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:c9319c79ef241fd05872375b9bb2a7a66244c792f3d481140c6b356549755e43
+oid sha256:e08d888727826021717b7329a74ea9e3bd7713da955a0e6fa135e8dd5403c969
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af42f3b9f3c4b8bc5336b00e86196f3c23dba0a3e3fe63a1d4044a926b805718
+oid sha256:dccad4434218b2f75957bbc90c9f9d97062a4ca76ad09aa30a50899cdc5df82e
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7ac2a2ddb2d8017926c10dd0a7e8e37172da712804d36f68e0c197f38d7cb34
+oid sha256:c0be2e94e934e35a7c4a7f3a8a7cda95df895fbedb953b8f3cf808dd94f80323
 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": 0.8942686319351196,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0026319252533228057,
+  "best_metric": 0.8367408514022827,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.005263850506645611,
   "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": 6.965,
       "eval_steps_per_second": 1.741,
       "step": 10
+    },
+    {
+      "epoch": 0.0031583103039873666,
+      "grad_norm": 1.8942865133285522,
+      "learning_rate": 0.000163742398974869,
+      "loss": 3.2126,
+      "step": 12
+    },
+    {
+      "epoch": 0.0039478878799842085,
+      "grad_norm": 2.632387638092041,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.1678,
+      "step": 15
+    },
+    {
+      "epoch": 0.0039478878799842085,
+      "eval_loss": 0.8524987697601318,
+      "eval_runtime": 459.1579,
+      "eval_samples_per_second": 6.969,
+      "eval_steps_per_second": 1.742,
+      "step": 15
+    },
+    {
+      "epoch": 0.00473746545598105,
+      "grad_norm": 1.9677852392196655,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 3.2285,
+      "step": 18
+    },
+    {
+      "epoch": 0.005263850506645611,
+      "eval_loss": 0.8367408514022827,
+      "eval_runtime": 461.6482,
+      "eval_samples_per_second": 6.932,
+      "eval_steps_per_second": 1.733,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7558642110824448.0,
+  "total_flos": 1.4589937097637888e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null