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:a51579b106688c68b29a853dff4455ec147ba32914864ff41f585b3e0418ca95
+oid sha256:54eaeccfa42366eec3053481adc58c9abe7844142d46ee69ee534db192a6b2d2
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:988e0150d49a2651e1005b097bc92b3dfcd4401ecd2b6d301c45e45cfdbed147
+oid sha256:fde7d245b1af815cdb37087ffa3096c9d00ecee212968f741f25b9891cc6f064
 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 sha256:09bf653dc25e0c029a8db4ba507ae3589e41445bb2b0fcc38f99c09150129f49
+oid sha256:b3febf3425d01f9a8670f76097b63bdde8ab2c4b9db69f7e047b33a3ea4a950e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1187446117401123,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.20949720670391062,
+  "best_metric": 1.0988595485687256,
+  "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": 11.617,
       "eval_steps_per_second": 2.909,
       "step": 300
+    },
+    {
+      "epoch": 0.2164804469273743,
+      "grad_norm": 0.4224921762943268,
+      "learning_rate": 7.95982009620349e-05,
+      "loss": 0.9126,
+      "step": 310
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "grad_norm": 0.41170719265937805,
+      "learning_rate": 7.255321559063053e-05,
+      "loss": 0.819,
+      "step": 320
+    },
+    {
+      "epoch": 0.23044692737430167,
+      "grad_norm": 0.4653985798358917,
+      "learning_rate": 6.566630769132923e-05,
+      "loss": 0.8104,
+      "step": 330
+    },
+    {
+      "epoch": 0.23743016759776536,
+      "grad_norm": 0.4874189496040344,
+      "learning_rate": 5.897102958714686e-05,
+      "loss": 0.8025,
+      "step": 340
+    },
+    {
+      "epoch": 0.24441340782122906,
+      "grad_norm": 1.3538293838500977,
+      "learning_rate": 5.250000000000002e-05,
+      "loss": 2.2914,
+      "step": 350
+    },
+    {
+      "epoch": 0.24441340782122906,
+      "eval_loss": 1.0988595485687256,
+      "eval_runtime": 53.0976,
+      "eval_samples_per_second": 11.356,
+      "eval_steps_per_second": 2.844,
+      "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