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:de10e3925aaaed122db82b599b45559d3a0a9ad695267bb9183241e5bc4454cd
+oid sha256:06242f238646121954c9fa4de7b9e057b2c6b6eb0e07d17440c0d5c11053fcdd
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c10c4a705aa11da2f048176528262701b632d35878cf69fd1ef1fd87271ab8b3
+oid sha256:e091db8b3dd4c73ef0cedd28dbfcf398f19f051b0f453f53d720d5417eb7037d
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66d4796167098b16cf920f3d72d4f9179afede6d2fe03cce48a0f87de28b7ee4
+oid sha256:a68a2c55c511c093af16aefb67eca81a483d7c2c144a45c1804469b0ec2c91e3
 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": 2.834376811981201,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.009992505620784412,
+  "best_metric": 2.5079739093780518,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.019985011241568824,
   "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": 2.592,
       "eval_steps_per_second": 1.296,
       "step": 10
+    },
+    {
+      "epoch": 0.011991006744941295,
+      "grad_norm": 4.357197284698486,
+      "learning_rate": 0.000163742398974869,
+      "loss": 9.6877,
+      "step": 12
+    },
+    {
+      "epoch": 0.014988758431176618,
+      "grad_norm": 5.791210174560547,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 10.6052,
+      "step": 15
+    },
+    {
+      "epoch": 0.014988758431176618,
+      "eval_loss": 2.6564278602600098,
+      "eval_runtime": 162.1433,
+      "eval_samples_per_second": 2.603,
+      "eval_steps_per_second": 1.301,
+      "step": 15
+    },
+    {
+      "epoch": 0.017986510117411942,
+      "grad_norm": 7.677189350128174,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 10.0151,
+      "step": 18
+    },
+    {
+      "epoch": 0.019985011241568824,
+      "eval_loss": 2.5079739093780518,
+      "eval_runtime": 162.1387,
+      "eval_samples_per_second": 2.603,
+      "eval_steps_per_second": 1.301,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6347829962342400.0,
+  "total_flos": 1.26956599246848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null