Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24f98c46f8054eec0d945c3a9447a15c89cbde2384fd990da64fa4227f255908
+oid sha256:b3ea623d582d7f851440887b474cf77f9cfd3cfd53d43c627ffc03ab670482cc
 size 1001465824

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ea9ee098fab23ffbcede66b7f90f1eac428c954ccdb58a79bf70437b1de24c5
+oid sha256:eb5ec94c240f19664dceacd79e68295d110a945379fa1796999f7ffeee9603ef
 size 509177556

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cc463bc6a591b06ca2cb3f06961a217df71f23c357566ef37a962e37c0b1714
+oid sha256:e7a05634e3e275423c3e9d79988215306eb482758bcb550a37efcfece02000d7
 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": 0.4052506685256958,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.10792660990526443,
+  "best_metric": 0.401653915643692,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.1199184554502938,
   "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": 10.026,
       "eval_steps_per_second": 2.507,
       "step": 450
+    },
+    {
+      "epoch": 0.1103249790142703,
+      "grad_norm": 0.9613426923751831,
+      "learning_rate": 3.990045318353154e-06,
+      "loss": 0.4621,
+      "step": 460
+    },
+    {
+      "epoch": 0.11272334812327617,
+      "grad_norm": 1.016109585762024,
+      "learning_rate": 2.250797124418014e-06,
+      "loss": 0.4734,
+      "step": 470
+    },
+    {
+      "epoch": 0.11512171723228205,
+      "grad_norm": 1.2553995847702026,
+      "learning_rate": 1.0023889196182526e-06,
+      "loss": 0.3936,
+      "step": 480
+    },
+    {
+      "epoch": 0.11752008634128792,
+      "grad_norm": 2.9403693675994873,
+      "learning_rate": 2.5090282323810766e-07,
+      "loss": 1.2895,
+      "step": 490
+    },
+    {
+      "epoch": 0.1199184554502938,
+      "grad_norm": 1.9742144346237183,
+      "learning_rate": 0.0,
+      "loss": 0.9806,
+      "step": 500
+    },
+    {
+      "epoch": 0.1199184554502938,
+      "eval_loss": 0.401653915643692,
+      "eval_runtime": 175.283,
+      "eval_samples_per_second": 10.018,
+      "eval_steps_per_second": 2.505,
+      "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": 1.44902656622592e+17,
+  "total_flos": 1.6100295180288e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null