Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b3022cf43ccfe9867ae8a9c64e9aabdf2a3053b1d2c825bb5e7b4eb9c9e6841
+oid sha256:a07e46e3b88df225c147765ab9645757040098cb5b4afd658d69b4b7c6b3b23e
 size 313820248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b439c7321226e387be653d739b1aba21a49021c9995e53a9fbaa7bcfd99f291f
+oid sha256:4a915b4e1bb7f8ec88ea64f0a3d5c0605ffbb4d87fdefb7483263c45fba22871
 size 159641284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:906a4c00e5c9edfe3eed563f07fc580ec44c7191fc0b782afccbe0255633e073
+oid sha256:662ffc216c7d58912a629bec81c1550588a648de6c8662a7441b7079343f396b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1123dd497c9b8910fe9a2e80a4ab323c0694a06c711a817decbfc0ad393e20a4
+oid sha256:913ab8b0d366eeaae4f2a144c807ce2c591297e394af2372dd426dd4c3850119
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6310955286026,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.01134650608659005,
+  "best_metric": 1.606103539466858,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.012967435527531487,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -316,6 +316,49 @@
       "eval_samples_per_second": 32.629,
       "eval_steps_per_second": 8.157,
       "step": 350
+    },
+    {
+      "epoch": 0.011670691974778338,
+      "grad_norm": 3.600574254989624,
+      "learning_rate": 4.5623534490777714e-05,
+      "loss": 1.8409,
+      "step": 360
+    },
+    {
+      "epoch": 0.011994877862966625,
+      "grad_norm": 3.5220589637756348,
+      "learning_rate": 3.9779037303794365e-05,
+      "loss": 1.5889,
+      "step": 370
+    },
+    {
+      "epoch": 0.012319063751154912,
+      "grad_norm": 3.7355663776397705,
+      "learning_rate": 3.42449822418582e-05,
+      "loss": 1.5124,
+      "step": 380
+    },
+    {
+      "epoch": 0.012643249639343199,
+      "grad_norm": 3.8457112312316895,
+      "learning_rate": 2.9048330664949622e-05,
+      "loss": 1.5491,
+      "step": 390
+    },
+    {
+      "epoch": 0.012967435527531487,
+      "grad_norm": 3.4412333965301514,
+      "learning_rate": 2.4214400137185785e-05,
+      "loss": 1.549,
+      "step": 400
+    },
+    {
+      "epoch": 0.012967435527531487,
+      "eval_loss": 1.606103539466858,
+      "eval_runtime": 396.0436,
+      "eval_samples_per_second": 32.794,
+      "eval_steps_per_second": 8.199,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.9469040170827776e+16,
+  "total_flos": 2.222863104029491e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null