Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfcde852ee9a7df2f5bcf7cc836b939566d77608613a6d4a635687153c582c11
+oid sha256:9e2abbb1735f8877d5656b2ed34fb8aa60ff3819e2d3cce28072a98700980f30
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d38562cb7ead31bb4f8455b0dd5948da0880af22bf9664749faf057882408fc
+oid sha256:ce38b47ce36a136252bcf94df6e2762be65ff87bc54fb805735cd7c00cedee0b
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1889983b1ecda80870c997c8619834b2bf57d34e140454ca55a974593ecf251f
+oid sha256:96bcc9f2208627343efb282c69f858dfa3339a1ca3e40f4ad215b8dc03deb055
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddc1c3c9081614df1d173d04f01c875f9673209b6198d21cb724fdbf44311722
+oid sha256:15517f711b4d803046b15167942c5e55ce6a93d9447a6347918a0d65acdb3f4a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1206214427947998,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.20949720670391062,
+  "best_metric": 1.0982829332351685,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.24441340782122906,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 11.677,
       "eval_steps_per_second": 2.924,
       "step": 300
+    },
+    {
+      "epoch": 0.2164804469273743,
+      "grad_norm": 0.4230874478816986,
+      "learning_rate": 8.225147432743606e-05,
+      "loss": 0.9144,
+      "step": 310
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "grad_norm": 0.41244614124298096,
+      "learning_rate": 7.497165611031821e-05,
+      "loss": 0.8197,
+      "step": 320
+    },
+    {
+      "epoch": 0.23044692737430167,
+      "grad_norm": 0.46321332454681396,
+      "learning_rate": 6.785518461437353e-05,
+      "loss": 0.8108,
+      "step": 330
+    },
+    {
+      "epoch": 0.23743016759776536,
+      "grad_norm": 0.4879332184791565,
+      "learning_rate": 6.093673057338509e-05,
+      "loss": 0.8025,
+      "step": 340
+    },
+    {
+      "epoch": 0.24441340782122906,
+      "grad_norm": 1.3698660135269165,
+      "learning_rate": 5.4250000000000024e-05,
+      "loss": 2.2907,
+      "step": 350
+    },
+    {
+      "epoch": 0.24441340782122906,
+      "eval_loss": 1.0982829332351685,
+      "eval_runtime": 51.8499,
+      "eval_samples_per_second": 11.63,
+      "eval_steps_per_second": 2.912,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.48689809063936e+16,
+  "total_flos": 9.882126363131904e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null