Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7abb7db7664824f9b99d55381d0dcb675f530fb79f26271dc148939c36ac1fd
+oid sha256:aa8a51ebbcb32c68a2554e237087d1035efa5a083be777faa4b3fbe4f9c04125
 size 1006723888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10338f323ee9598dc921000b563a1a867ee9769cd4e365d536e38b4bfde7ebb1
+oid sha256:887ce0a12f0297bc8950056646dc889b71dd9951e4a66fc37a67ec1540939514
 size 511971668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed2a10045379cb883a1fb249a06e1e128f5649c0bf5bd9fec5bdd35f11b3fb09
+oid sha256:b6cf4ce058e3ca489edbe37db984d596614690f02ef602ad22fbe9004a2f60f6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4be7b38aa7a01f117ebb95bff4f596a12bcbebf1c53b704b1e44c42b56276682
+oid sha256:fe3012fb121cd84e6e41f718fd33de9e34ed33145ada7b055f7e25e49408431d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.4155665934085846,
-  "best_model_checkpoint": "miner_id_24/checkpoint-400",
-  "epoch": 0.08318602474784237,
+  "best_metric": 0.39971646666526794,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.09358427784132266,
   "eval_steps": 50,
-  "global_step": 400,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,49 @@
       "eval_samples_per_second": 6.281,
       "eval_steps_per_second": 1.573,
       "step": 400
+    },
+    {
+      "epoch": 0.08526567536653842,
+      "grad_norm": 0.9245039820671082,
+      "learning_rate": 2.081714761313074e-05,
+      "loss": 0.4084,
+      "step": 410
+    },
+    {
+      "epoch": 0.08734532598523448,
+      "grad_norm": 0.9160316586494446,
+      "learning_rate": 1.656275751894957e-05,
+      "loss": 0.4022,
+      "step": 420
+    },
+    {
+      "epoch": 0.08942497660393053,
+      "grad_norm": 0.9029657244682312,
+      "learning_rate": 1.275871237837696e-05,
+      "loss": 0.3921,
+      "step": 430
+    },
+    {
+      "epoch": 0.0915046272226266,
+      "grad_norm": 0.8298301696777344,
+      "learning_rate": 9.423545116956494e-06,
+      "loss": 0.3997,
+      "step": 440
+    },
+    {
+      "epoch": 0.09358427784132266,
+      "grad_norm": 0.8411400318145752,
+      "learning_rate": 6.573504334335994e-06,
+      "loss": 0.3864,
+      "step": 450
+    },
+    {
+      "epoch": 0.09358427784132266,
+      "eval_loss": 0.39971646666526794,
+      "eval_runtime": 80.8995,
+      "eval_samples_per_second": 6.267,
+      "eval_steps_per_second": 1.57,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -387,7 +430,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.360703465376973e+16,
+  "total_flos": 6.027457627737293e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null