Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28598f95ed60e857719652de1993acd6e4525c104785c48bca1d881f7796d57a
+oid sha256:4d9053147535d1a6842a50db700abeb3ea14c0d0553eadc54c3b5a3d5e5b04a6
 size 132164608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a37f4ccd96bf0c853ec5cde57cece5a83778ac816f0a770f01903d411cbc5b0
+oid sha256:d3fd7748c8830d1d92e3866d8434b912cc0738638f56d70fb0f7dd21b9f89c1e
 size 264524418

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f34bf20c962369d8f5ced8a82490dacebca1df36419a52d4df62804775e0beb
+oid sha256:ef9cb48c182dbc512d633e4dd95831e8bcc4b3518dc81b75ab79863c4c45da6d
 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": 2.936434507369995,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.012334258402713537,
+  "best_metric": 2.904956817626953,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.018501387604070305,
   "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": 12.814,
       "eval_steps_per_second": 6.417,
       "step": 20
+    },
+    {
+      "epoch": 0.012950971322849213,
+      "grad_norm": 1.7145406007766724,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 10.1028,
+      "step": 21
+    },
+    {
+      "epoch": 0.014801110083256245,
+      "grad_norm": 4.471871852874756,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 10.9136,
+      "step": 24
+    },
+    {
+      "epoch": 0.015417823003391921,
+      "eval_loss": 2.9108190536499023,
+      "eval_runtime": 53.3341,
+      "eval_samples_per_second": 12.806,
+      "eval_steps_per_second": 6.412,
+      "step": 25
+    },
+    {
+      "epoch": 0.016651248843663275,
+      "grad_norm": 2.2609989643096924,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 11.5034,
+      "step": 27
+    },
+    {
+      "epoch": 0.018501387604070305,
+      "grad_norm": 2.196725368499756,
+      "learning_rate": 0.0,
+      "loss": 10.759,
+      "step": 30
+    },
+    {
+      "epoch": 0.018501387604070305,
+      "eval_loss": 2.904956817626953,
+      "eval_runtime": 53.3934,
+      "eval_samples_per_second": 12.792,
+      "eval_steps_per_second": 6.405,
+      "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": 6861133447680000.0,
+  "total_flos": 1.0255588942848e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null