Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b529a5fb82252572705c3df411b468d63d5dd950cd8332aae8f13a6631cda05
+oid sha256:6b0aee6ea50b7b3b5bf9852112f6b0f8b3058d6f62cd10ad2677cb54d7a6ad79
 size 10636096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:244ceef474e72f91b7f14bc7925f469578f9deb0b86d73f285607d899e672e48
+oid sha256:fa8a7da091a3e0ee074735dd08ea738d4776b51aa6e843cc0ee560e4f02d9b1c
 size 5561210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01bbb0c02f10dd6427423731b88eae10bac23b6b06d18622e34c839014e063a8
+oid sha256:a35c79150762672b52a2bf3cb58745a9ff6f45141e794981596d9b4ed5f5a921
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c0cbab52df187d8502a1b66e46607ea8ce4ac36a84891208388bc9974f53e8
+oid sha256:2e87d47519e32af310d5ce258e0454d331221391a1b9ee9143859120658f7a9a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.05978865921497345,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.07793219898688142,
+  "best_metric": 0.05939556285738945,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.08659133220764602,
   "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": 17.784,
       "eval_steps_per_second": 8.892,
       "step": 450
+    },
+    {
+      "epoch": 0.07966402563103434,
+      "grad_norm": 0.6104562878608704,
+      "learning_rate": 9.684576015420278e-07,
+      "loss": 0.092,
+      "step": 460
+    },
+    {
+      "epoch": 0.08139585227518725,
+      "grad_norm": 0.5883759260177612,
+      "learning_rate": 5.463099816548579e-07,
+      "loss": 0.1223,
+      "step": 470
+    },
+    {
+      "epoch": 0.08312767891934017,
+      "grad_norm": 0.410600870847702,
+      "learning_rate": 2.4329828146074095e-07,
+      "loss": 0.1423,
+      "step": 480
+    },
+    {
+      "epoch": 0.0848595055634931,
+      "grad_norm": 0.8246781229972839,
+      "learning_rate": 6.089874350439506e-08,
+      "loss": 0.198,
+      "step": 490
+    },
+    {
+      "epoch": 0.08659133220764602,
+      "grad_norm": 0.7569292187690735,
+      "learning_rate": 0.0,
+      "loss": 0.1517,
+      "step": 500
+    },
+    {
+      "epoch": 0.08659133220764602,
+      "eval_loss": 0.05939556285738945,
+      "eval_runtime": 84.1062,
+      "eval_samples_per_second": 28.916,
+      "eval_steps_per_second": 14.458,
+      "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": 1244985730007040.0,
+  "total_flos": 1383975915356160.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null