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:e3e1a407aab40ba08fa8a8ea3c13438e57bf3a44a514d6c73dbfa246e04ebfd8
+oid sha256:3e6ea7b241b4f9f9443226c77ec0ddc3d195b4ab92ca161006d24bba4b25c9f2
 size 2373352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f0175de6b2c3dc232ca2fe7227b1f09c1096cfbe9b7cc08e81ffa15ab80eb27
+oid sha256:6ebf81ce2f30ceaa0816c5f504298f977d88affe8df2b5c42500440fd9be33ea
 size 4830970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c24338e53d3592bc74837c8eccbd148ebcaec1a0a77f92bfa34aa4a05ffaa7c2
+oid sha256:31da54e1659981157850fdddbbf2938c01bd3de00de502ee4a6a6d8bde4938a5
 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": 11.483320236206055,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.017502236396872935,
+  "best_metric": 11.483193397521973,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.019446929329858816,
   "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": 72.57,
       "eval_steps_per_second": 18.146,
       "step": 450
+    },
+    {
+      "epoch": 0.01789117498347011,
+      "grad_norm": 0.17763635516166687,
+      "learning_rate": 4.144998534599878e-06,
+      "loss": 11.4219,
+      "step": 460
+    },
+    {
+      "epoch": 0.018280113570067286,
+      "grad_norm": 0.187831848859787,
+      "learning_rate": 2.3382067214827915e-06,
+      "loss": 11.4227,
+      "step": 470
+    },
+    {
+      "epoch": 0.01866905215666446,
+      "grad_norm": 0.4871636629104614,
+      "learning_rate": 1.0413166446519713e-06,
+      "loss": 11.445,
+      "step": 480
+    },
+    {
+      "epoch": 0.01905799074326164,
+      "grad_norm": 0.4641425609588623,
+      "learning_rate": 2.6064662219881083e-07,
+      "loss": 11.5431,
+      "step": 490
+    },
+    {
+      "epoch": 0.019446929329858816,
+      "grad_norm": 1.2540117502212524,
+      "learning_rate": 0.0,
+      "loss": 11.5946,
+      "step": 500
+    },
+    {
+      "epoch": 0.019446929329858816,
+      "eval_loss": 11.483193397521973,
+      "eval_runtime": 149.1427,
+      "eval_samples_per_second": 72.588,
+      "eval_steps_per_second": 18.15,
+      "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": 61975756800000.0,
+  "total_flos": 68861952000000.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null