Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dbc157b16d127095d3b041cb9e440b7bc7a5f5552212fba2f9bd935f2ba3b25
+oid sha256:13e89a69b413fa4715aa6dc3e7a022efb3638fd17ad3e94dc4a9bcba6e87939e
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ddaae87e12380274c4f5726bafce50f74922967853e95e197744f80c8f97d2b
+oid sha256:5bf1d4ac38035eea9b5198269cd962e66f0fdb4a03be098925142f57a7eedf88
 size 147360212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c38003ef86abbb071d125f7ff66342a2ea51deb2b5edf0d2a212cc88e85cc744
+oid sha256:2c5b7b8cedc3ef093635f1a60d8a6212ed24442565a3e3618b3eb39b9178a0d9
 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": 1.5629593133926392,
-  "best_model_checkpoint": "miner_id_24/checkpoint-450",
-  "epoch": 0.008813765142538168,
+  "best_metric": 1.5615293979644775,
+  "best_model_checkpoint": "miner_id_24/checkpoint-500",
+  "epoch": 0.009793072380597964,
   "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": 26.565,
       "eval_steps_per_second": 6.642,
       "step": 450
+    },
+    {
+      "epoch": 0.009009626590150128,
+      "grad_norm": 0.4325626492500305,
+      "learning_rate": 3.990045318353154e-06,
+      "loss": 1.6155,
+      "step": 460
+    },
+    {
+      "epoch": 0.009205488037762086,
+      "grad_norm": 0.4722021222114563,
+      "learning_rate": 2.250797124418014e-06,
+      "loss": 1.5226,
+      "step": 470
+    },
+    {
+      "epoch": 0.009401349485374046,
+      "grad_norm": 0.49364137649536133,
+      "learning_rate": 1.0023889196182526e-06,
+      "loss": 1.5093,
+      "step": 480
+    },
+    {
+      "epoch": 0.009597210932986006,
+      "grad_norm": 0.5476292967796326,
+      "learning_rate": 2.5090282323810766e-07,
+      "loss": 1.5315,
+      "step": 490
+    },
+    {
+      "epoch": 0.009793072380597964,
+      "grad_norm": 0.8033114075660706,
+      "learning_rate": 0.0,
+      "loss": 1.574,
+      "step": 500
+    },
+    {
+      "epoch": 0.009793072380597964,
+      "eval_loss": 1.5615293979644775,
+      "eval_runtime": 809.085,
+      "eval_samples_per_second": 26.571,
+      "eval_steps_per_second": 6.643,
+      "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": 2.951250143556403e+16,
+  "total_flos": 3.2862904541773824e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null