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:ea3a360f5343e976710653feed24558cd831ac8f25b847c85db2be40216fbbae
+oid sha256:849a72ff52b8bc2a8af5552ebd0ed2478fe51ed93c8fb606267f44f9b03cecde
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4014c57ae0f27f8a68740a911e0d9536d3fb65c1b027c33fbca28bbadd6f33a
+oid sha256:9a41500702f93a35f81c9c800c4666d6633e5ce1f21dda2691d9fd9c1ef13790
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20efeed8359c730e586f1b7f06278afa1441ab77b8079094afd4d1c8544d9bf9
+oid sha256:1da087fd5b2cc926e4168efc7d258313d88f010a602804a95e7662b97eb818aa
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd4836ddf60b44e58a6b1c94aa6a6c90a55c6b9d3781b50bd68866141db98eb6
+oid sha256:44be7752e8f250f5c645b94c737a086e3ba6f8529fa94bf2d0ed1a0911f14f5a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.7514146566390991,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.005240678143751802,
+  "epoch": 0.007861017215627703,
   "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": 16.427,
       "eval_steps_per_second": 4.107,
       "step": 100
+    },
+    {
+      "epoch": 0.005764745958126981,
+      "grad_norm": 1.6452189683914185,
+      "learning_rate": 0.00019518163667954527,
+      "loss": 1.2991,
+      "step": 110
+    },
+    {
+      "epoch": 0.006288813772502162,
+      "grad_norm": 1.5686390399932861,
+      "learning_rate": 0.00019206065447161056,
+      "loss": 1.162,
+      "step": 120
+    },
+    {
+      "epoch": 0.006812881586877342,
+      "grad_norm": 1.821743369102478,
+      "learning_rate": 0.00018850090580795544,
+      "loss": 1.1572,
+      "step": 130
+    },
+    {
+      "epoch": 0.007336949401252522,
+      "grad_norm": 4.036351680755615,
+      "learning_rate": 0.00018451973342624464,
+      "loss": 1.2418,
+      "step": 140
+    },
+    {
+      "epoch": 0.007861017215627703,
+      "grad_norm": 12.068865776062012,
+      "learning_rate": 0.00018013653319813575,
+      "loss": 1.8739,
+      "step": 150
+    },
+    {
+      "epoch": 0.007861017215627703,
+      "eval_loss": 1.8119529485702515,
+      "eval_runtime": 489.208,
+      "eval_samples_per_second": 16.425,
+      "eval_steps_per_second": 4.107,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.88564197343232e+16,
+  "total_flos": 2.82846296014848e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null