Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4235e535c25261b13d613b8257d39724a9b67e7ffc7b3487c81dece41610b5c
+oid sha256:5813d56d0aba386abdc9b79ca3a9d7b3cc33cdb3efdf07cf8e70c15b5e8acf78
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87372a4011f191226058ca74143afbe8b5d833710b58bcdab7704829702aece5
+oid sha256:b53e0b76705822a6bcba0011ce7a2a3a6712d01f8e34e3e7d72c6506936e6e39
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e48bd82550a2fa78d62e6c67b78275b42000d371384591edff6b0d24a3bc5bf
+oid sha256:d75c7dd0aed4dd831c43c8a6f52fbed675f5f4e205b9be1ecf0cfba00f87b077
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bafcafa93344e734000a1bd1b561500d69d1ccecac0e67c8cade94cdf739e25e
+oid sha256:cd10496d8a5f7e45002ec724483dbe1d4186b3c7101bd21f93cd0629ecfe77be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.6901915073394775,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.024289531212047608,
+  "epoch": 0.048579062424095217,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 16.755,
       "eval_steps_per_second": 4.194,
       "step": 50
+    },
+    {
+      "epoch": 0.02914743745445713,
+      "grad_norm": 13.382312774658203,
+      "learning_rate": 0.00020275275110137215,
+      "loss": 2.9041,
+      "step": 60
+    },
+    {
+      "epoch": 0.03400534369686665,
+      "grad_norm": 11.256575584411621,
+      "learning_rate": 0.00020201220897726938,
+      "loss": 2.3314,
+      "step": 70
+    },
+    {
+      "epoch": 0.03886324993927617,
+      "grad_norm": 19.787755966186523,
+      "learning_rate": 0.00020078198147448128,
+      "loss": 3.2341,
+      "step": 80
+    },
+    {
+      "epoch": 0.04372115618168569,
+      "grad_norm": 25.911598205566406,
+      "learning_rate": 0.00019906806213773937,
+      "loss": 3.3715,
+      "step": 90
+    },
+    {
+      "epoch": 0.048579062424095217,
+      "grad_norm": 18.073326110839844,
+      "learning_rate": 0.0001968788010097697,
+      "loss": 3.3957,
+      "step": 100
+    },
+    {
+      "epoch": 0.048579062424095217,
+      "eval_loss": 1.8113958835601807,
+      "eval_runtime": 51.8565,
+      "eval_samples_per_second": 16.719,
+      "eval_steps_per_second": 4.185,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -72,7 +115,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8943737556172800.0,
+  "total_flos": 1.78874751123456e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null