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:bce98b48629c60c6b60f1ed0df64f3c8a3e1e672030de247564403bae5baa738
+oid sha256:462404eeee9948994b2af935f781a9133aadb9fb54138bf96ea96e5a9e33cdb8
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15c2f3f1ceb13add92d96570c136e0d43f930cb04806b8aae056f79834c3d6bd
+oid sha256:71058b88ca8479af284c1947ab6aa57576f40c6094dad987d5d13db71a1ddc63
 size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d81fd208bdc2fb241aa669b00418a37ab56d4805a35a3cff82c1eab50e268837
+oid sha256:eec7cfeb3f09f8ad87b650905721ae90d703b1c28ce9ccc59dc079a2427b73ed
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea278ffcc402f8731d694a21dbc5a96671a02299dc57c40b61a02431bc8aed26
+oid sha256:200a199971193d5b4ec602093f689606117a65db31ca244b618fc0f0cd969846
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6477181315422058,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.01646843549862763,
+  "best_metric": 0.6367893815040588,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.018298261665141813,
   "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": 17.579,
       "eval_steps_per_second": 4.395,
       "step": 450
+    },
+    {
+      "epoch": 0.016834400731930467,
+      "grad_norm": 0.7986826300621033,
+      "learning_rate": 4.2031059906924e-06,
+      "loss": 0.5613,
+      "step": 460
+    },
+    {
+      "epoch": 0.0172003659652333,
+      "grad_norm": 0.9289596080780029,
+      "learning_rate": 2.3709853203820825e-06,
+      "loss": 0.6961,
+      "step": 470
+    },
+    {
+      "epoch": 0.01756633119853614,
+      "grad_norm": 0.9395463466644287,
+      "learning_rate": 1.0559145415396157e-06,
+      "loss": 0.6394,
+      "step": 480
+    },
+    {
+      "epoch": 0.017932296431838975,
+      "grad_norm": 0.949378252029419,
+      "learning_rate": 2.643005468090745e-07,
+      "loss": 0.6338,
+      "step": 490
+    },
+    {
+      "epoch": 0.018298261665141813,
+      "grad_norm": 1.6931450366973877,
+      "learning_rate": 0.0,
+      "loss": 0.6262,
+      "step": 500
+    },
+    {
+      "epoch": 0.018298261665141813,
+      "eval_loss": 0.6367893815040588,
+      "eval_runtime": 654.042,
+      "eval_samples_per_second": 17.592,
+      "eval_steps_per_second": 4.399,
+      "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": 7.54897863573504e+16,
+  "total_flos": 8.3877540397056e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null