Training in progress, step 400, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:023c2d698fecfc984e17730c34cb90653e99b41003570e33ddabcb73070c981a
+oid sha256:20bfa195723cb5e5627947c48f26aab5046a0409b339033a16d2f22718804e40
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a114e278af1711783c9eac6fa1060780a703980b622f510c43bc0931947d34bb
+oid sha256:211637f21c3abdb1716a1fabcb8c5e63d3351e48bc0fa4f7667befe8ef431889
 size 82461044

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13fe4b337f45d709ea68a7e25687b162198cdd306b4ab2f6b2887f81efef51bf
+oid sha256:2c4ead089cf94832276d3e2bad2b7c18561fea4acccb1d58107ff810a0ef91cd
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da27c36e86fbec616f670eea7cf6f44ac00b01103ba631450b5687f812aaa463
+oid sha256:2661f04b964aebdbfc5fe2d76ad72c51b84450f62ecbdcf121c15876692362c9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2823299169540405,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.20167098818784213,
+  "best_metric": 1.2757760286331177,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.23048112935753384,
   "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": 16.327,
       "eval_steps_per_second": 4.087,
       "step": 350
+    },
+    {
+      "epoch": 0.20743301642178047,
+      "grad_norm": 0.6709028482437134,
+      "learning_rate": 4.738676287689473e-05,
+      "loss": 1.701,
+      "step": 360
+    },
+    {
+      "epoch": 0.2131950446557188,
+      "grad_norm": 0.6328491568565369,
+      "learning_rate": 4.131639140249173e-05,
+      "loss": 1.524,
+      "step": 370
+    },
+    {
+      "epoch": 0.21895707288965716,
+      "grad_norm": 0.835404634475708,
+      "learning_rate": 3.5568459816422774e-05,
+      "loss": 1.2396,
+      "step": 380
+    },
+    {
+      "epoch": 0.2247191011235955,
+      "grad_norm": 0.9026359915733337,
+      "learning_rate": 3.017097146359502e-05,
+      "loss": 0.96,
+      "step": 390
+    },
+    {
+      "epoch": 0.23048112935753384,
+      "grad_norm": 1.3837984800338745,
+      "learning_rate": 2.5150222364709875e-05,
+      "loss": 0.7806,
+      "step": 400
+    },
+    {
+      "epoch": 0.23048112935753384,
+      "eval_loss": 1.2757760286331177,
+      "eval_runtime": 44.9117,
+      "eval_samples_per_second": 16.276,
+      "eval_steps_per_second": 4.075,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.343776141941146e+16,
+  "total_flos": 7.243788459599462e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null