Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06242f238646121954c9fa4de7b9e057b2c6b6eb0e07d17440c0d5c11053fcdd
+oid sha256:96f13e8ade0879977c043f1d795d65b83b172e20c98e92e1e539c83c5c26957a
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e091db8b3dd4c73ef0cedd28dbfcf398f19f051b0f453f53d720d5417eb7037d
+oid sha256:ef8d95638c8b49b682ae230545db38d92126e345efbbab65739406938124c6e8
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a68a2c55c511c093af16aefb67eca81a483d7c2c144a45c1804469b0ec2c91e3
+oid sha256:e7bf6dd89e9518686b0bf29643f50f49c99d22638851f6461958723770603929
 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": 2.5079739093780518,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.019985011241568824,
+  "best_metric": 2.4360692501068115,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.029977516862353237,
   "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": 2.603,
       "eval_steps_per_second": 1.301,
       "step": 20
+    },
+    {
+      "epoch": 0.020984261803647264,
+      "grad_norm": 8.353514671325684,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 10.3783,
+      "step": 21
+    },
+    {
+      "epoch": 0.02398201348988259,
+      "grad_norm": 11.086196899414062,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 9.4603,
+      "step": 24
+    },
+    {
+      "epoch": 0.02498126405196103,
+      "eval_loss": 2.4464001655578613,
+      "eval_runtime": 162.0333,
+      "eval_samples_per_second": 2.604,
+      "eval_steps_per_second": 1.302,
+      "step": 25
+    },
+    {
+      "epoch": 0.02697976517611791,
+      "grad_norm": 6.061897277832031,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 9.5595,
+      "step": 27
+    },
+    {
+      "epoch": 0.029977516862353237,
+      "grad_norm": 5.1886305809021,
+      "learning_rate": 0.0,
+      "loss": 9.5828,
+      "step": 30
+    },
+    {
+      "epoch": 0.029977516862353237,
+      "eval_loss": 2.4360692501068115,
+      "eval_runtime": 162.3182,
+      "eval_samples_per_second": 2.6,
+      "eval_steps_per_second": 1.3,
+      "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": 1.26956599246848e+16,
+  "total_flos": 1.90434898870272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null