Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2920a971dec518416d33ac3f026faa6fccf691838a3225fcb56335c75e5f7625
+oid sha256:1cc632775ecec91b0f7cbea2615c186dbdb24acb8ac4b10fc606313e33cce724
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:097a9d61c267f7d0794c19db5fa7920df00d481dbc7b6a7ea56aa2d62a3e99a9
+oid sha256:53647ed16cc27c0f5dd56c972ffb053962a18bd1fedf6b2873f6e282fe120997
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea3c486b366b7ad1bd39abe0b3d1a0af4c6b486923a5eced42a19e659304e95
+oid sha256:b674d3044c6b6e7f8a15a1bf0a765c6d25615fdb79bf21ae1edf6a1d46e6c9b9
 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": 0.4402143955230713,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0005088572973316795,
+  "best_metric": 0.43388381600379944,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0007632859459975193,
   "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": 3.133,
       "eval_steps_per_second": 1.566,
       "step": 20
+    },
+    {
+      "epoch": 0.0005343001621982635,
+      "grad_norm": 3.5380730628967285,
+      "learning_rate": 2.8711035421746367e-05,
+      "loss": 1.7239,
+      "step": 21
+    },
+    {
+      "epoch": 0.0006106287567980154,
+      "grad_norm": 3.277222156524658,
+      "learning_rate": 1.3551568628929434e-05,
+      "loss": 1.7184,
+      "step": 24
+    },
+    {
+      "epoch": 0.0006360716216645995,
+      "eval_loss": 0.435041606426239,
+      "eval_runtime": 5287.0075,
+      "eval_samples_per_second": 3.13,
+      "eval_steps_per_second": 1.565,
+      "step": 25
+    },
+    {
+      "epoch": 0.0006869573513977674,
+      "grad_norm": 2.5718576908111572,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 1.8221,
+      "step": 27
+    },
+    {
+      "epoch": 0.0007632859459975193,
+      "grad_norm": 3.041604995727539,
+      "learning_rate": 0.0,
+      "loss": 1.79,
+      "step": 30
+    },
+    {
+      "epoch": 0.0007632859459975193,
+      "eval_loss": 0.43388381600379944,
+      "eval_runtime": 5287.4764,
+      "eval_samples_per_second": 3.13,
+      "eval_steps_per_second": 1.565,
+      "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": 1.054695455981568e+16,
+  "total_flos": 1.5996214415720448e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null