Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34b616edce3c659fa5a3a1e2e1fd506e2883f960c3e97136037f070707892d81
+oid sha256:fdb5a9bb053473bf8e0de29d64b1e848e7c2d962c5f1869366410f7d9a8f517b
 size 598799664

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64209db8f3cb4bee434f1d3d51ce076f6069986691f906a7a5764fdab051996
+oid sha256:21cf3e15967105794d24f1c6581ee61f20e9cb0aacd5f4e20bcae76bf847c3b0
 size 167923706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd66f2dc416a164022f9a63e90b05cd64c9e0e49360e1de46684b5ebbb8d3b1a
+oid sha256:9b0ae598748e69b3cd8972746107b8fb2745f98e4fd90cec1f97a4c6c8e80b94
 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": 1.2517874240875244,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0003470715835140998,
+  "best_metric": 1.1996384859085083,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0006941431670281996,
   "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": 5.198,
       "eval_steps_per_second": 2.599,
       "step": 10
+    },
+    {
+      "epoch": 0.00041648590021691975,
+      "grad_norm": 3.965546131134033,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 5.3549,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005206073752711496,
+      "grad_norm": 2.184412956237793,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 4.4727,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005206073752711496,
+      "eval_loss": 1.2216558456420898,
+      "eval_runtime": 1479.7059,
+      "eval_samples_per_second": 8.199,
+      "eval_steps_per_second": 4.099,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006247288503253796,
+      "grad_norm": 2.2891042232513428,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.0955,
+      "step": 18
+    },
+    {
+      "epoch": 0.0006941431670281996,
+      "eval_loss": 1.1996384859085083,
+      "eval_runtime": 1103.7842,
+      "eval_samples_per_second": 10.991,
+      "eval_steps_per_second": 5.496,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1933802597253120.0,
+  "total_flos": 4064263085752320.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null