Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a792ab734fdb12fcd9be0bb1e867fe91183c7f9ecf21c1163b4b797a274441b8
+oid sha256:8588b129197ba536e22f31768f7613f554c8e309180200a4d0029f902770f333
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7356b4fe4d49ca57dbf8d429321cdac26633c7d44a51745b879f8b6570da2d09
+oid sha256:e2ceda64f9b4bc13464e324f76e252bd7a0e47d2990afd2ae8fb10963c35d06e
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5260c8125a24537a0b9406dcd050daa45aa08666d31e6a0297dc30b84741333
+oid sha256:f2b8943e674f8bbdced045cb2530ea33584297335f08ea6bc4a911f482fdfb11
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd10496d8a5f7e45002ec724483dbe1d4186b3c7101bd21f93cd0629ecfe77be
+oid sha256:7e883b7b3f89fde3f0f981a15cfeb8504571510ffa0b99f735bed98a1fe00478
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3669174313545227,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.087527352297593,
+  "best_metric": 0.36381667852401733,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.13129102844638948,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 9.999,
       "eval_steps_per_second": 2.515,
       "step": 100
+    },
+    {
+      "epoch": 0.0962800875273523,
+      "grad_norm": 0.6095497608184814,
+      "learning_rate": 0.00019422486395072398,
+      "loss": 0.8385,
+      "step": 110
+    },
+    {
+      "epoch": 0.1050328227571116,
+      "grad_norm": 0.44535937905311584,
+      "learning_rate": 0.0001911191806751811,
+      "loss": 0.5802,
+      "step": 120
+    },
+    {
+      "epoch": 0.1137855579868709,
+      "grad_norm": 0.10592010617256165,
+      "learning_rate": 0.00018757688175987723,
+      "loss": 0.1586,
+      "step": 130
+    },
+    {
+      "epoch": 0.12253829321663019,
+      "grad_norm": 0.025220032781362534,
+      "learning_rate": 0.00018361522492905716,
+      "loss": 0.0018,
+      "step": 140
+    },
+    {
+      "epoch": 0.13129102844638948,
+      "grad_norm": 0.014781222678720951,
+      "learning_rate": 0.00017925351097657625,
+      "loss": 0.002,
+      "step": 150
+    },
+    {
+      "epoch": 0.13129102844638948,
+      "eval_loss": 0.36381667852401733,
+      "eval_runtime": 48.1198,
+      "eval_samples_per_second": 9.996,
+      "eval_steps_per_second": 2.515,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.252570367721472e+16,
+  "total_flos": 4.905515964432384e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null