Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f64b9258ac80da142a63acc7cbf6876522c5103b777c1b955bc27f1408ca0516
+oid sha256:91001afcce286c33437fe8cb781bf2d2e7a68b0c9f27b39387011d68cd0e29e8
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a15194f0f584809f7f084c3d3c8e9527a461cca8df33091cb05007bf58d7c1a1
+oid sha256:de70acdfc34cafcdc708216ca3328735ce786773e20f06fa59c970dbb5fd3d1c
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd3f07e2983188d4722a82fd116dd58664f39b493fc1be3b04e80cfa19f1df0b
+oid sha256:2b48224e45cb502ee8ecd7dfdbc0c3b2ecf1cb31ae633c1f705b79ed73109c2c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f939f73d23e2dbcf206924457b3eb57b1e3cb5e54dc5c680d84d6737616b0365
+oid sha256:b0f69d9f90a0d5ce8ac61f1f875459a761943b0c4252d8391ecd4046776d8753
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.309641718864441,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.018342373503131306,
+  "best_metric": 1.215065360069275,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.020962712575007206,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 16.385,
       "eval_steps_per_second": 4.097,
       "step": 350
+    },
+    {
+      "epoch": 0.018866441317506484,
+      "grad_norm": 1.5316487550735474,
+      "learning_rate": 4.496232384598384e-05,
+      "loss": 1.1357,
+      "step": 360
+    },
+    {
+      "epoch": 0.019390509131881666,
+      "grad_norm": 1.5178347826004028,
+      "learning_rate": 3.9202529516782854e-05,
+      "loss": 1.0699,
+      "step": 370
+    },
+    {
+      "epoch": 0.019914576946256847,
+      "grad_norm": 2.074788808822632,
+      "learning_rate": 3.374867815139649e-05,
+      "loss": 1.0479,
+      "step": 380
+    },
+    {
+      "epoch": 0.020438644760632025,
+      "grad_norm": 2.566411256790161,
+      "learning_rate": 2.8627340365457602e-05,
+      "loss": 1.1419,
+      "step": 390
+    },
+    {
+      "epoch": 0.020962712575007206,
+      "grad_norm": 7.236230850219727,
+      "learning_rate": 2.3863466801864254e-05,
+      "loss": 1.6114,
+      "step": 400
+    },
+    {
+      "epoch": 0.020962712575007206,
+      "eval_loss": 1.215065360069275,
+      "eval_runtime": 490.1796,
+      "eval_samples_per_second": 16.392,
+      "eval_steps_per_second": 4.098,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.59974690701312e+16,
+  "total_flos": 7.54256789372928e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null