Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8e5ff6fdf5d4a84b8911162dcee2530d15290ab1e2a8fc776e0f39bb07c007
+oid sha256:ddbba15e81bfcf58052a41c18cd6b1b2dbb08d73044f26b95792512840987690
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e3f3205d5a9ab8f0ea6e794388497006bc20cef52548f78d9fac15a46d57c17
+oid sha256:f90a8cde59d78d2d75b14df8a80e63fcfbf097b2ef768f2c0b07472d039cae4f
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:148f1afbe85e53f6df3756a21f8a0ab665094392e08503828b5e3a1004bdf711
+oid sha256:933e7a10d39a8bc7b41a4d7891c460551af07930f25cbc6e9459a8df7bea5f1c
 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": 1.335775375366211,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00016986364196141547,
+  "best_metric": 1.2575994729995728,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00033972728392283095,
   "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": 6.448,
       "eval_steps_per_second": 3.224,
       "step": 10
+    },
+    {
+      "epoch": 0.00020383637035369857,
+      "grad_norm": 48.66492462158203,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 5.9054,
+      "step": 12
+    },
+    {
+      "epoch": 0.0002547954629421232,
+      "grad_norm": 5.9232587814331055,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 5.7512,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002547954629421232,
+      "eval_loss": 1.3063114881515503,
+      "eval_runtime": 3840.6394,
+      "eval_samples_per_second": 6.454,
+      "eval_steps_per_second": 3.227,
+      "step": 15
+    },
+    {
+      "epoch": 0.0003057545555305479,
+      "grad_norm": 2.6109163761138916,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 5.721,
+      "step": 18
+    },
+    {
+      "epoch": 0.00033972728392283095,
+      "eval_loss": 1.2575994729995728,
+      "eval_runtime": 3839.1217,
+      "eval_samples_per_second": 6.457,
+      "eval_steps_per_second": 3.228,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3349006302314496.0,
+  "total_flos": 6698012604628992.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null