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:ab9465a98f2fe6998f861dd5603ce299f221337ffeaac1030a638718911f9d3d
+oid sha256:4b3d0e8f7f4eb019c24ae60c1090b731ba0fea6b2a2da033bb7ce8d82c604a4e
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ace6fd7a81cbccc2d6c499464656208050f0f4c8de34268605b70ff3b22da307
+oid sha256:ca604f3e279bd74b1dbf4563383698a5b8f0aefd19080c5c4cf0875907cbf848
 size 71878996

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3226d686d6ec89d4341834cfee429c8902273be180494be5fb597e6b1d18a5f9
+oid sha256:160d11514f6437ef8fcf50bf7e24fdd242c3f667acd1171fc3baf04ffc809252
 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": 2.72652006149292,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.014038371548900327,
+  "best_metric": 2.7256171703338623,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.015598190609889253,
   "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": 42.069,
       "eval_steps_per_second": 10.52,
       "step": 450
+    },
+    {
+      "epoch": 0.014350335361098112,
+      "grad_norm": 1.0083255767822266,
+      "learning_rate": 4.22247514272324e-06,
+      "loss": 2.7585,
+      "step": 460
+    },
+    {
+      "epoch": 0.014662299173295897,
+      "grad_norm": 0.8869374394416809,
+      "learning_rate": 2.38191152001518e-06,
+      "loss": 2.7606,
+      "step": 470
+    },
+    {
+      "epoch": 0.014974262985493684,
+      "grad_norm": 0.9429048299789429,
+      "learning_rate": 1.0607805071688306e-06,
+      "loss": 2.6848,
+      "step": 480
+    },
+    {
+      "epoch": 0.015286226797691468,
+      "grad_norm": 1.2137974500656128,
+      "learning_rate": 2.655185216791625e-07,
+      "loss": 2.6912,
+      "step": 490
+    },
+    {
+      "epoch": 0.015598190609889253,
+      "grad_norm": 2.361453056335449,
+      "learning_rate": 0.0,
+      "loss": 2.7743,
+      "step": 500
+    },
+    {
+      "epoch": 0.015598190609889253,
+      "eval_loss": 2.7256171703338623,
+      "eval_runtime": 321.5524,
+      "eval_samples_per_second": 41.974,
+      "eval_steps_per_second": 10.496,
+      "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": 6767252429340672.0,
+  "total_flos": 7530440069480448.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null