Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0c7d13fafd9abf7ef2ff638411616173b1059a0c3315d59e6b17307c2abdbf3
+oid sha256:f63287f71741657e67743f272886f1c595bf92a1d03189984552a9c27f95122d
 size 56660888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6e32a5b67f49fa11e8f926ddc0d2e3c9683674cd2efa87c30b2cdbddfe0a767
+oid sha256:ccdeb5f216b9b73c741deb16a7ef7fb674446ad7bbef841aa8cd7426d1edd8cf
 size 113488058

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f21b2c50a91a7d44b73675857caaecd86b906a07f0581676f56776824318a5ba
+oid sha256:732f4baeaa4944417ef090e2b340bbb18a6c6e47bd4124ccec37cdce05e59c23
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7031258940696716,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0030845157310302285,
+  "best_metric": 0.6288348436355591,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.006169031462060457,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 19.548,
       "eval_steps_per_second": 9.781,
       "step": 10
+    },
+    {
+      "epoch": 0.003701418877236274,
+      "grad_norm": 0.17671124637126923,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.5097,
+      "step": 12
+    },
+    {
+      "epoch": 0.0046267735965453425,
+      "grad_norm": 0.215486541390419,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5113,
+      "step": 15
+    },
+    {
+      "epoch": 0.0046267735965453425,
+      "eval_loss": 0.6584131121635437,
+      "eval_runtime": 70.0635,
+      "eval_samples_per_second": 19.482,
+      "eval_steps_per_second": 9.748,
+      "step": 15
+    },
+    {
+      "epoch": 0.005552128315854411,
+      "grad_norm": 0.27064475417137146,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.5853,
+      "step": 18
+    },
+    {
+      "epoch": 0.006169031462060457,
+      "eval_loss": 0.6288348436355591,
+      "eval_runtime": 70.2349,
+      "eval_samples_per_second": 19.435,
+      "eval_steps_per_second": 9.725,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 668839830355968.0,
+  "total_flos": 1321366494117888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null