Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37837b678ff32a9d46081fef5c965b72178328008b67cdf3fcbf58782633ac71
+oid sha256:33acb1d6c50fefa22243a8eef262650d8d92602708a320e06a67a922b9da403e
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1f25225d7d4d67cdba238771305e91331c0d5d241af925125c2d71a05d3e215
+oid sha256:aa87a3572fdf661d7fa7e0cddba214f25e757325e93af1e6d455aeef606d3563
 size 147360212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d98e31570c65c1304aa3ca79af60e9837b5f8bda25e97642e96d222a6719c140
+oid sha256:4599e2b662b721751b8f29197346da4bcf5ecef4f1b957d258185032c4290ecd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0f69d9f90a0d5ce8ac61f1f875459a761943b0c4252d8391ecd4046776d8753
+oid sha256:cb0db0205cf37887636e31665ab1051856b2efe4ed0485b1a8cad32db1f6dfbb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2252267599105835,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.09256045354622237,
+  "best_metric": 1.222978949546814,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.10413051023950018,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 23.836,
       "eval_steps_per_second": 5.959,
       "step": 400
+    },
+    {
+      "epoch": 0.09487446488487794,
+      "grad_norm": 0.2047654241323471,
+      "learning_rate": 1.9480266573755372e-05,
+      "loss": 1.2399,
+      "step": 410
+    },
+    {
+      "epoch": 0.0971884762235335,
+      "grad_norm": 0.2079543024301529,
+      "learning_rate": 1.5499094192044554e-05,
+      "loss": 1.2494,
+      "step": 420
+    },
+    {
+      "epoch": 0.09950248756218906,
+      "grad_norm": 0.20079194009304047,
+      "learning_rate": 1.1939345528389446e-05,
+      "loss": 1.254,
+      "step": 430
+    },
+    {
+      "epoch": 0.10181649890084461,
+      "grad_norm": 0.1996968388557434,
+      "learning_rate": 8.818363320454701e-06,
+      "loss": 1.2664,
+      "step": 440
+    },
+    {
+      "epoch": 0.10413051023950018,
+      "grad_norm": 0.3467692732810974,
+      "learning_rate": 6.1513526798373514e-06,
+      "loss": 1.1918,
+      "step": 450
+    },
+    {
+      "epoch": 0.10413051023950018,
+      "eval_loss": 1.222978949546814,
+      "eval_runtime": 76.2973,
+      "eval_samples_per_second": 23.854,
+      "eval_steps_per_second": 5.964,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.1870192510304256e+16,
+  "total_flos": 3.5861722136838144e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null