Training in progress, step 57, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a179ef06fa006143118138438936f03fe0009da8921d74ead29955a1c84b61d
+oid sha256:22265fae1703ffda9751b773d5c3f7c52db6160760fbd17c897889a60eb3721e
 size 332316480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce644ea9fa07baff2b19a3abd61fae774b05d89b4feef1eb90b2d2a5c1a92757
+oid sha256:8910bbf4b3c1586cc12c75c8bd014aec8494d951b6a7185091f8af4f1b4a3258
 size 169157892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0029a7336834e104646d4ee0f59f44545cf434ad316a616dea1fdae6a1890483
+oid sha256:3ace65d523f54a708c493d5f6fdd6b6fd3d9877ce27d356fd561ffbc523c678f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c19540610427b7a8e051502a2f9b29e8689f426c64528ae25ca45e698aa73ad
+oid sha256:798c2fb93c2c30432cc6d8a50fd6e334ae2cbcbf55475fcdeccb88eb2c638bd2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.17902410030365,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 2.6315789473684212,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 57,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,55 @@
       "eval_samples_per_second": 22.16,
       "eval_steps_per_second": 5.54,
       "step": 50
+    },
+    {
+      "epoch": 2.6842105263157894,
+      "grad_norm": 1.3527997732162476,
+      "learning_rate": 3.967505666178556e-06,
+      "loss": 0.5721,
+      "step": 51
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 1.6944499015808105,
+      "learning_rate": 2.7665454196040664e-06,
+      "loss": 0.5942,
+      "step": 52
+    },
+    {
+      "epoch": 2.7894736842105265,
+      "grad_norm": 1.7159970998764038,
+      "learning_rate": 1.7765412472811771e-06,
+      "loss": 0.6168,
+      "step": 53
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 1.695430874824524,
+      "learning_rate": 1.0019147481706625e-06,
+      "loss": 0.5101,
+      "step": 54
+    },
+    {
+      "epoch": 2.8947368421052633,
+      "grad_norm": 1.4705897569656372,
+      "learning_rate": 4.461255922609986e-07,
+      "loss": 0.632,
+      "step": 55
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 1.322156548500061,
+      "learning_rate": 1.1165606884234181e-07,
+      "loss": 0.4171,
+      "step": 56
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.7574959993362427,
+      "learning_rate": 0.0,
+      "loss": 0.5181,
+      "step": 57
     }
   ],
   "logging_steps": 1,
@@ -396,12 +445,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.0563013293572096e+16,
+  "total_flos": 2.338589547115315e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null