Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58d861a4785445a4f639486dc4428fdab90ad4745f0b1c61a036a71e85cb3218
+oid sha256:c10020194eb4da53b42711f2bf49a13870475370533afe029033683bd34bb73b
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89e2231e4be6c5fcaeefbb57c0798ed41e4935b3d747475c3f794a46d3d8720e
+oid sha256:3a8a417afea632c89d4408f12357c65cfce5930654669f153f18e90c72c25e90
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 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": 11.761784553527832,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.019015925837889233,
+  "best_metric": 11.761639595031738,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.02852388875683385,
   "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": 44.958,
       "eval_steps_per_second": 22.53,
       "step": 20
+    },
+    {
+      "epoch": 0.019966722129783693,
+      "grad_norm": 0.046757008880376816,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 11.761,
+      "step": 21
+    },
+    {
+      "epoch": 0.022819111005467078,
+      "grad_norm": 0.053075361996889114,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 11.7616,
+      "step": 24
+    },
+    {
+      "epoch": 0.02376990729736154,
+      "eval_loss": 11.761663436889648,
+      "eval_runtime": 9.3829,
+      "eval_samples_per_second": 47.214,
+      "eval_steps_per_second": 23.66,
+      "step": 25
+    },
+    {
+      "epoch": 0.025671499881150462,
+      "grad_norm": 0.04611106216907501,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 11.7612,
+      "step": 27
+    },
+    {
+      "epoch": 0.02852388875683385,
+      "grad_norm": 0.0431927815079689,
+      "learning_rate": 0.0,
+      "loss": 11.7593,
+      "step": 30
+    },
+    {
+      "epoch": 0.02852388875683385,
+      "eval_loss": 11.761639595031738,
+      "eval_runtime": 9.8419,
+      "eval_samples_per_second": 45.012,
+      "eval_steps_per_second": 22.557,
+      "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": 4074000875520.0,
+  "total_flos": 6111001313280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null