Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f42f6604c474515d9650eccb85195f3fbfb50933f9a96bf7b0450590af8e306b
+oid sha256:3dbc157b16d127095d3b041cb9e440b7bc7a5f5552212fba2f9bd935f2ba3b25
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbdaf54e4e87c3bf76ff42e3d4933bb4e29b44fc563fc7d946c60214bd795749
+oid sha256:2ddaae87e12380274c4f5726bafce50f74922967853e95e197744f80c8f97d2b
 size 147360212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71fc351677279f18f516b810eb4ab3d66980707ebcb130a8442241cf3d17881b
+oid sha256:c38003ef86abbb071d125f7ff66342a2ea51deb2b5edf0d2a212cc88e85cc744
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89df26d2648b7bbd96c19b1cc0947215f3b7f788b7b6e7a6d1179c8d03cbffea
+oid sha256:23d0c4fcd75282d05c3ecf542229a263cdfdea966c314071913c5dc6faf85a25
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5720521211624146,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.007834457904478372,
+  "best_metric": 1.5629593133926392,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.008813765142538168,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 26.693,
       "eval_steps_per_second": 6.674,
       "step": 400
+    },
+    {
+      "epoch": 0.008030319352090332,
+      "grad_norm": 0.4348071813583374,
+      "learning_rate": 1.9671249579380422e-05,
+      "loss": 1.6855,
+      "step": 410
+    },
+    {
+      "epoch": 0.00822618079970229,
+      "grad_norm": 0.5242032408714294,
+      "learning_rate": 1.5651046095888127e-05,
+      "loss": 1.6195,
+      "step": 420
+    },
+    {
+      "epoch": 0.00842204224731425,
+      "grad_norm": 0.5005368590354919,
+      "learning_rate": 1.205639793553052e-05,
+      "loss": 1.569,
+      "step": 430
+    },
+    {
+      "epoch": 0.00861790369492621,
+      "grad_norm": 0.5892754793167114,
+      "learning_rate": 8.904817862812098e-06,
+      "loss": 1.5471,
+      "step": 440
+    },
+    {
+      "epoch": 0.008813765142538168,
+      "grad_norm": 0.715459406375885,
+      "learning_rate": 6.211660059051443e-06,
+      "loss": 1.5927,
+      "step": 450
+    },
+    {
+      "epoch": 0.008813765142538168,
+      "eval_loss": 1.5629593133926392,
+      "eval_runtime": 809.2741,
+      "eval_samples_per_second": 26.565,
+      "eval_steps_per_second": 6.642,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.620346133066547e+16,
+  "total_flos": 2.951250143556403e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null