Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27c9d494e0c1f59af7fee84092f59f3a5768b26237bfbc131d5f8875ba8d0915
+oid sha256:49f9f26440169027c0aa1d14509a44136b15c9189414fb8eedf0370afe45dca8
 size 406863720

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd087d8b2cbbc0fc84f6b752aa272194f9275a7a8700b28a2eec1d5a64727ab3
+oid sha256:ee5698688aef6bf49781e0a287f223f0dc50fb63f79f154a9049a329dc55c4e7
 size 207013892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82fce3ff3e5de9ad840eeea42923439859da84e119d1587d914a1485e5f8a9b9
+oid sha256:3c265974053480d01182c17cad4b5b6834a8770f52deb2c91afe3194f03b7928
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2f43eae3d8b1b29d23e364f4f65c01c337c44f0992ce19d5a6cf14f65803d2b
+oid sha256:0873218b672c06f65bcbdbef35d38ce732851774107c53582718a1316dbb1e40
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.32846999168396,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.01801477211313277,
+  "best_metric": 2.2165262699127197,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.03602954422626554,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 18.402,
       "eval_steps_per_second": 4.612,
       "step": 50
+    },
+    {
+      "epoch": 0.021617726535759323,
+      "grad_norm": 0.6720779538154602,
+      "learning_rate": 0.00020075518705111234,
+      "loss": 2.4082,
+      "step": 60
+    },
+    {
+      "epoch": 0.025220680958385876,
+      "grad_norm": 0.6647239327430725,
+      "learning_rate": 0.00020002194090852784,
+      "loss": 2.2645,
+      "step": 70
+    },
+    {
+      "epoch": 0.02882363538101243,
+      "grad_norm": 0.6222731471061707,
+      "learning_rate": 0.00019880383387374748,
+      "loss": 2.2457,
+      "step": 80
+    },
+    {
+      "epoch": 0.03242658980363899,
+      "grad_norm": 0.6799861192703247,
+      "learning_rate": 0.00019710680044180106,
+      "loss": 2.0081,
+      "step": 90
+    },
+    {
+      "epoch": 0.03602954422626554,
+      "grad_norm": 1.6060737371444702,
+      "learning_rate": 0.0001949391083889838,
+      "loss": 2.1461,
+      "step": 100
+    },
+    {
+      "epoch": 0.03602954422626554,
+      "eval_loss": 2.2165262699127197,
+      "eval_runtime": 63.3419,
+      "eval_samples_per_second": 18.455,
+      "eval_steps_per_second": 4.626,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6861640048312320.0,
+  "total_flos": 1.38916639014912e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null