Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f6b6e88fab7e73b1927556deacf3e8e302b6d8fc88359fed3bf3cdc73313672
+oid sha256:ef960ed157da2ee1ec0f179e2bd9dfc33e13c98de053dca02446f7fef7f523b8
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee44534c6f348481b700c9bcceb4760ae21d4beb9ee10d542e1f8420e4c44fa9
+oid sha256:47cb9ab736b34aaf68a8a658b98cbaa3b3154dd2fd8f0ba17bfa1eb3ff3a290e
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83361e520816e05e7f16754438edf4c9a8891eb40fbd7325ea6aeff6f814573e
+oid sha256:71d98682b213644071c2d315689392b423e45ba4a1b0618d07fbddb9a563d406
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.165391683578491,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0014248312465492369,
+  "best_metric": 2.1252670288085938,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.002137246869823855,
   "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": 47.658,
       "eval_steps_per_second": 23.833,
       "step": 20
+    },
+    {
+      "epoch": 0.0014960728088766987,
+      "grad_norm": 1.945841908454895,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.0475,
+      "step": 21
+    },
+    {
+      "epoch": 0.0017097974958590841,
+      "grad_norm": 2.166755199432373,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.2409,
+      "step": 24
+    },
+    {
+      "epoch": 0.001781039058186546,
+      "eval_loss": 2.1316721439361572,
+      "eval_runtime": 124.1003,
+      "eval_samples_per_second": 47.631,
+      "eval_steps_per_second": 23.819,
+      "step": 25
+    },
+    {
+      "epoch": 0.0019235221828414698,
+      "grad_norm": 2.1919233798980713,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.2256,
+      "step": 27
+    },
+    {
+      "epoch": 0.002137246869823855,
+      "grad_norm": 1.7260620594024658,
+      "learning_rate": 0.0,
+      "loss": 2.0275,
+      "step": 30
+    },
+    {
+      "epoch": 0.002137246869823855,
+      "eval_loss": 2.1252670288085938,
+      "eval_runtime": 123.7376,
+      "eval_samples_per_second": 47.77,
+      "eval_steps_per_second": 23.889,
+      "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": 360477150412800.0,
+  "total_flos": 540715725619200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null