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:a2b49238da4c41404dd097adc65d8a182b42c0457858cf70f7b84c156bc0a315
+oid sha256:74e6f1beec75228b6b0bc2d421cb7c447ff656d777fa73073f37b5cd23deaab1
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:374abdf38288bae20534803eebd1640c3c5f26125d1a555a4ed5f0f6b0d34376
+oid sha256:6da96d7ade289abb7fcddf165809be0562c0ab4726f8f864b2882a62c5384fa1
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3ca9c86f4e1e8136456f71fa3c0684780b4398a9136b4c1725c36b538b5bfbb
+oid sha256:8e2118335db2898473d06b89728a309b26c700cc73a5bfb5c9c460b690637f00
 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": 1.249632477760315,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0033819488480236735,
+  "best_metric": 1.2432726621627808,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0050729232720355105,
   "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": 14.155,
       "eval_steps_per_second": 7.078,
       "step": 20
+    },
+    {
+      "epoch": 0.0035510462904248573,
+      "grad_norm": 0.4052756428718567,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.2445,
+      "step": 21
+    },
+    {
+      "epoch": 0.004058338617628408,
+      "grad_norm": 0.46778208017349243,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.2339,
+      "step": 24
+    },
+    {
+      "epoch": 0.004227436060029592,
+      "eval_loss": 1.2444090843200684,
+      "eval_runtime": 175.9887,
+      "eval_samples_per_second": 14.149,
+      "eval_steps_per_second": 7.074,
+      "step": 25
+    },
+    {
+      "epoch": 0.004565630944831959,
+      "grad_norm": 0.466905802488327,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.1967,
+      "step": 27
+    },
+    {
+      "epoch": 0.0050729232720355105,
+      "grad_norm": 0.46483084559440613,
+      "learning_rate": 0.0,
+      "loss": 1.2324,
+      "step": 30
+    },
+    {
+      "epoch": 0.0050729232720355105,
+      "eval_loss": 1.2432726621627808,
+      "eval_runtime": 175.9673,
+      "eval_samples_per_second": 14.15,
+      "eval_steps_per_second": 7.075,
+      "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": 9088119223615488.0,
+  "total_flos": 1.3261235193643008e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null