Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ef3439c7c950619bc70c1c38dafe4703aec5f1de5b4a72bbaf5c5464e3ba9e2
+oid sha256:78ea5d69c29f4c409145c01c8c32bc7fb30d282379b404e41117534388d93e9c
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac0f5f8d7955336f9c4252db79e7fc3b5e32eb89d861fd4703693b8f3428813b
+oid sha256:c3a5c672c3e6975bc84938d5be717adbb6a14873ccf2748d5985f9013289929a
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbb9e91f83953c523df848d18f17ed8971dc8a2dd5518ba86e7e2c27fdc46c46
+oid sha256:f8065cbbf95f63271f72fac5f49ace8523a0fc6cc077455c905ea647193a9963
 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": 2.3630073070526123,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.07640878701050621,
+  "best_metric": 2.351961374282837,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.11461318051575932,
   "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": 3.799,
       "eval_steps_per_second": 0.963,
       "step": 20
+    },
+    {
+      "epoch": 0.08022922636103152,
+      "grad_norm": 0.5455902218818665,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 9.4206,
+      "step": 21
+    },
+    {
+      "epoch": 0.09169054441260745,
+      "grad_norm": 0.5599693059921265,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 9.5553,
+      "step": 24
+    },
+    {
+      "epoch": 0.09551098376313276,
+      "eval_loss": 2.353801727294922,
+      "eval_runtime": 57.9063,
+      "eval_samples_per_second": 3.817,
+      "eval_steps_per_second": 0.967,
+      "step": 25
+    },
+    {
+      "epoch": 0.10315186246418338,
+      "grad_norm": 0.5651564002037048,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 9.3167,
+      "step": 27
+    },
+    {
+      "epoch": 0.11461318051575932,
+      "grad_norm": 0.5002607703208923,
+      "learning_rate": 0.0,
+      "loss": 9.2053,
+      "step": 30
+    },
+    {
+      "epoch": 0.11461318051575932,
+      "eval_loss": 2.351961374282837,
+      "eval_runtime": 57.9236,
+      "eval_samples_per_second": 3.815,
+      "eval_steps_per_second": 0.967,
+      "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": 1.473673206693888e+16,
+  "total_flos": 2.210509810040832e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null