Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e280faf6b10ddce218b223d08e875d55ce1676e01f1682e076357c13b025ac0d
+oid sha256:804e66fb8775bc53874275754ae3235908b3206ce942cc57734582d60d22928e
 size 262219392

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc2e5166f2e3c2af5be4c9094a1e485c66fce69d008716a04011f6384448738
+oid sha256:bd07c50fc7945c05803117c1b70dfbe25654d70a289b17532b15309af12f0a72
 size 133778516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2096e127292fe61b4d4febaa26e79a15799382b567b3b3571a1ac39fb3efc9c5
+oid sha256:69331ff271a34482b4c65bbcd7b359361db942c133b23226dd4a13ff53579b9d
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5af47dd9c5e9b44c4716c2346f73b0786fc7e3f54a83c79e7160e9fd20c0002
+oid sha256:eee6af1247b0c3edba481f71529e1869926553e17a2f84fc94836be1e54d922b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.036011815071106,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.07271552072392341,
+  "best_metric": 1.0343050956726074,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.08079502302658156,
   "eval_steps": 50,
-  "global_step": 450,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -402,6 +402,49 @@
       "eval_samples_per_second": 9.221,
       "eval_steps_per_second": 2.307,
       "step": 450
+    },
+    {
+      "epoch": 0.07433142118445504,
+      "grad_norm": 0.9224958419799805,
+      "learning_rate": 4.183736838661559e-06,
+      "loss": 2.2102,
+      "step": 460
+    },
+    {
+      "epoch": 0.07594732164498667,
+      "grad_norm": 0.8685920834541321,
+      "learning_rate": 2.3600591207489855e-06,
+      "loss": 2.1594,
+      "step": 470
+    },
+    {
+      "epoch": 0.0775632221055183,
+      "grad_norm": 1.0734760761260986,
+      "learning_rate": 1.0510485759104009e-06,
+      "loss": 2.2938,
+      "step": 480
+    },
+    {
+      "epoch": 0.07917912256604993,
+      "grad_norm": 1.2365227937698364,
+      "learning_rate": 2.6308257193898664e-07,
+      "loss": 2.4919,
+      "step": 490
+    },
+    {
+      "epoch": 0.08079502302658156,
+      "grad_norm": 3.410151243209839,
+      "learning_rate": 0.0,
+      "loss": 2.3632,
+      "step": 500
+    },
+    {
+      "epoch": 0.08079502302658156,
+      "eval_loss": 1.0343050956726074,
+      "eval_runtime": 141.8642,
+      "eval_samples_per_second": 9.185,
+      "eval_steps_per_second": 2.298,
+      "step": 500
     }
   ],
   "logging_steps": 10,
@@ -425,12 +468,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9.06163151437824e+16,
+  "total_flos": 9.91328861159424e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null