Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:036a2924083ee1fa72bc41c1c86e3c86ecd3a9d3c0aab0e4f47746d642a0d3d1
+oid sha256:44b13c6f630aa2beb59468833d38c529427b5f746b7de85995eb82c29cae174e
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b88e4120ce40a43e5f8981607f62d54b655bbc0eba52c33b872fe6205fa3c418
+oid sha256:3760bdda6da915b795e4774a6ec7994c149684c5a0becd8dcc91521927065bb8
 size 400361770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af7e1cddce70edc2e4374c3bb5fe3a4427b87ebc740dfbc7223046fe644e372b
+oid sha256:e48edcebabf5e5f11375e5ac67145183527090086d1b3209c2358749ad54019d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.985470771789551,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.01137009664582149,
+  "best_metric": 2.715874195098877,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.02274019329164298,
   "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": 6.985,
       "eval_steps_per_second": 1.753,
       "step": 10
+    },
+    {
+      "epoch": 0.013644115974985787,
+      "grad_norm": 2.700772285461426,
+      "learning_rate": 0.000163742398974869,
+      "loss": 2.642,
+      "step": 12
+    },
+    {
+      "epoch": 0.017055144968732235,
+      "grad_norm": 2.2496864795684814,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.45,
+      "step": 15
+    },
+    {
+      "epoch": 0.017055144968732235,
+      "eval_loss": 2.8052423000335693,
+      "eval_runtime": 106.248,
+      "eval_samples_per_second": 6.974,
+      "eval_steps_per_second": 1.751,
+      "step": 15
+    },
+    {
+      "epoch": 0.02046617396247868,
+      "grad_norm": 2.46319580078125,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 2.2653,
+      "step": 18
+    },
+    {
+      "epoch": 0.02274019329164298,
+      "eval_loss": 2.715874195098877,
+      "eval_runtime": 106.9327,
+      "eval_samples_per_second": 6.93,
+      "eval_steps_per_second": 1.739,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7860667205812224.0,
+  "total_flos": 1.5529610821238784e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null