Training in progress, step 107, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd87937ced3de3b818b57ee45c5ad91a0b2aab76050990853b0ceba243e4d99c
+oid sha256:5508feddb72e1df80a397ad696709dfc1b3d28a096365a692bda3a96f182f042
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb46749be138d01511e0975759ec14610856e157605aa7830b164a27a94c78bd
+oid sha256:db31e72e84d509117d060edb2ada4fe8d0e69eb0f459dbeb4b6cff8b22d71e3a
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9e5f4f92834f76f4e8e16f9610fd5a1611a04f1f6f3ed0dbb8212c20d8ab159
+oid sha256:b64f8ff6880c5e67b66094199c91b541de8f77d54887348e36823d92a7ac0bd7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54e1b33060aa1896ff83a569391d348a9ec0988e6492b2677c2ebd57a88700b8
+oid sha256:9115d19f29cad07fed0dd5f8f69efe017189f597938ab6d300b5e3ea914190e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.23224526643753052,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.9345794392523364,
+  "epoch": 1.0,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 107,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -731,6 +731,55 @@
       "eval_samples_per_second": 12.141,
       "eval_steps_per_second": 3.086,
       "step": 100
+    },
+    {
+      "epoch": 0.9439252336448598,
+      "grad_norm": 0.7002161741256714,
+      "learning_rate": 9.410911550880475e-07,
+      "loss": 0.2533,
+      "step": 101
+    },
+    {
+      "epoch": 0.9532710280373832,
+      "grad_norm": 0.6093440651893616,
+      "learning_rate": 6.54164563305465e-07,
+      "loss": 0.1811,
+      "step": 102
+    },
+    {
+      "epoch": 0.9626168224299065,
+      "grad_norm": 0.7323504686355591,
+      "learning_rate": 4.189949386787462e-07,
+      "loss": 0.2834,
+      "step": 103
+    },
+    {
+      "epoch": 0.9719626168224299,
+      "grad_norm": 0.701038122177124,
+      "learning_rate": 2.3582894166930268e-07,
+      "loss": 0.2602,
+      "step": 104
+    },
+    {
+      "epoch": 0.9813084112149533,
+      "grad_norm": 0.44046589732170105,
+      "learning_rate": 1.0485868811441757e-07,
+      "loss": 0.2167,
+      "step": 105
+    },
+    {
+      "epoch": 0.9906542056074766,
+      "grad_norm": 0.6788187026977539,
+      "learning_rate": 2.6221547724253337e-08,
+      "loss": 0.3156,
+      "step": 106
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.561313807964325,
+      "learning_rate": 0.0,
+      "loss": 0.2182,
+      "step": 107
     }
   ],
   "logging_steps": 1,
@@ -754,12 +803,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.6405085168861184e+17,
+  "total_flos": 1.7536470352920576e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null