Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4892c6838cd6450b229f9f1455dd702457eaf335237fad7b54148e05bdb34d7c
+oid sha256:075dab25755f35a388f38d5ec254131cd38b4dbe9faa3f08c45fd634de714013
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f77c07f6629135b4fc133c006b2f2e58dbe69f8298ad9bc31e6b47bfca19853d
+oid sha256:a16241656ee6d887dafa8f05435f9233e8af1574f90f009525fc21aaead3ac02
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c29493907822832b1da2d0bb8bfe551337f924596f34bef9288a6f81648b1988
+oid sha256:a235bd5b22847df5efc576b2d53304138bedaafdab52b3f19ffc508dcd8204f7
 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": 1.5826470851898193,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.01839249586168843,
+  "best_metric": 1.49298894405365,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.03678499172337686,
   "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": 17.519,
       "eval_steps_per_second": 4.391,
       "step": 50
+    },
+    {
+      "epoch": 0.022070995034026118,
+      "grad_norm": 0.9022707939147949,
+      "learning_rate": 0.00020075518705111234,
+      "loss": 1.6254,
+      "step": 60
+    },
+    {
+      "epoch": 0.025749494206363802,
+      "grad_norm": 0.8804805874824524,
+      "learning_rate": 0.00020002194090852784,
+      "loss": 1.5379,
+      "step": 70
+    },
+    {
+      "epoch": 0.02942799337870149,
+      "grad_norm": 0.9261283874511719,
+      "learning_rate": 0.00019880383387374748,
+      "loss": 1.4729,
+      "step": 80
+    },
+    {
+      "epoch": 0.033106492551039174,
+      "grad_norm": 0.9060719013214111,
+      "learning_rate": 0.00019710680044180106,
+      "loss": 1.4268,
+      "step": 90
+    },
+    {
+      "epoch": 0.03678499172337686,
+      "grad_norm": 1.1774567365646362,
+      "learning_rate": 0.0001949391083889838,
+      "loss": 1.383,
+      "step": 100
+    },
+    {
+      "epoch": 0.03678499172337686,
+      "eval_loss": 1.49298894405365,
+      "eval_runtime": 65.3303,
+      "eval_samples_per_second": 17.526,
+      "eval_steps_per_second": 4.393,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8886804283392000.0,
+  "total_flos": 1.7773608566784e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null