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:f3d086e190bad1973305f2b5d7df993d761ed72543bb2d83717e6aeaa84693b2
+oid sha256:09505c25550333885133c94c3605c650daa21e690743c88e0015fccae6c91bd2
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a05e3083482400402257f6db4ed479a8d51899cdd85370b479269a4835977f6d
+oid sha256:c4d2e7c38161a2e1c7f2660cd991626140cb8a128622dacf42fb61706c0fe7a9
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:534517e56dab0276725bf822ba3788b434f603c7b78bf640c8cfb5648c866e66
+oid sha256:efbaca5a41d6eb7ddf5ffcdaadbefc90141ba0339ef8e68e464b674133adc821
 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": 10.380498886108398,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0002823004665015209,
+  "best_metric": 10.379438400268555,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0005646009330030418,
   "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": 201.467,
       "eval_steps_per_second": 100.74,
       "step": 10
+    },
+    {
+      "epoch": 0.0003387605598018251,
+      "grad_norm": 0.03111659176647663,
+      "learning_rate": 0.000163742398974869,
+      "loss": 10.3798,
+      "step": 12
+    },
+    {
+      "epoch": 0.00042345069975228137,
+      "grad_norm": 0.03311929851770401,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.3795,
+      "step": 15
+    },
+    {
+      "epoch": 0.00042345069975228137,
+      "eval_loss": 10.37988567352295,
+      "eval_runtime": 74.304,
+      "eval_samples_per_second": 200.729,
+      "eval_steps_per_second": 100.371,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005081408397027376,
+      "grad_norm": 0.03382084518671036,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 10.3808,
+      "step": 18
+    },
+    {
+      "epoch": 0.0005646009330030418,
+      "eval_loss": 10.379438400268555,
+      "eval_runtime": 74.7732,
+      "eval_samples_per_second": 199.47,
+      "eval_steps_per_second": 99.742,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 268050038784.0,
+  "total_flos": 529562271744.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null