Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26f5ce926d12ae5566b4582e76cd8795850ebbd48aeaa3fe8afcd9e1c3149ab1
+oid sha256:2176c32ce834d20923887229b1d8b223fdc741dfa630a4613c33424eb3ae21ec
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07a0e50545b540b367f16bb13d496f2e4b62954e1efd357f82ac1d32d5dfe453
+oid sha256:d8cbad83832e66200dc627ddb3034dbaeb3c3532903e58c879425ac054212a48
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d143b857efe9b2f5e9e5f3317722527032a2ebf78aea15c1a29bea382f3d58b
+oid sha256:4f4be8a1df7b05b3bd2cc866295a0a33e473ace78c6b0920d4624e7837fc6750
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5158158540725708,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07766990291262135,
+  "best_metric": 0.4938437342643738,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.11650485436893204,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 12.641,
       "eval_steps_per_second": 3.204,
       "step": 20
+    },
+    {
+      "epoch": 0.08155339805825243,
+      "grad_norm": 1.000632643699646,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.8741,
+      "step": 21
+    },
+    {
+      "epoch": 0.09320388349514563,
+      "grad_norm": 0.9927970170974731,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 2.0363,
+      "step": 24
+    },
+    {
+      "epoch": 0.0970873786407767,
+      "eval_loss": 0.49725064635276794,
+      "eval_runtime": 17.2337,
+      "eval_samples_per_second": 12.592,
+      "eval_steps_per_second": 3.191,
+      "step": 25
+    },
+    {
+      "epoch": 0.10485436893203884,
+      "grad_norm": 1.104741096496582,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 2.0511,
+      "step": 27
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "grad_norm": 1.2001004219055176,
+      "learning_rate": 0.0,
+      "loss": 1.8453,
+      "step": 30
+    },
+    {
+      "epoch": 0.11650485436893204,
+      "eval_loss": 0.4938437342643738,
+      "eval_runtime": 17.1904,
+      "eval_samples_per_second": 12.623,
+      "eval_steps_per_second": 3.199,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.53913198493696e+16,
+  "total_flos": 3.80869797740544e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null