Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2db6089097ee5f04d991284485dbd43aa49e594e1f23d2382a28cc62b0f28d14
+oid sha256:5af04d18e4134b46a9a0895ab542b9c3456027e09170b7329e6eca48611aeffa
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb9e72c750a9ef36d7584f089d4d76da2995c4993e0f7b33d0bcde182605b60b
+oid sha256:7fa09760f408923f94fd1029a2eb68494cebe8d18e1abc6d9040da33552ab1de
 size 203622650

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97bec130ebc68c6c5cae1b22505c8330a3d1c8764d6741896721a15f7baaa77b
+oid sha256:20e1816ae3370f89ccd7ca21572840bb755ebc45ccbed715a8dd0c0de6a21ed9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.293621778488159,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0008618275052248292,
+  "best_metric": 2.027435064315796,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0017236550104496584,
   "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": 6.715,
       "eval_steps_per_second": 3.358,
       "step": 10
+    },
+    {
+      "epoch": 0.001034193006269795,
+      "grad_norm": 1.4376518726348877,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 2.1546,
+      "step": 12
+    },
+    {
+      "epoch": 0.0012927412578372438,
+      "grad_norm": 0.8561299443244934,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.0008,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012927412578372438,
+      "eval_loss": 2.138024091720581,
+      "eval_runtime": 726.3131,
+      "eval_samples_per_second": 6.727,
+      "eval_steps_per_second": 3.364,
+      "step": 15
+    },
+    {
+      "epoch": 0.0015512895094046927,
+      "grad_norm": 0.7144878506660461,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.1058,
+      "step": 18
+    },
+    {
+      "epoch": 0.0017236550104496584,
+      "eval_loss": 2.027435064315796,
+      "eval_runtime": 726.536,
+      "eval_samples_per_second": 6.725,
+      "eval_steps_per_second": 3.363,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1852139254579200.0,
+  "total_flos": 3745437159260160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null