Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d078bdc7e42b078c8272e5d7b5d43f3ed5900fd7f4091db1912f10572a0eb55
+oid sha256:4da1c7d747ef639a882f98d46b30ea8429de79de7f9b11a2edf96ed562f113eb
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f74ddfe510b560455b79e88b55fa61f2c2350c3095470522a6f340c392c7bfe
+oid sha256:3f34858cd1af631e7f8da701386070354a95f34eb526d7165eb8fadfb443babe
 size 201541754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f08d317b23a426766fdf8b72bc4f2be56971e2b8ed5cb73f614b927115f23949
+oid sha256:06d4336fb000f20d2a211ff8fbbb1890ff4f5ffb57097f927b5bcbf456d4cd44
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.505024790763855,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.015594541910331383,
+  "best_metric": 1.4978605508804321,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.023391812865497075,
   "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": 3.783,
       "eval_steps_per_second": 1.891,
       "step": 20
+    },
+    {
+      "epoch": 0.016374269005847954,
+      "grad_norm": 1.0933345556259155,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 6.107,
+      "step": 21
+    },
+    {
+      "epoch": 0.01871345029239766,
+      "grad_norm": 0.8241513967514038,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 6.1344,
+      "step": 24
+    },
+    {
+      "epoch": 0.01949317738791423,
+      "eval_loss": 1.4986428022384644,
+      "eval_runtime": 142.7114,
+      "eval_samples_per_second": 3.784,
+      "eval_steps_per_second": 1.892,
+      "step": 25
+    },
+    {
+      "epoch": 0.021052631578947368,
+      "grad_norm": 0.9181810617446899,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 6.4848,
+      "step": 27
+    },
+    {
+      "epoch": 0.023391812865497075,
+      "grad_norm": 0.8675422072410583,
+      "learning_rate": 0.0,
+      "loss": 5.8816,
+      "step": 30
+    },
+    {
+      "epoch": 0.023391812865497075,
+      "eval_loss": 1.4978605508804321,
+      "eval_runtime": 142.7544,
+      "eval_samples_per_second": 3.783,
+      "eval_steps_per_second": 1.891,
+      "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": 7368366033469440.0,
+  "total_flos": 1.105254905020416e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null