Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:976a9742c1227ca7a6e6df52d5ae82f529c304421e223890e634f9d48eae6efe
+oid sha256:f67ae05c502a678d8e43e12b7bbad4caaf6ac34628043d1164c9a0493a40f832
 size 1006723888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f863ea5acb51028be5c29ec5a83a5dd9e000ab2b3fb1632defe2a4b3822934f
+oid sha256:ad62a158663cb0a00908103a6e8b4230b817c42ad3819a73f534490d32526879
 size 511971668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:424d5c02bcb17daf3aa2cfea2fff82942e6a1690c03f59c47ffbc28e96c0aa7b
+oid sha256:a4d723ba4874efb6b0df0bd5060d2b0fd6a692ec34184abcbf402615ba4357f1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac6ee4c7143f9893927b533c972fc3aa0da9526c7e014b3849d291e400a8521c
+oid sha256:cc8fda128404f5cc7285a078c14dccabc8f3e7d949516ad102b12752c4b2742a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.36825886368751526,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.18714909544603867,
+  "best_metric": 0.3663117289543152,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.20794343938448742,
   "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": 6.271,
       "eval_steps_per_second": 1.571,
       "step": 450
+    },
+    {
+      "epoch": 0.19130796423372842,
+      "grad_norm": 0.6672781109809875,
+      "learning_rate": 4.144998534599878e-06,
+      "loss": 0.3583,
+      "step": 460
+    },
+    {
+      "epoch": 0.19546683302141818,
+      "grad_norm": 0.49665266275405884,
+      "learning_rate": 2.3382067214827915e-06,
+      "loss": 0.3413,
+      "step": 470
+    },
+    {
+      "epoch": 0.19962570180910794,
+      "grad_norm": 0.5892883539199829,
+      "learning_rate": 1.0413166446519713e-06,
+      "loss": 0.3746,
+      "step": 480
+    },
+    {
+      "epoch": 0.20378457059679767,
+      "grad_norm": 0.6554787755012512,
+      "learning_rate": 2.6064662219881083e-07,
+      "loss": 0.3965,
+      "step": 490
+    },
+    {
+      "epoch": 0.20794343938448742,
+      "grad_norm": 0.7458004355430603,
+      "learning_rate": 0.0,
+      "loss": 0.4067,
+      "step": 500
+    },
+    {
+      "epoch": 0.20794343938448742,
+      "eval_loss": 0.3663117289543152,
+      "eval_runtime": 80.842,
+      "eval_samples_per_second": 6.271,
+      "eval_steps_per_second": 1.571,
+      "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": 1.200157492248576e+17,
+  "total_flos": 1.33350832472064e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null