Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:615f214c786c29ad50a88c588b39ffcae42e5cf4b24639a37458f232c82d8196
+oid sha256:1d8c3f7999b2043fea2ea90ca8c1f5491e76f00826772aac67b1c4fb32a4ac1c
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ef3d569f0feee7bbfb4d8f056e95c690b28aedcb13884b8a802be8f27d4681f
+oid sha256:6ce8d1896843648bd5a9f427f5356651d8bcd608e5a429b9b5e216224d9fd3e2
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10ed3347bac4bd11b84cafc58fab117491444ca2498e8432344896bb3701b6ef
+oid sha256:36de6021643d50a2e37adfebc48eac0227506eaf27bf48d55765a73f7ed91b8d
 size 14308

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": 1.9741289615631104,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0007970795007094007,
+  "epoch": 0.0015941590014188014,
   "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": 17.022,
       "eval_steps_per_second": 4.256,
       "step": 50
+    },
+    {
+      "epoch": 0.0009564954008512809,
+      "grad_norm": 0.5567274689674377,
+      "learning_rate": 0.00020275275110137215,
+      "loss": 1.8676,
+      "step": 60
+    },
+    {
+      "epoch": 0.001115911300993161,
+      "grad_norm": 0.9768388867378235,
+      "learning_rate": 0.00020201220897726938,
+      "loss": 1.824,
+      "step": 70
+    },
+    {
+      "epoch": 0.0012753272011350413,
+      "grad_norm": 0.8935255408287048,
+      "learning_rate": 0.00020078198147448128,
+      "loss": 1.8593,
+      "step": 80
+    },
+    {
+      "epoch": 0.0014347431012769214,
+      "grad_norm": 1.3647874593734741,
+      "learning_rate": 0.00019906806213773937,
+      "loss": 2.0022,
+      "step": 90
+    },
+    {
+      "epoch": 0.0015941590014188014,
+      "grad_norm": 9.45513916015625,
+      "learning_rate": 0.0001968788010097697,
+      "loss": 1.7834,
+      "step": 100
+    },
+    {
+      "epoch": 0.0015941590014188014,
+      "eval_loss": 2.133173704147339,
+      "eval_runtime": 1552.7201,
+      "eval_samples_per_second": 17.011,
+      "eval_steps_per_second": 4.253,
+      "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": 9153408411893760.0,
+  "total_flos": 1.857342095228928e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null