Training in progress, step 25, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c9e2d6ca2cfdea6a28a84d60973c98b945cdbec3ac091793d2366b4b8681255
+oid sha256:fb231c786aa007c6d056d0e6bfc6ac79217cc4d2263035c8251de5027594f2a3
 size 63592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03c44349348d24bf95d09ef7d1035086157349a66574a920e8c2be4cd7fcd587
+oid sha256:7a79d368b35830970c9cbcefd02d07a2ad2bec98a0d558f238f81a675856053e
 size 136814

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6c308f72e634c6d4709c1a706d150b00f5df05813f2ee8017457cbf49afc5af
+oid sha256:803e29d36c86e3231da33cb4c7e707352912eae2f15f55d0eb50583e0db78ca9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
+oid sha256:4521b8db9cc205e54aa606d85e707c024abd2d8ad4a20bec4b2cff365dc59cdf
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 11.06680965423584,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.00032361935891005,
+  "best_metric": 11.065860748291016,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.0004045241986375625,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,28 @@
       "eval_samples_per_second": 53.236,
       "eval_steps_per_second": 26.618,
       "step": 20
+    },
+    {
+      "epoch": 0.0003398003268555525,
+      "grad_norm": 0.36386507749557495,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 11.0748,
+      "step": 21
+    },
+    {
+      "epoch": 0.00038834323069206,
+      "grad_norm": 0.40148958563804626,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 11.0616,
+      "step": 24
+    },
+    {
+      "epoch": 0.0004045241986375625,
+      "eval_loss": 11.065860748291016,
+      "eval_runtime": 122.8041,
+      "eval_samples_per_second": 52.979,
+      "eval_steps_per_second": 26.489,
+      "step": 25
     }
   ],
   "logging_steps": 3,
@@ -112,12 +134,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 9358540800.0,
+  "total_flos": 11698176000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null