Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:535ec51b7f39e2891c062187f8451b548cc2f087c749aa6bb1c4ddf290410bda
+oid sha256:74f183633dad000a0e47c32abe84d5827c40702ccecfff49901512389350c58c
 size 56662952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da8ebe21f9cf12927dd2b67c7f7c40bcd3d5df55056ba1c31f45c9ff7153724c
+oid sha256:be51221098653bc48f6099edc2dc5f0896063d279182a03e8a63c443afa82186
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:821b7b9dd9b9adeb3b6e0fc7064d604faabda3faff14c6313f8149673e918289
+oid sha256:82b93107c2130590d832409ff5536612f9a10a908a196ef6b6c07e81941a0ae5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.5645692348480225,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00014421118285617458,
+  "best_metric": 2.385772705078125,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00028842236571234917,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 28.94,
       "eval_steps_per_second": 14.471,
       "step": 10
+    },
+    {
+      "epoch": 0.0001730534194274095,
+      "grad_norm": 6.821072578430176,
+      "learning_rate": 0.000163742398974869,
+      "loss": 10.1128,
+      "step": 12
+    },
+    {
+      "epoch": 0.00021631677428426188,
+      "grad_norm": 7.551280498504639,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.2312,
+      "step": 15
+    },
+    {
+      "epoch": 0.00021631677428426188,
+      "eval_loss": 2.4281718730926514,
+      "eval_runtime": 1010.8266,
+      "eval_samples_per_second": 28.884,
+      "eval_steps_per_second": 14.443,
+      "step": 15
+    },
+    {
+      "epoch": 0.00025958012914111423,
+      "grad_norm": 8.599263191223145,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 10.306,
+      "step": 18
+    },
+    {
+      "epoch": 0.00028842236571234917,
+      "eval_loss": 2.385772705078125,
+      "eval_runtime": 1019.4012,
+      "eval_samples_per_second": 28.641,
+      "eval_steps_per_second": 14.321,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 601010208768000.0,
+  "total_flos": 1202020417536000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null