Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:564657632e83983f42c8a7f6a7477f27793512fa85a06e2e6c2a12e6cd9969d7
+oid sha256:4abd2394bff0d5e0616490f53057db386a685e20efe8926ec587b5254a7069df
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28650369f2a7b6d493bf1524fed346c9b02e71f03a379ed2593a3da6998c44d9
+oid sha256:b7578dca2bdcf0edb5113f6c91fe537bb8201d93a35c843ef88c65f039995d65
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3b67b1207b5c559b7cad0867484d06ef195f7498fd5847ee189fc6b9848dce0
+oid sha256:4fb04d53c32f2d5bd67ab5c0e66af36987277bd0439697b05fa91b0129cac6e9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6533744931221008,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004730928444707274,
+  "best_metric": 0.5574434995651245,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.009461856889414548,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 2.847,
       "eval_steps_per_second": 1.423,
       "step": 10
+    },
+    {
+      "epoch": 0.0052040212891780015,
+      "grad_norm": 0.7032672762870789,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.6387,
+      "step": 11
+    },
+    {
+      "epoch": 0.005677114133648729,
+      "grad_norm": 0.823402464389801,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7466,
+      "step": 12
+    },
+    {
+      "epoch": 0.006150206978119456,
+      "grad_norm": 0.6160491108894348,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.4986,
+      "step": 13
+    },
+    {
+      "epoch": 0.0066232998225901835,
+      "grad_norm": 0.745175838470459,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.5589,
+      "step": 14
+    },
+    {
+      "epoch": 0.007096392667060911,
+      "grad_norm": 0.8077852725982666,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.7678,
+      "step": 15
+    },
+    {
+      "epoch": 0.007096392667060911,
+      "eval_loss": 0.5799944400787354,
+      "eval_runtime": 314.2728,
+      "eval_samples_per_second": 2.832,
+      "eval_steps_per_second": 1.416,
+      "step": 15
+    },
+    {
+      "epoch": 0.007569485511531638,
+      "grad_norm": 0.6418875455856323,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.4989,
+      "step": 16
+    },
+    {
+      "epoch": 0.008042578356002365,
+      "grad_norm": 0.7355498671531677,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.5961,
+      "step": 17
+    },
+    {
+      "epoch": 0.008515671200473094,
+      "grad_norm": 0.889188826084137,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.6423,
+      "step": 18
+    },
+    {
+      "epoch": 0.008988764044943821,
+      "grad_norm": 0.6980040073394775,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5257,
+      "step": 19
+    },
+    {
+      "epoch": 0.009461856889414548,
+      "grad_norm": 0.6116844415664673,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.6106,
+      "step": 20
+    },
+    {
+      "epoch": 0.009461856889414548,
+      "eval_loss": 0.5574434995651245,
+      "eval_runtime": 316.095,
+      "eval_samples_per_second": 2.816,
+      "eval_steps_per_second": 1.408,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3439964549283840.0,
+  "total_flos": 7071038240194560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null