Training in progress, step 350, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a89c59bf3864b7305e20ccd9430e0ab610f6cae4ebe9f3753a81fa09446b1206
+oid sha256:aee6ed3c05428b44110e484c5d881e7899a865aa805b08a623e67ef8441824e6
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:771ce74afffabf95c1ffbab46f6e4580f7487dac7e2a9dd326932204e2f15d92
+oid sha256:59271043586c4698f23841d46c3d037e7aaef955ddd49c140067880e1a67514a
 size 328468852

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3cb1012e9683b81c3f7ec494c0b281829c21298d5ca725b1ba1625a4f03cb8
+oid sha256:db6565a983eb60a1ab2039221a989689679339010c7128893817127967f2ed54
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e3407292f65425c0593f095883f5f3c050baccb28fc15b3c1ad88090d6c23ef
+oid sha256:9aefa5c0989fb1076f44dee5ec81119730caab480902e567590e4c3defecd81d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.582470417022705,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.25773195876288657,
+  "best_metric": 1.5370266437530518,
+  "best_model_checkpoint": "miner_id_24/checkpoint-350",
+  "epoch": 0.3006872852233677,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,49 @@
       "eval_samples_per_second": 17.757,
       "eval_steps_per_second": 4.457,
       "step": 300
+    },
+    {
+      "epoch": 0.2663230240549828,
+      "grad_norm": 0.7815156579017639,
+      "learning_rate": 8.263051337963623e-05,
+      "loss": 1.711,
+      "step": 310
+    },
+    {
+      "epoch": 0.27491408934707906,
+      "grad_norm": 0.9176328778266907,
+      "learning_rate": 7.531714761313074e-05,
+      "loss": 1.6178,
+      "step": 320
+    },
+    {
+      "epoch": 0.28350515463917525,
+      "grad_norm": 1.0819611549377441,
+      "learning_rate": 6.816788131766559e-05,
+      "loss": 1.5278,
+      "step": 330
+    },
+    {
+      "epoch": 0.2920962199312715,
+      "grad_norm": 1.2202140092849731,
+      "learning_rate": 6.121754499999055e-05,
+      "loss": 1.4741,
+      "step": 340
+    },
+    {
+      "epoch": 0.3006872852233677,
+      "grad_norm": 3.0831830501556396,
+      "learning_rate": 5.450000000000003e-05,
+      "loss": 1.447,
+      "step": 350
+    },
+    {
+      "epoch": 0.3006872852233677,
+      "eval_loss": 1.5370266437530518,
+      "eval_runtime": 27.5847,
+      "eval_samples_per_second": 17.763,
+      "eval_steps_per_second": 4.459,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -301,7 +344,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.3320825700352e+16,
+  "total_flos": 6.2207629983744e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null