Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d03e90d9df1b338b7439e482a08ff45783224762852bcf380888a7a1725cf23e
+oid sha256:d899b9b44828f0297b9f6217945ac2a339ec82ebeadfb4d8724b9e91572d050e
 size 295488936

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec01c07c74e94449c9799f9708b9dc1ce943eeb4cd9cfb5c16b7e0118169b549
+oid sha256:1117734ad619919636cf3a095e4e4502f42c834e375c5ec02aed5e2d67cdfe1a
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5857b8669f527dea2d44ffeef9bae03f52fee98fb82eaf4eb9ec42c1dcebc908
+oid sha256:769f047583b2fcdc7aa25db8a01280cf2a8e77e7912e9cc9fef875a47cba852c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:152cf5e1f9adf3dc2c608dbb3e394e09940ab42688cdb5a07d89f1cccb7f89a5
+oid sha256:d4d0f57336dd58c2282a758b1873df2644647c71e8296b0dab58cb3a9f5f7c78
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2068699598312378,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0017353278034220663,
+  "best_metric": 1.0001741647720337,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.0034706556068441327,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 44.428,
       "eval_steps_per_second": 11.107,
       "step": 50
+    },
+    {
+      "epoch": 0.00208239336410648,
+      "grad_norm": 0.7354454398155212,
+      "learning_rate": 6.992307692307692e-06,
+      "loss": 0.5196,
+      "step": 60
+    },
+    {
+      "epoch": 0.002429458924790893,
+      "grad_norm": 0.7986167669296265,
+      "learning_rate": 6.215384615384615e-06,
+      "loss": 0.6819,
+      "step": 70
+    },
+    {
+      "epoch": 0.0027765244854753065,
+      "grad_norm": 1.4324290752410889,
+      "learning_rate": 5.438461538461538e-06,
+      "loss": 0.9526,
+      "step": 80
+    },
+    {
+      "epoch": 0.0031235900461597196,
+      "grad_norm": 3.554446220397949,
+      "learning_rate": 4.661538461538462e-06,
+      "loss": 1.2829,
+      "step": 90
+    },
+    {
+      "epoch": 0.0034706556068441327,
+      "grad_norm": 30.22225570678711,
+      "learning_rate": 3.884615384615385e-06,
+      "loss": 2.0732,
+      "step": 100
+    },
+    {
+      "epoch": 0.0034706556068441327,
+      "eval_loss": 1.0001741647720337,
+      "eval_runtime": 274.0964,
+      "eval_samples_per_second": 44.262,
+      "eval_steps_per_second": 11.065,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3469845316239360.0,
+  "total_flos": 6939690632478720.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null