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:ae5ed928a43303348bb3702371bc2941af1a00baf1bb1467a7e617aa3ce11193
+oid sha256:659c800c49c269d317be714b3310a903a53ed47abc6a3547e2eaaa3378193148
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe0050bf591756cc97a97f6209235a6c5f4b2718af63c4a914c86062c2ba4d32
+oid sha256:55d3240782e38d92e87d837340d619029d2cd265e925b684e5d65b3d9212e9e2
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53857b31065290226097899a29c43817f42b59cc1033072766ec46b6e8e362ce
+oid sha256:98e41df5f771584bb63c4aed1116817e1f4c07c6c2296db725d83962a1293b12
 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": 1.0215682983398438,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.003769140164899882,
+  "best_metric": 1.003777027130127,
+  "best_model_checkpoint": "miner_id_24/checkpoint-25",
+  "epoch": 0.004711425206124852,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 25,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 7.335,
       "eval_steps_per_second": 3.669,
       "step": 20
+    },
+    {
+      "epoch": 0.003957597173144876,
+      "grad_norm": 1.8999024629592896,
+      "learning_rate": 3.308693936411421e-05,
+      "loss": 4.0118,
+      "step": 21
+    },
+    {
+      "epoch": 0.004146054181389871,
+      "grad_norm": 2.3246095180511475,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 3.8845,
+      "step": 22
+    },
+    {
+      "epoch": 0.004334511189634864,
+      "grad_norm": 2.1159679889678955,
+      "learning_rate": 8.645454235739903e-06,
+      "loss": 3.7619,
+      "step": 23
+    },
+    {
+      "epoch": 0.004522968197879859,
+      "grad_norm": 2.50178599357605,
+      "learning_rate": 2.1852399266194314e-06,
+      "loss": 4.4033,
+      "step": 24
+    },
+    {
+      "epoch": 0.004711425206124852,
+      "grad_norm": 2.0925161838531494,
+      "learning_rate": 0.0,
+      "loss": 3.8412,
+      "step": 25
+    },
+    {
+      "epoch": 0.004711425206124852,
+      "eval_loss": 1.003777027130127,
+      "eval_runtime": 305.195,
+      "eval_samples_per_second": 7.323,
+      "eval_steps_per_second": 3.663,
+      "step": 25
     }
   ],
   "logging_steps": 1,
@@ -210,12 +253,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5705610716774400.0,
+  "total_flos": 7132013395968000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null