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:d53a8252851379d1c57808a74bd9f61e3cc6e8f00577a463d71786c937d95601
+oid sha256:faaeeeda328032a869898e08f292c4b10b7036a1bffc44806bbe84510e00ae8f
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a2cab22c44f43693e87749e625e9806e6971247f8ca551e9f2e79654f6ad035
+oid sha256:68ef0a386340620d9fd5d5caf4bbebc4a95d3d97fdae075eaa303d7d2ca57d93
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a81c37cef9d69bc8e31b2db7a7a01102e161ecef2ab1a8e0a5803314b5d183f
+oid sha256:635e164509d6a12ce01017e85a3fd6a4c5139a815063192ae0a884ad364308b0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8544739484786987,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0024351637647631805,
+  "best_metric": 0.8460270762443542,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0036527456471447703,
   "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": 1.906,
       "eval_steps_per_second": 0.953,
       "step": 20
+    },
+    {
+      "epoch": 0.0025569219530013395,
+      "grad_norm": 0.5297064781188965,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 3.4236,
+      "step": 21
+    },
+    {
+      "epoch": 0.0029221965177158166,
+      "grad_norm": 0.503964900970459,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 3.4543,
+      "step": 24
+    },
+    {
+      "epoch": 0.0030439547059539756,
+      "eval_loss": 0.8473823666572571,
+      "eval_runtime": 1813.4165,
+      "eval_samples_per_second": 1.907,
+      "eval_steps_per_second": 0.954,
+      "step": 25
+    },
+    {
+      "epoch": 0.0032874710824302936,
+      "grad_norm": 0.8906158208847046,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 3.3607,
+      "step": 27
+    },
+    {
+      "epoch": 0.0036527456471447703,
+      "grad_norm": 0.49788740277290344,
+      "learning_rate": 0.0,
+      "loss": 3.7162,
+      "step": 30
+    },
+    {
+      "epoch": 0.0036527456471447703,
+      "eval_loss": 0.8460270762443542,
+      "eval_runtime": 1814.3234,
+      "eval_samples_per_second": 1.906,
+      "eval_steps_per_second": 0.954,
+      "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": 1.999566438137856e+16,
+  "total_flos": 3.078697531736064e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null