Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a06aeab1aec86300e6c1a0ab95a4d6539811a8cb6d486774344a53cdf56e5e2
+oid sha256:09e18b61ae27ec68b9b88d44e61be3008df85974a508e09b2d24bb905c81ded2
 size 1163996488

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9fb318d22d6f88f98d101e40354de70fcbed94551dbf0d0807c9d6573bccc5f3
+oid sha256:3b130348ae3941f2079204df2d240458fcf468f254d8ee8d8b3fc84f5c89f90a
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a61b4372520fc0761e876c8de37dde6116645eb0b904f7a1f561307c37cb2b6
+oid sha256:75e72a99565ae8bb95213b93c1292dc017d22b82a9c2b29ae6424067697a68ab
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:697eb5c311706d748c20f07b0521bb9d1f71aee638eb745112aecf80a82e51da
+oid sha256:d4ffe1cc6011db9bcd26d2a5ee9a2f60bf90f43b3c6aed165ee32997fe344b31
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.153864622116089,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.024140012070006035,
+  "epoch": 0.036210018105009054,
   "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": 17.312,
       "eval_steps_per_second": 4.335,
       "step": 100
+    },
+    {
+      "epoch": 0.026554013277006638,
+      "grad_norm": 4.219131946563721,
+      "learning_rate": 0.0002085764548830435,
+      "loss": 1.8166,
+      "step": 110
+    },
+    {
+      "epoch": 0.02896801448400724,
+      "grad_norm": 3.56708025932312,
+      "learning_rate": 0.00020524128762162305,
+      "loss": 2.1941,
+      "step": 120
+    },
+    {
+      "epoch": 0.03138201569100785,
+      "grad_norm": 6.397162437438965,
+      "learning_rate": 0.00020143724248105043,
+      "loss": 2.0798,
+      "step": 130
+    },
+    {
+      "epoch": 0.03379601689800845,
+      "grad_norm": 5.533897876739502,
+      "learning_rate": 0.0001971828523868693,
+      "loss": 1.9979,
+      "step": 140
+    },
+    {
+      "epoch": 0.036210018105009054,
+      "grad_norm": 7.768519878387451,
+      "learning_rate": 0.0001924988442999686,
+      "loss": 2.1741,
+      "step": 150
+    },
+    {
+      "epoch": 0.036210018105009054,
+      "eval_loss": 2.3202924728393555,
+      "eval_runtime": 100.8543,
+      "eval_samples_per_second": 17.302,
+      "eval_steps_per_second": 4.333,
+      "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": 1.66312072445952e+16,
+  "total_flos": 2.49468108668928e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null