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:f4f3fbf00862632baf3c119ca82b104caed11f310a0a693ccf730306b4d4f279
+oid sha256:dac697d79f71aeca70d236d49564140d9616efd48e9770369e86d1fed3b596a6
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6966aab58b06a67c428daa6071d698998133f1fba615ef5652b4e2be88d8cc55
+oid sha256:241628657c2ac3de1d7335b97f9fcb24c0e121901a5251c921c05beb7e7f3956
 size 127788756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e0f4ca7bf5e92c470812e30e31e73f76412609321b341aefa4c5b3a580e4d2
+oid sha256:ff5848d108a7c7fcbc7dbb34aa525212737fe6f8487e66189776e5fdf9159f0f
 size 14308

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d65cbcc88ce62ea29e227485d6b50848e9fbaab924ae7e4e51111e4715d6b102
+oid sha256:935feb3a63b37324efd90f0473c874080c886e9eea264139d581d13a208d37c1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8012982606887817,
-  "best_model_checkpoint": "miner_id_24/checkpoint-350",
-  "epoch": 0.1196785775346213,
+  "best_metric": 0.7848264575004578,
+  "best_model_checkpoint": "miner_id_24/checkpoint-400",
+  "epoch": 0.13677551718242434,
   "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": 6.753,
       "eval_steps_per_second": 1.688,
       "step": 350
+    },
+    {
+      "epoch": 0.1230979654641819,
+      "grad_norm": 0.3492680490016937,
+      "learning_rate": 4.452151674945458e-05,
+      "loss": 0.7909,
+      "step": 360
+    },
+    {
+      "epoch": 0.1265173533937425,
+      "grad_norm": 0.31265050172805786,
+      "learning_rate": 3.8818190992108515e-05,
+      "loss": 0.6951,
+      "step": 370
+    },
+    {
+      "epoch": 0.12993674132330313,
+      "grad_norm": 4.880677700042725,
+      "learning_rate": 3.3417808757755355e-05,
+      "loss": 0.9059,
+      "step": 380
+    },
+    {
+      "epoch": 0.13335612925286375,
+      "grad_norm": 0.3902217745780945,
+      "learning_rate": 2.8346680165796253e-05,
+      "loss": 0.7231,
+      "step": 390
+    },
+    {
+      "epoch": 0.13677551718242434,
+      "grad_norm": 0.9335039258003235,
+      "learning_rate": 2.362951124498323e-05,
+      "loss": 0.7406,
+      "step": 400
+    },
+    {
+      "epoch": 0.13677551718242434,
+      "eval_loss": 0.7848264575004578,
+      "eval_runtime": 182.302,
+      "eval_samples_per_second": 6.758,
+      "eval_steps_per_second": 1.69,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -344,7 +387,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8789464952274944e+17,
+  "total_flos": 2.1471407162523648e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null