Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ae482b6d15dc2b649ec983dde1707412baef329de3a76c4f769397e27f61a29
+oid sha256:4c126cc47bd8f4955a98a883a51f9f029ca6a67f0d2b221904b0893189bedac7
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e45274aa9b99e5869cba483380398b8c518368d7d0ef114f611ea6af6c51c1
+oid sha256:07950f81671dbfdac03e925010e2c1537fff68aa4832e444b49b79e6c3c652fa
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d9db27186f8bec49db820e6ed2a7779212f5092142a6e82e6b3fcd0d809cb7
+oid sha256:147d5e53ee6646f08d73447e32b1869281903fe32cf71e9d840fefdd1b37a62f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de68da4a411755dd89261d95dc85b46978ce68b71b6b640a5e732fce38d3ca1d
+oid sha256:673699a33c258fc5668f5919a0c3d2b61b77874f7dbb4fb806a02e77a15f3cef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.73129653930664,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.5247813411078717,
+  "best_metric": 11.730972290039062,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.5830903790087464,
   "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": 222.65,
       "eval_steps_per_second": 56.125,
       "step": 450
+    },
+    {
+      "epoch": 0.5364431486880467,
+      "grad_norm": 0.2577865421772003,
+      "learning_rate": 3.893199558198952e-06,
+      "loss": 11.7349,
+      "step": 460
+    },
+    {
+      "epoch": 0.5481049562682215,
+      "grad_norm": 0.36814334988594055,
+      "learning_rate": 2.1961661262525285e-06,
+      "loss": 11.7333,
+      "step": 470
+    },
+    {
+      "epoch": 0.5597667638483965,
+      "grad_norm": 0.2903134822845459,
+      "learning_rate": 9.780590914721787e-07,
+      "loss": 11.7317,
+      "step": 480
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.42444494366645813,
+      "learning_rate": 2.4481294888766817e-07,
+      "loss": 11.728,
+      "step": 490
+    },
+    {
+      "epoch": 0.5830903790087464,
+      "grad_norm": 0.48598408699035645,
+      "learning_rate": 0.0,
+      "loss": 11.7218,
+      "step": 500
+    },
+    {
+      "epoch": 0.5830903790087464,
+      "eval_loss": 11.730972290039062,
+      "eval_runtime": 1.6274,
+      "eval_samples_per_second": 221.829,
+      "eval_steps_per_second": 55.918,
+      "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": 23306954342400.0,
+  "total_flos": 25896615936000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null