Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e9f62ce442d2206a6217340dcb02487b81e352cc0ee85fb0134ac14c4d63f38
+oid sha256:65c016719c49be4ca5558ed86f62d48ff6511503d71d15734669ea899a7d5a07
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:032e106364ecc96e517002bdb753961e732393df86bfe59cfc313a5bb2516bc5
-size 341314196
+oid sha256:91d008f322fef9cbeb7f253b9b0010ac1539ec3c214ce9cf2b7e45cb201581d9
+size 341314644

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ffbf14335584bec486063b086aadc67b4f8f619b529239bb561df25995bb21d
+oid sha256:34709fca1d7c4f31268ebac24fa0fec894fb794996213a9a74e5d79229a2caac
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:335c5ad5d49110db61ad1b0e85277ad0de8eaa71b71c181fa25e7d8bd8f3fc98
+oid sha256:41439765e4324bfba55c134066121dc462eb56b67b27f6e7308aecd489d52c0e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.7571074962615967,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.0384172109104879,
+  "best_metric": 2.572946310043335,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.04610065309258548,
   "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": 15.614,
       "eval_steps_per_second": 3.903,
       "step": 250
+    },
+    {
+      "epoch": 0.039953899346907414,
+      "grad_norm": 4.981348514556885,
+      "learning_rate": 0.00011487096017983597,
+      "loss": 4.7851,
+      "step": 260
+    },
+    {
+      "epoch": 0.041490587783326933,
+      "grad_norm": 6.857975482940674,
+      "learning_rate": 0.00010762954765706012,
+      "loss": 4.6581,
+      "step": 270
+    },
+    {
+      "epoch": 0.043027276219746446,
+      "grad_norm": 8.468694686889648,
+      "learning_rate": 0.00010037045234293992,
+      "loss": 4.5606,
+      "step": 280
+    },
+    {
+      "epoch": 0.04456396465616596,
+      "grad_norm": 11.279480934143066,
+      "learning_rate": 9.312903982016405e-05,
+      "loss": 5.3172,
+      "step": 290
+    },
+    {
+      "epoch": 0.04610065309258548,
+      "grad_norm": 19.332422256469727,
+      "learning_rate": 8.594058952263925e-05,
+      "loss": 5.3847,
+      "step": 300
+    },
+    {
+      "epoch": 0.04610065309258548,
+      "eval_loss": 2.572946310043335,
+      "eval_runtime": 175.6968,
+      "eval_samples_per_second": 15.595,
+      "eval_steps_per_second": 3.899,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.936943131007386e+16,
+  "total_flos": 5.902866787074048e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null