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:ae1f4b3b8fa6482f26dcfd2b7ef12e44d2ff4bcd09b4f11c4634e1aea0fe583a
+oid sha256:07e8b59a814c9a088f6b9062440659bccc8fc289625fd1ff2e5b3c52147998cd
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21b877f28a07db9e7c30507f62636ff07f2b91a50901c52a31c8f64674570380
+oid sha256:8889c11567294a3dfe42417a85989fcd84a90c7cb2632f1841d04ba92d392ee0
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda6339cd47db3af8603587297922a0b548d42f4acbf057bbe10b7c4a0841407
+oid sha256:b18fd526770faca31d6b68eaac69de0bf5165319660d891f391c0303ed73e314
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bf1a6f89c4ccfeb423775f70e378195af348273ade7a1d504b8ad665994fa62
+oid sha256:0585a94ca770852d904d0a057ee7d0f13731dc026d439d9add35f155aff77fb2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.639454960823059,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.048579062424095217,
+  "epoch": 0.07286859363614283,
   "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": 16.745,
       "eval_steps_per_second": 4.191,
       "step": 100
+    },
+    {
+      "epoch": 0.053436968666504735,
+      "grad_norm": 20.774890899658203,
+      "learning_rate": 0.000203792591238937,
+      "loss": 3.2651,
+      "step": 110
+    },
+    {
+      "epoch": 0.05829487490891426,
+      "grad_norm": 13.955368041992188,
+      "learning_rate": 0.0002005339186394757,
+      "loss": 2.3564,
+      "step": 120
+    },
+    {
+      "epoch": 0.06315278115132378,
+      "grad_norm": 20.711078643798828,
+      "learning_rate": 0.00019681712224065936,
+      "loss": 3.2759,
+      "step": 130
+    },
+    {
+      "epoch": 0.0680106873937333,
+      "grad_norm": 20.040428161621094,
+      "learning_rate": 0.0001926603099009319,
+      "loss": 3.2425,
+      "step": 140
+    },
+    {
+      "epoch": 0.07286859363614283,
+      "grad_norm": 50.84387969970703,
+      "learning_rate": 0.00018808373319217114,
+      "loss": 3.6393,
+      "step": 150
+    },
+    {
+      "epoch": 0.07286859363614283,
+      "eval_loss": 1.8135055303573608,
+      "eval_runtime": 51.7534,
+      "eval_samples_per_second": 16.753,
+      "eval_steps_per_second": 4.193,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.78874751123456e+16,
+  "total_flos": 2.68312126685184e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null