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:aa8a51ebbcb32c68a2554e237087d1035efa5a083be777faa4b3fbe4f9c04125
+oid sha256:3d891ef520b2ab72433790aff0ff7da025ec4b8f9e7ade86613e2f859ee7124d
 size 1006723888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:887ce0a12f0297bc8950056646dc889b71dd9951e4a66fc37a67ec1540939514
+oid sha256:7a14d0c901de26136844d9e6f604c584126a9632997ca3b5f8de9d25d7f4174d
 size 511971668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6cf4ce058e3ca489edbe37db984d596614690f02ef602ad22fbe9004a2f60f6
+oid sha256:790902726b2a9a483e01259d5009c663b982a9482d8a7398a9439ae9add7dea5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
+oid sha256:71a96715f430c2eb0d6104363f54769b2c1bdb005671dc81f0d67833a84ba743
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.39971646666526794,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.09358427784132266,
+  "best_metric": 0.3960544764995575,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.10398253093480295,
   "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": 6.267,
       "eval_steps_per_second": 1.57,
       "step": 450
+    },
+    {
+      "epoch": 0.09566392846001871,
+      "grad_norm": 1.0529413223266602,
+      "learning_rate": 4.22247514272324e-06,
+      "loss": 0.3989,
+      "step": 460
+    },
+    {
+      "epoch": 0.09774357907871478,
+      "grad_norm": 1.2673580646514893,
+      "learning_rate": 2.38191152001518e-06,
+      "loss": 0.4017,
+      "step": 470
+    },
+    {
+      "epoch": 0.09982322969741084,
+      "grad_norm": 0.7570623755455017,
+      "learning_rate": 1.0607805071688306e-06,
+      "loss": 0.4142,
+      "step": 480
+    },
+    {
+      "epoch": 0.10190288031610689,
+      "grad_norm": 0.9010934829711914,
+      "learning_rate": 2.655185216791625e-07,
+      "loss": 0.3869,
+      "step": 490
+    },
+    {
+      "epoch": 0.10398253093480295,
+      "grad_norm": 1.2820464372634888,
+      "learning_rate": 0.0,
+      "loss": 0.4153,
+      "step": 500
+    },
+    {
+      "epoch": 0.10398253093480295,
+      "eval_loss": 0.3960544764995575,
+      "eval_runtime": 80.8174,
+      "eval_samples_per_second": 6.273,
+      "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": 6.027457627737293e+16,
+  "total_flos": 6.694211790097613e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null