Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:780ca9ea6bec6229fe7e0d5a3838448b72bdcfa4a6a92192f128e5a44d814f87
+oid sha256:4daa8372a646806b343e84b941ed388aff25fa982442144d18a8d0db02ab75aa
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03a4c5996e7a1ff890ee9fd657be505265cdc6e49597fb1e49968d6f0e1cded3
+oid sha256:95f1e43a0751897bc233882d0c2a84cdc1a54609a966e1c223d4671acc7cfe8b
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98f0b46a055895d37d66fcedbb237bcf5d7d58216e3c9875c0855f56c45a5101
+oid sha256:6589d018f91f97165f298b9b659197fbb9fe8847d828b74d5b8f2a889526405a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d0f57336dd58c2282a758b1873df2644647c71e8296b0dab58cb3a9f5f7c78
+oid sha256:7e45926e8bb4228c69b4b56f6b51f1445c0aeb3fb7bb09ed84764ec2b4c3a8ff
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.5890767574310303,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.10582010582010581,
+  "best_metric": 0.47778764367103577,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.15873015873015872,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 19.483,
       "eval_steps_per_second": 4.895,
       "step": 100
+    },
+    {
+      "epoch": 0.1164021164021164,
+      "grad_norm": 7.185388088226318,
+      "learning_rate": 3.1076923076923076e-06,
+      "loss": 0.3998,
+      "step": 110
+    },
+    {
+      "epoch": 0.12698412698412698,
+      "grad_norm": 5.154370307922363,
+      "learning_rate": 2.330769230769231e-06,
+      "loss": 0.3106,
+      "step": 120
+    },
+    {
+      "epoch": 0.13756613756613756,
+      "grad_norm": 11.753735542297363,
+      "learning_rate": 1.5538461538461538e-06,
+      "loss": 0.3945,
+      "step": 130
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 8.9371976852417,
+      "learning_rate": 7.769230769230769e-07,
+      "loss": 0.438,
+      "step": 140
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "grad_norm": 16.33173942565918,
+      "learning_rate": 0.0,
+      "loss": 0.4991,
+      "step": 150
+    },
+    {
+      "epoch": 0.15873015873015872,
+      "eval_loss": 0.47778764367103577,
+      "eval_runtime": 20.4229,
+      "eval_samples_per_second": 19.488,
+      "eval_steps_per_second": 4.896,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -124,12 +167,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.5547217133568e+16,
+  "total_flos": 5.3320825700352e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null