Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c545cb8d0d6f41df3a89f2b44ea668d6ab0a8bb37e85bb2a70ec42a7c240316
+oid sha256:8c87f29e60c5e09cd5df4311dee83f99b94bea618b9355301adc10a4eb39dcc9
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebc7b0f4d309034f0bdbc4aa6de2beaf82482688ab10c653d02afe3766c60996
+oid sha256:852988a45cbd28b2a5c0415ccd0a86dcde134d50d9c802edaae5072023bfad73
 size 501028338

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd11c0e5fa567a288a3e7fc5c47f799160ad0c2656a839e3b49ff66725e523e2
+oid sha256:c7332cedcc7b3b36b7974e070bd9fa7171e6a96e191919b27b6014d872048e1e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 3.4370737075805664,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0016354567012838335,
+  "best_metric": 2.66746187210083,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.003270913402567667,
   "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": 5.044,
       "eval_steps_per_second": 2.523,
       "step": 10
+    },
+    {
+      "epoch": 0.0019625480415406,
+      "grad_norm": 1.746925711631775,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 3.4661,
+      "step": 12
+    },
+    {
+      "epoch": 0.0024531850519257502,
+      "grad_norm": 1.3604792356491089,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.7556,
+      "step": 15
+    },
+    {
+      "epoch": 0.0024531850519257502,
+      "eval_loss": 2.8416481018066406,
+      "eval_runtime": 510.5806,
+      "eval_samples_per_second": 5.043,
+      "eval_steps_per_second": 2.523,
+      "step": 15
+    },
+    {
+      "epoch": 0.0029438220623109004,
+      "grad_norm": 1.0310943126678467,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.6629,
+      "step": 18
+    },
+    {
+      "epoch": 0.003270913402567667,
+      "eval_loss": 2.66746187210083,
+      "eval_runtime": 510.8032,
+      "eval_samples_per_second": 5.041,
+      "eval_steps_per_second": 2.522,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6347789697024000.0,
+  "total_flos": 1.2695579394048e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null