Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69b6c7e872003635c704f98856184c03202a83857cb39c3370f2560bbe458d17
+oid sha256:ded30752c82015cdc81c5cd344f66ff786790fa455dbfd06c1304c2bb0ad3c4b
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:195427fe163b1df48f7ec036714491bb2ad8036f81e2c2bb5fb766c0b87ba5d1
+oid sha256:ddf474575d250c98f0bbeb23f7ae703bcb03a5d658c648939bc68929972c1e31
 size 82461044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:875d3390db0bf91ba85b959107272542a145d32919484e75275127d8c1cbeb93
+oid sha256:bcc24c73277f3c96f28b7c301c952e3126c4ad16110cf35bdcfaeb3044f08301
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4724a4322486cf07c6f137f6430836b1a2cb9ae0cd696f1604a47814630e3ba
+oid sha256:6a53e373878af8696de39d4b7adb8634138f0e346e89bffc05bcb76c7b6de169
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.5629172325134277,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.07964501080896576,
+  "best_metric": 2.5573015213012695,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.09102286949596086,
   "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": 10.025,
       "eval_steps_per_second": 2.508,
       "step": 350
+    },
+    {
+      "epoch": 0.08192058254636478,
+      "grad_norm": 0.5457383394241333,
+      "learning_rate": 4.5843938039042344e-05,
+      "loss": 2.6142,
+      "step": 360
+    },
+    {
+      "epoch": 0.0841961542837638,
+      "grad_norm": 0.5010927319526672,
+      "learning_rate": 3.997120656613154e-05,
+      "loss": 2.5545,
+      "step": 370
+    },
+    {
+      "epoch": 0.08647172602116282,
+      "grad_norm": 0.5765501856803894,
+      "learning_rate": 3.441041693867878e-05,
+      "loss": 2.4515,
+      "step": 380
+    },
+    {
+      "epoch": 0.08874729775856184,
+      "grad_norm": 0.5465764999389648,
+      "learning_rate": 2.9188660764780296e-05,
+      "loss": 2.4339,
+      "step": 390
+    },
+    {
+      "epoch": 0.09102286949596086,
+      "grad_norm": 0.9333412647247314,
+      "learning_rate": 2.4331377915626298e-05,
+      "loss": 2.4501,
+      "step": 400
+    },
+    {
+      "epoch": 0.09102286949596086,
+      "eval_loss": 2.5573015213012695,
+      "eval_runtime": 184.621,
+      "eval_samples_per_second": 10.026,
+      "eval_steps_per_second": 2.508,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.1507924488893235e+17,
+  "total_flos": 1.3159403401877914e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null