Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76d4572e3d2a3cae6f9718ea5a29dd63abda644d8ea35c02bcb16a3f679e2e36
+oid sha256:a8388fac3c8ec92e748e5c1bac94d17337e4712b9ab6780abd168a89ba1dfae1
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06af619dfe543bb13415ac04cbd1f9c836118c87bad87ec675c06a0685b454c0
-size 341314196
+oid sha256:98da35fc79c3e2c67bcced87f63b04465c396b220687042bfa650ba4fd8a5457
+size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb310fe4d4125a691a551bc8b5d6d61eab62d73e96f347f182ef4b8819ccd80a
+oid sha256:a11ecd7e47d45a3f251b3d832d4548c6c6de28225f2c7f28365eff461d2d3992
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc179f00b2227acaa3346fbc12b482f11319c504cfa09741eaad17d644154679
+oid sha256:c9ba82c4660fefa9fbbf06a718c7a06114d84fa536c01a280f55e7524e533da3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.8165959119796753,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.3450655624568668,
+  "best_metric": 1.5225303173065186,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.4140786749482402,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 16.315,
       "eval_steps_per_second": 4.119,
       "step": 250
+    },
+    {
+      "epoch": 0.3588681849551415,
+      "grad_norm": 16.661788940429688,
+      "learning_rate": 0.00011431869594820213,
+      "loss": 3.6444,
+      "step": 260
+    },
+    {
+      "epoch": 0.37267080745341613,
+      "grad_norm": 21.61427116394043,
+      "learning_rate": 0.00010711209790870886,
+      "loss": 2.8124,
+      "step": 270
+    },
+    {
+      "epoch": 0.3864734299516908,
+      "grad_norm": 14.587434768676758,
+      "learning_rate": 9.988790209129117e-05,
+      "loss": 2.6168,
+      "step": 280
+    },
+    {
+      "epoch": 0.4002760524499655,
+      "grad_norm": 10.792880058288574,
+      "learning_rate": 9.268130405179787e-05,
+      "loss": 2.8998,
+      "step": 290
+    },
+    {
+      "epoch": 0.4140786749482402,
+      "grad_norm": 19.90591049194336,
+      "learning_rate": 8.55274136114727e-05,
+      "loss": 2.9482,
+      "step": 300
+    },
+    {
+      "epoch": 0.4140786749482402,
+      "eval_loss": 1.5225303173065186,
+      "eval_runtime": 18.6815,
+      "eval_samples_per_second": 16.326,
+      "eval_steps_per_second": 4.122,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.4718712946688e+16,
+  "total_flos": 5.36624555360256e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null