381df697735030b77
+oid sha256:090e504a81765b504142cff403afcf92b817f0e48945f0e4e014e79a6565dad0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7997989654541016,
-  "best_model_checkpoint": "miner_id_24/checkpoint-1500",
-  "epoch": 2.2263030977555185,
+  "best_metric": 0.7954422831535339,
+  "best_model_checkpoint": "miner_id_24/checkpoint-1650",
+  "epoch": 2.4488963086625857,
   "eval_steps": 150,
-  "global_step": 1500,
+  "global_step": 1650,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 40.629,
       "eval_steps_per_second": 20.315,
       "step": 1500
+    },
+    {
+      "epoch": 2.300500834724541,
+      "grad_norm": 0.18251581490039825,
+      "learning_rate": 9.733794785622253e-05,
+      "loss": 0.7668,
+      "step": 1550
+    },
+    {
+      "epoch": 2.374698571693563,
+      "grad_norm": 0.1793128401041031,
+      "learning_rate": 9.202138944469168e-05,
+      "loss": 0.7456,
+      "step": 1600
+    },
+    {
+      "epoch": 2.4488963086625857,
+      "grad_norm": 0.17612189054489136,
+      "learning_rate": 8.672744727162781e-05,
+      "loss": 0.7508,
+      "step": 1650
+    },
+    {
+      "epoch": 2.4488963086625857,
+      "eval_loss": 0.7954422831535339,
+      "eval_runtime": 14.3584,
+      "eval_samples_per_second": 39.559,
+      "eval_steps_per_second": 19.779,
+      "step": 1650
     }
   ],
   "logging_steps": 50,
@@ -333,7 +362,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.7100828573696e+16,
+  "total_flos": 1.88109114310656e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null