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:fe0408b405c80a6b4c1bc7c8e96ace0db94219772039caab7faf82e69cdd436f
+oid sha256:58d861a4785445a4f639486dc4428fdab90ad4745f0b1c61a036a71e85cb3218
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:199b7f4e59067a6652ae05df0d11ef6a77a14252722044d003dca80bcadbdd5a
+oid sha256:89e2231e4be6c5fcaeefbb57c0798ed41e4935b3d747475c3f794a46d3d8720e
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97ead28242dd097af80112cb3bd8d751944021cbf255fca1535e0f2a22344d9
+oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.76247787475586,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.009507962918944617,
+  "best_metric": 11.761784553527832,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.019015925837889233,
   "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": 45.172,
       "eval_steps_per_second": 22.637,
       "step": 10
+    },
+    {
+      "epoch": 0.011409555502733539,
+      "grad_norm": 0.04291345179080963,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 11.761,
+      "step": 12
+    },
+    {
+      "epoch": 0.014261944378416925,
+      "grad_norm": 0.0457707941532135,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 11.762,
+      "step": 15
+    },
+    {
+      "epoch": 0.014261944378416925,
+      "eval_loss": 11.762060165405273,
+      "eval_runtime": 9.392,
+      "eval_samples_per_second": 47.168,
+      "eval_steps_per_second": 23.637,
+      "step": 15
+    },
+    {
+      "epoch": 0.01711433325410031,
+      "grad_norm": 0.04285963624715805,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 11.7608,
+      "step": 18
+    },
+    {
+      "epoch": 0.019015925837889233,
+      "eval_loss": 11.761784553527832,
+      "eval_runtime": 9.8536,
+      "eval_samples_per_second": 44.958,
+      "eval_steps_per_second": 22.53,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2037000437760.0,
+  "total_flos": 4074000875520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null