Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b23585b4897ab94727c79ee2d11789db3c675915a8c980dc9ff11b965bdabd4
+oid sha256:6aeaccaf15d9cc905756383f4d5dc0bc26f9ef298ed5479c32a3032eaf843504
 size 25192688

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a237be99af1effd8dc1d3fddb943cc9a08b543eca15dd4a61485b31fa4e42691
+oid sha256:7026a902d899090a80dd51ccbfc74cfec268b79a877b96ff256662b6cd6a4ba0
 size 50445306

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec134605e1e781fc705a3279e09b0cbaee66f077da601816e59f2b3169ff7952
+oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
 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": 4.929401397705078,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00016036820539959748,
+  "best_metric": 4.605849742889404,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00032073641079919497,
   "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": 29.365,
       "eval_steps_per_second": 14.682,
       "step": 10
+    },
+    {
+      "epoch": 0.00019244184647951697,
+      "grad_norm": 8.726426124572754,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 19.5447,
+      "step": 12
+    },
+    {
+      "epoch": 0.00024055230809939623,
+      "grad_norm": 9.420560836791992,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 20.2183,
+      "step": 15
+    },
+    {
+      "epoch": 0.00024055230809939623,
+      "eval_loss": 4.678121566772461,
+      "eval_runtime": 890.1762,
+      "eval_samples_per_second": 29.495,
+      "eval_steps_per_second": 14.748,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002886627697192755,
+      "grad_norm": 7.593912124633789,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 19.6809,
+      "step": 18
+    },
+    {
+      "epoch": 0.00032073641079919497,
+      "eval_loss": 4.605849742889404,
+      "eval_runtime": 894.7504,
+      "eval_samples_per_second": 29.344,
+      "eval_steps_per_second": 14.672,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 151685494210560.0,
+  "total_flos": 303370988421120.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null