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:ddc0d080daf9f36b20d9af7f32de001f50cda12c7d0babdbb79d46ee9643dcf5
+oid sha256:a89c59bf3864b7305e20ccd9430e0ab610f6cae4ebe9f3753a81fa09446b1206
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3dc805f052e23ef1d50bb2f989067dd601be6bc613556b646acd36f8d3b2e714
-size 328468404
+oid sha256:771ce74afffabf95c1ffbab46f6e4580f7487dac7e2a9dd326932204e2f15d92
+size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a8bf54e605c69e3ca1544f43f033c47c7e11641af7e205ed25a5aa2e16f1dcd
+oid sha256:dc3cb1012e9683b81c3f7ec494c0b281829c21298d5ca725b1ba1625a4f03cb8
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5245962b37abe5debb29d3c0771306ab720257c32ca897672f6c78751ec6642f
+oid sha256:4e3407292f65425c0593f095883f5f3c050baccb28fc15b3c1ad88090d6c23ef
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.633361577987671,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.21477663230240548,
+  "best_metric": 1.582470417022705,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.25773195876288657,
   "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": 17.714,
       "eval_steps_per_second": 4.447,
       "step": 250
+    },
+    {
+      "epoch": 0.22336769759450173,
+      "grad_norm": 0.8555697202682495,
+      "learning_rate": 0.00012039360249617425,
+      "loss": 1.7972,
+      "step": 260
+    },
+    {
+      "epoch": 0.23195876288659795,
+      "grad_norm": 0.9596598744392395,
+      "learning_rate": 0.00011280404514057264,
+      "loss": 1.6636,
+      "step": 270
+    },
+    {
+      "epoch": 0.24054982817869416,
+      "grad_norm": 1.0088611841201782,
+      "learning_rate": 0.00010519595485942743,
+      "loss": 1.5343,
+      "step": 280
+    },
+    {
+      "epoch": 0.24914089347079038,
+      "grad_norm": 1.1968733072280884,
+      "learning_rate": 9.76063975038258e-05,
+      "loss": 1.4937,
+      "step": 290
+    },
+    {
+      "epoch": 0.25773195876288657,
+      "grad_norm": 4.135494709014893,
+      "learning_rate": 9.00723486343046e-05,
+      "loss": 1.479,
+      "step": 300
+    },
+    {
+      "epoch": 0.25773195876288657,
+      "eval_loss": 1.582470417022705,
+      "eval_runtime": 27.5946,
+      "eval_samples_per_second": 17.757,
+      "eval_steps_per_second": 4.457,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.443402141696e+16,
+  "total_flos": 5.3320825700352e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null