Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12f45ec22165ba1a861376f483e15a312a9bbb064049e491217a861806d9e6d0
+oid sha256:c7db1582b3d837e7c69d7fd1318ff7feb9ce5e4e835721a47a607dd4442ab49b
 size 186962

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2e4dc769dca0e09f70f9422f9d936a5364eedbf163bb2584f9f072e6d4ca109
+oid sha256:90296c457dae8a5161567d650ce6487b929f907a79a57ebc1131ccf3e29d4e8b
 size 121430

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86b3b899a403b943c8f371dbf58756cf7d82685fb2a4135034bbda1824ea90fe
+oid sha256:815170232c37daa4028d07a1de57f229a2ae17f768632678693799e961896f8d
 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": 6.927796363830566,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.09768009768009768,
+  "best_metric": 6.925678253173828,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.14652014652014653,
   "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": 353.306,
       "eval_steps_per_second": 89.858,
       "step": 20
+    },
+    {
+      "epoch": 0.10256410256410256,
+      "grad_norm": 0.1820620894432068,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 6.9255,
+      "step": 21
+    },
+    {
+      "epoch": 0.11721611721611722,
+      "grad_norm": 0.1464235484600067,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 6.926,
+      "step": 24
+    },
+    {
+      "epoch": 0.1221001221001221,
+      "eval_loss": 6.9260029792785645,
+      "eval_runtime": 0.4927,
+      "eval_samples_per_second": 351.118,
+      "eval_steps_per_second": 89.302,
+      "step": 25
+    },
+    {
+      "epoch": 0.13186813186813187,
+      "grad_norm": 0.1777586191892624,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 6.9252,
+      "step": 27
+    },
+    {
+      "epoch": 0.14652014652014653,
+      "grad_norm": 0.15981440246105194,
+      "learning_rate": 0.0,
+      "loss": 6.9238,
+      "step": 30
+    },
+    {
+      "epoch": 0.14652014652014653,
+      "eval_loss": 6.925678253173828,
+      "eval_runtime": 0.4856,
+      "eval_samples_per_second": 356.267,
+      "eval_steps_per_second": 90.611,
+      "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": 235721195520.0,
+  "total_flos": 353581793280.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null