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:b854e08d60e939ef5c6f8b43ae1ab79b64fac3894b2c1a0fbe94f444f51b1aa3
+oid sha256:9ea700f4f7ef6987346fc059f66ca3e37f612f4b454b9ca1ca3d64cfad809068
 size 191968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37c76ae8831fb0e153189ecf8c8eb1e5c573cb5ec1685811bb399ca17e572f5b
+oid sha256:29887705fae9b65ea052c9e3c0a3eadad434a661af987d8128c419eb06fa1e50
 size 253144

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:526b5a79482e8e0048f4b347be4d333d12b87f099b138bc8ad03b0a7d0cd11f3
+oid sha256:acd761876d7a227bba78c669c746a47a1a949b2a96bdcbed304bd16c2c329aee
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9b2510d4f3300d86de2c5b705a4b3113b18ea2234bf5e3432bd4dee5175a4db
+oid sha256:e79d8c81c28cccecf62c97d7dd656ff3c70055cc3d5608fb5051fff0516dc264
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.734283447265625,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.2915451895043732,
+  "best_metric": 11.732454299926758,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.3498542274052478,
   "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": 220.625,
       "eval_steps_per_second": 55.615,
       "step": 250
+    },
+    {
+      "epoch": 0.3032069970845481,
+      "grad_norm": 0.1815534234046936,
+      "learning_rate": 0.00011210963902166683,
+      "loss": 11.7412,
+      "step": 260
+    },
+    {
+      "epoch": 0.31486880466472306,
+      "grad_norm": 0.2676528990268707,
+      "learning_rate": 0.00010504229891530386,
+      "loss": 11.7368,
+      "step": 270
+    },
+    {
+      "epoch": 0.32653061224489793,
+      "grad_norm": 0.2543658912181854,
+      "learning_rate": 9.795770108469618e-05,
+      "loss": 11.7335,
+      "step": 280
+    },
+    {
+      "epoch": 0.33819241982507287,
+      "grad_norm": 0.25447171926498413,
+      "learning_rate": 9.08903609783332e-05,
+      "loss": 11.7292,
+      "step": 290
+    },
+    {
+      "epoch": 0.3498542274052478,
+      "grad_norm": 0.3657534718513489,
+      "learning_rate": 8.387470996680658e-05,
+      "loss": 11.7254,
+      "step": 300
+    },
+    {
+      "epoch": 0.3498542274052478,
+      "eval_loss": 11.732454299926758,
+      "eval_runtime": 1.6359,
+      "eval_samples_per_second": 220.675,
+      "eval_steps_per_second": 55.627,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 12948307968000.0,
+  "total_flos": 15537969561600.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null