Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:768e39ae96a1f88b2a0266572991ca94de481c55236e6a22ee968e14639ea95b
+oid sha256:d064b46c77d9b972e330ec97b486e4b890a5829357e61aadc2092468c13140aa
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19d5d5bc7e02bf77e4e181830a9069bc0d8a71c266e6489bb8e1ca3223f809e3
+oid sha256:aad7a8928adf015778815bc52874ffc224c0e64b5a4975553cae50fcf6848fc7
 size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:662d74ebc635d419c4f1e4e0aa3d1f12f95487bd7370e0eba631af5e5b92ae56
+oid sha256:916730fff46a0a6855d5adeb0fc0c58f288d066653384445db6a001223fa7cee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c579f5f648f371ddcf6d84448bace40e1d46168d2f7b5fae9b6105a9c79d201
+oid sha256:2c9718e38efb2d48aaa61791c4fc8b4a7f9cfd08f355dda43ae7de9f2cb195d8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.16511203348636627,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.1913672124176058,
+  "best_metric": 0.1643463671207428,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.212630236019562,
   "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": 13.695,
       "eval_steps_per_second": 3.431,
       "step": 450
+    },
+    {
+      "epoch": 0.19561981713799703,
+      "grad_norm": 0.3398416042327881,
+      "learning_rate": 4.125629382569038e-06,
+      "loss": 0.1377,
+      "step": 460
+    },
+    {
+      "epoch": 0.19987242185838827,
+      "grad_norm": 0.6524055004119873,
+      "learning_rate": 2.327280521849694e-06,
+      "loss": 0.1348,
+      "step": 470
+    },
+    {
+      "epoch": 0.2041250265787795,
+      "grad_norm": 0.5883779525756836,
+      "learning_rate": 1.0364506790227565e-06,
+      "loss": 0.1782,
+      "step": 480
+    },
+    {
+      "epoch": 0.20837763129917075,
+      "grad_norm": 0.6829372644424438,
+      "learning_rate": 2.5942864732872295e-07,
+      "loss": 0.181,
+      "step": 490
+    },
+    {
+      "epoch": 0.212630236019562,
+      "grad_norm": 1.7673338651657104,
+      "learning_rate": 0.0,
+      "loss": 0.2541,
+      "step": 500
+    },
+    {
+      "epoch": 0.212630236019562,
+      "eval_loss": 0.1643463671207428,
+      "eval_runtime": 72.4913,
+      "eval_samples_per_second": 13.657,
+      "eval_steps_per_second": 3.421,
+      "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": 1.0116469187464397e+17,
+  "total_flos": 1.1238426161656627e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null