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:bdb0f1ff827ccc7f2492734ea34ccce68ef3661168251f78a561a65227f17951
+oid sha256:4048df42b0edbd9da090c8c014a7d4b251e358d7a9d32eb021f26dcc9ff5c37f
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6eba9a2958906c9a0ef8450189316d6f8f090310143e8d57d793a21d50e56f2
+oid sha256:777919d2370e3423725dcf405283182c643b494622ae665c493c9d3b6622dc7c
 size 25279290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7d873e5981a74ca193df96e36ccebe68055d4a9941f3ec8ce17e5615941b9a7
+oid sha256:9a9ab7db431e6cea4f6f67f645378c70ef004171a9209f8ce85124ff5172a3ca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:b7af249df5fe11a9896f83a1f972a51ac4c516f61ca7fde0473cca60d389d7ec
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.8233513832092285,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00036778565452054543,
+  "best_metric": 3.755293130874634,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0007355713090410909,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 15.443,
       "eval_steps_per_second": 7.722,
       "step": 10
+    },
+    {
+      "epoch": 0.0004045642199726,
+      "grad_norm": 2.8351001739501953,
+      "learning_rate": 9.890738003669029e-05,
+      "loss": 16.4796,
+      "step": 11
+    },
+    {
+      "epoch": 0.0004413427854246545,
+      "grad_norm": 3.332181453704834,
+      "learning_rate": 9.567727288213005e-05,
+      "loss": 15.6604,
+      "step": 12
+    },
+    {
+      "epoch": 0.00047812135087670906,
+      "grad_norm": 4.804444313049316,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 15.2079,
+      "step": 13
+    },
+    {
+      "epoch": 0.0005148999163287636,
+      "grad_norm": 2.3618407249450684,
+      "learning_rate": 8.345653031794292e-05,
+      "loss": 14.6311,
+      "step": 14
+    },
+    {
+      "epoch": 0.0005516784817808181,
+      "grad_norm": 3.831026792526245,
+      "learning_rate": 7.500000000000001e-05,
+      "loss": 15.2172,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005516784817808181,
+      "eval_loss": 3.776841878890991,
+      "eval_runtime": 743.7441,
+      "eval_samples_per_second": 15.394,
+      "eval_steps_per_second": 7.698,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005884570472328727,
+      "grad_norm": 3.0379860401153564,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 15.2776,
+      "step": 16
+    },
+    {
+      "epoch": 0.0006252356126849272,
+      "grad_norm": 3.142021417617798,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 14.6165,
+      "step": 17
+    },
+    {
+      "epoch": 0.0006620141781369818,
+      "grad_norm": 3.2710373401641846,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 16.1777,
+      "step": 18
+    },
+    {
+      "epoch": 0.0006987927435890363,
+      "grad_norm": 4.714978218078613,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 15.0562,
+      "step": 19
+    },
+    {
+      "epoch": 0.0007355713090410909,
+      "grad_norm": 3.9726500511169434,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 15.9209,
+      "step": 20
+    },
+    {
+      "epoch": 0.0007355713090410909,
+      "eval_loss": 3.755293130874634,
+      "eval_runtime": 739.3398,
+      "eval_samples_per_second": 15.485,
+      "eval_steps_per_second": 7.743,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 150139305984000.0,
+  "total_flos": 300278611968000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null