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:e1a5304ca49fa77defb02a1c0415bc5da40292be189d48846da02d8189a8e695
+oid sha256:4b3674391edda5d280b168d6a18101f52936d24b034b5c830d733d2d4bef61bd
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5abc96cfadce876d4b1cdc59aced4e3585cf6697e15d67988397ffd9c097fc32
+oid sha256:4a06897fad877e55f749cb8adbc67a121c15743f8beeeb37ace8757e3de77166
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7df0ca3ad0a10b20e487b3c58626ef76f8524f36a4e67e15566b1577ef91441e
+oid sha256:87d71ed0147d49c979a1b06e57cb03086cfcd715853811657d1f40156acf29bf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23d0c4fcd75282d05c3ecf542229a263cdfdea966c314071913c5dc6faf85a25
+oid sha256:ddd16399db35d8a29f2ca6eadbdcd4462c58bf5886d5df4eb74f5a14652bb30c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2511337995529175,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.6211180124223602,
+  "best_metric": 1.2475330829620361,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.6901311249137336,
   "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": 16.058,
       "eval_steps_per_second": 4.054,
       "step": 450
+    },
+    {
+      "epoch": 0.6349206349206349,
+      "grad_norm": 11.425106048583984,
+      "learning_rate": 3.990045318353154e-06,
+      "loss": 2.3746,
+      "step": 460
+    },
+    {
+      "epoch": 0.6487232574189096,
+      "grad_norm": 10.9284086227417,
+      "learning_rate": 2.250797124418014e-06,
+      "loss": 2.2794,
+      "step": 470
+    },
+    {
+      "epoch": 0.6625258799171843,
+      "grad_norm": 8.530669212341309,
+      "learning_rate": 1.0023889196182526e-06,
+      "loss": 1.8834,
+      "step": 480
+    },
+    {
+      "epoch": 0.6763285024154589,
+      "grad_norm": 16.04986000061035,
+      "learning_rate": 2.5090282323810766e-07,
+      "loss": 2.6432,
+      "step": 490
+    },
+    {
+      "epoch": 0.6901311249137336,
+      "grad_norm": 21.996217727661133,
+      "learning_rate": 0.0,
+      "loss": 2.5017,
+      "step": 500
+    },
+    {
+      "epoch": 0.6901311249137336,
+      "eval_loss": 1.2475330829620361,
+      "eval_runtime": 18.9299,
+      "eval_samples_per_second": 16.112,
+      "eval_steps_per_second": 4.068,
+      "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": 8.04936833040384e+16,
+  "total_flos": 8.9437425893376e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null