Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6058eec092c81464450059d3a9cf8f5397d5918b09b4c54b58cffe6a1e13a53
+oid sha256:630c5409a30788a21559f06166bfcc846250d3b105b923cc8357f07e912318f3
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49e2195baa8bb3b644bfcb681e2ee31dadafd820422c4904c8a648eb17bead17
+oid sha256:b111d17c6da2597d3b1c6661de5a66cd6c7fd87ec4d9d19ca279f77005bc7460
 size 147950010

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fddb71a9a3d250332f98e562706fe25ec1ff4e66f7c9c4eb0af41236fd2dde1a
+oid sha256:89699f0b3577d72b5b6de2d71d0ef276004d62fe3404dae5160b3a000e6359ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2709317207336426,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.011534025374855825,
+  "best_metric": 1.2335487604141235,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.02306805074971165,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 11.371,
       "eval_steps_per_second": 5.701,
       "step": 10
+    },
+    {
+      "epoch": 0.01384083044982699,
+      "grad_norm": 0.8952862024307251,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 1.2837,
+      "step": 12
+    },
+    {
+      "epoch": 0.01730103806228374,
+      "grad_norm": 0.8020761013031006,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 1.2892,
+      "step": 15
+    },
+    {
+      "epoch": 0.01730103806228374,
+      "eval_loss": 1.2458020448684692,
+      "eval_runtime": 32.0747,
+      "eval_samples_per_second": 11.38,
+      "eval_steps_per_second": 5.705,
+      "step": 15
+    },
+    {
+      "epoch": 0.020761245674740483,
+      "grad_norm": 1.059036374092102,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 1.1986,
+      "step": 18
+    },
+    {
+      "epoch": 0.02306805074971165,
+      "eval_loss": 1.2335487604141235,
+      "eval_runtime": 32.0723,
+      "eval_samples_per_second": 11.381,
+      "eval_steps_per_second": 5.706,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 653134418411520.0,
+  "total_flos": 1306268836823040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null