Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80b0c069be1f99334549ee3e7ef82e4f991c65184bdb174892b650818ac6c42a
+oid sha256:f326f334eef37db7e81d1bdc92c8688331a0abc7cc3fb88f688626369d739878
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b1cbe3e1ad56eb729f9949a7f151384f75f7de2164ced739ee717f579afa50a
+oid sha256:dcb7967971c95e1cb3bec161bb5c36617b4c72d2f099ade3d966881a7c490888
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3273e6662d5bc26ddd0f96c5fb57c8729c00be63cf0428e791e11030a9be6376
+oid sha256:25eaed32035452f61b530f05ddb1757ce562ec2a5b996368ee4ed21c4aef9551
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14680b86f4f2c08a2d7e1e3f0cdd35571310973b8d85bb4aabd1acab6b3cccbe
+oid sha256:27d9d26262db0192551c63e8e2cb503f12fb8cb162ff6ce7f18ac6f7e9d328d6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.273123025894165,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.0032591337222566243,
+  "epoch": 0.006518267444513249,
   "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": 14.515,
       "eval_steps_per_second": 3.629,
       "step": 50
+    },
+    {
+      "epoch": 0.003910960466707949,
+      "grad_norm": 2.3496737480163574,
+      "learning_rate": 0.0002077466612270217,
+      "loss": 1.0568,
+      "step": 60
+    },
+    {
+      "epoch": 0.004562787211159274,
+      "grad_norm": 2.499488353729248,
+      "learning_rate": 0.0002069878791491233,
+      "loss": 1.1359,
+      "step": 70
+    },
+    {
+      "epoch": 0.005214613955610598,
+      "grad_norm": 3.1299209594726562,
+      "learning_rate": 0.00020572735047631578,
+      "loss": 1.2264,
+      "step": 80
+    },
+    {
+      "epoch": 0.005866440700061924,
+      "grad_norm": 3.3837058544158936,
+      "learning_rate": 0.00020397121637758515,
+      "loss": 1.2004,
+      "step": 90
+    },
+    {
+      "epoch": 0.006518267444513249,
+      "grad_norm": 2.973175287246704,
+      "learning_rate": 0.00020172803256173445,
+      "loss": 1.545,
+      "step": 100
+    },
+    {
+      "epoch": 0.006518267444513249,
+      "eval_loss": 1.275679111480713,
+      "eval_runtime": 446.3022,
+      "eval_samples_per_second": 14.474,
+      "eval_steps_per_second": 3.619,
+      "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": 1.0149182388043776e+16,
+  "total_flos": 2.0633874937675776e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null