Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:665e35ae15189f15c319a4046aa86a5993185926ead098b2d9c7b11d20305444
+oid sha256:659ffd181c7b1c0537f66e3a3e5f02f57840deb20eeee0a6fd38720b004ab82f
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2830cede074f3c13303fd38fae8b758493ff30d06165102783629c65be2f3ac9
+oid sha256:28ce3623f8801bf3d21c0b2d1bc13bed207192bd38be4215e447bbd8ed34c62d
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89e9a5f6b567e7bec4407740e09a58d03cf9e44a5ff68d908a8995269b154a65
+oid sha256:c1834c699db824ee5fdd8c7d0dce6336414565f167b8340930d902363ba23ad0
 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": 1.6838022470474243,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0033350008337502085,
+  "best_metric": 1.6474578380584717,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0050025012506253125,
   "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": 8.594,
       "eval_steps_per_second": 2.149,
       "step": 20
+    },
+    {
+      "epoch": 0.003501750875437719,
+      "grad_norm": 0.7741876840591431,
+      "learning_rate": 5.7422070843492734e-05,
+      "loss": 1.5741,
+      "step": 21
+    },
+    {
+      "epoch": 0.00400200100050025,
+      "grad_norm": 0.7283011078834534,
+      "learning_rate": 2.7103137257858868e-05,
+      "loss": 1.6454,
+      "step": 24
+    },
+    {
+      "epoch": 0.00416875104218776,
+      "eval_loss": 1.6534961462020874,
+      "eval_runtime": 587.7652,
+      "eval_samples_per_second": 8.592,
+      "eval_steps_per_second": 2.149,
+      "step": 25
+    },
+    {
+      "epoch": 0.004502251125562781,
+      "grad_norm": 1.129853367805481,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 1.6665,
+      "step": 27
+    },
+    {
+      "epoch": 0.0050025012506253125,
+      "grad_norm": 0.9340394139289856,
+      "learning_rate": 0.0,
+      "loss": 1.6475,
+      "step": 30
+    },
+    {
+      "epoch": 0.0050025012506253125,
+      "eval_loss": 1.6474578380584717,
+      "eval_runtime": 587.2295,
+      "eval_samples_per_second": 8.6,
+      "eval_steps_per_second": 2.151,
+      "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": 1.355242939613184e+16,
+  "total_flos": 2.016337056497664e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null