Training in progress, step 550, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1169929913bb5c932000d9767b768f52232cc25b87794b8470c01fa18b6febe3
+oid sha256:f6af08d76a9fceca32bff48f799195d010dca79f33f8c81d319400ad2402ccb7
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec6eb1e6db84c334570c122af91c407546f0a6028677bbf77e984e91c6f2d2a0
+oid sha256:9ea6c15f3b7a29a14d859e550c46d3a37ab660f7fac91aa2b67f82f5dfb3e735
 size 85723732

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46bad0fc23adfd09dbc19f3f7be3435ddfe15414ebed26616a6aecc380fbdf3f
+oid sha256:24234b9f02099e93a544d84dde2a4254f3926f51e08f716f06999d6cb929bbeb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b782a524e5b57eb023365370accae538ac5e68454bafa53a6dd8b2c51cead56
+oid sha256:6bb9c0d62d6b3cf0976c16f73e9bd814b298ebffa1786831bc2a68d8e48809b9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8650081157684326,
-  "best_model_checkpoint": "miner_id_24/checkpoint-500",
-  "epoch": 0.13652809065465218,
+  "best_metric": 1.862091302871704,
+  "best_model_checkpoint": "miner_id_24/checkpoint-550",
+  "epoch": 0.15018089972011742,
   "eval_steps": 50,
-  "global_step": 500,
+  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -445,6 +445,49 @@
       "eval_samples_per_second": 25.164,
       "eval_steps_per_second": 6.291,
       "step": 500
+    },
+    {
+      "epoch": 0.13925865246774524,
+      "grad_norm": 10.133707046508789,
+      "learning_rate": 1.1264792494342857e-05,
+      "loss": 7.0925,
+      "step": 510
+    },
+    {
+      "epoch": 0.14198921428083827,
+      "grad_norm": 10.4485445022583,
+      "learning_rate": 8.936522714508678e-06,
+      "loss": 7.8088,
+      "step": 520
+    },
+    {
+      "epoch": 0.14471977609393133,
+      "grad_norm": 13.265645980834961,
+      "learning_rate": 6.866382254766157e-06,
+      "loss": 7.6878,
+      "step": 530
+    },
+    {
+      "epoch": 0.14745033790702436,
+      "grad_norm": 12.639242172241211,
+      "learning_rate": 5.060239153161872e-06,
+      "loss": 7.4659,
+      "step": 540
+    },
+    {
+      "epoch": 0.15018089972011742,
+      "grad_norm": 26.739566802978516,
+      "learning_rate": 3.5232131185484076e-06,
+      "loss": 7.7885,
+      "step": 550
+    },
+    {
+      "epoch": 0.15018089972011742,
+      "eval_loss": 1.862091302871704,
+      "eval_runtime": 245.1426,
+      "eval_samples_per_second": 25.161,
+      "eval_steps_per_second": 6.29,
+      "step": 550
     }
   ],
   "logging_steps": 10,
@@ -473,7 +516,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.51564749340672e+17,
+  "total_flos": 3.867212242747392e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null