Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d9a73e741eefb644630fadfa546497cb4fe33ba0f87e9b658291535fa30c51f
+oid sha256:056a46bcbac60d6e917614c2d1e9fa915417f221af7f0bde6710d3e21f3375d2
 size 111454040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e7ac410d0991fccceb1a4c28c9e49f65788864b80e5911167d4920ba463a14c
+oid sha256:842c6a1ca707825f2688bee9c61cc4f4a449babc9073e3e23b01a794328ead09
 size 56950676

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b558e885770b766cd461fb1c8f1ae28550e8f96a3f3691981d26f79330fc5e9
+oid sha256:a95bb917618d6b3dbc089cac4c9f61c14ca385d595854a7db3eaaf658076ad01
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:1d95f3fb1f9df4cdd5f470d1684a242bf1d1940d47b9622802f603a91ffa5bc0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6596146821975708,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.003198976327575176,
+  "best_metric": 0.5206258296966553,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.006397952655150352,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,92 @@
       "eval_samples_per_second": 5.393,
       "eval_steps_per_second": 2.699,
       "step": 10
+    },
+    {
+      "epoch": 0.0035188739603326936,
+      "grad_norm": 0.9339617490768433,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.557,
+      "step": 11
+    },
+    {
+      "epoch": 0.003838771593090211,
+      "grad_norm": 1.4919383525848389,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.6669,
+      "step": 12
+    },
+    {
+      "epoch": 0.004158669225847729,
+      "grad_norm": 1.0844578742980957,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.0863,
+      "step": 13
+    },
+    {
+      "epoch": 0.004478566858605247,
+      "grad_norm": 1.1643762588500977,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.7271,
+      "step": 14
+    },
+    {
+      "epoch": 0.0047984644913627635,
+      "grad_norm": 2.4205377101898193,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.1354,
+      "step": 15
+    },
+    {
+      "epoch": 0.0047984644913627635,
+      "eval_loss": 0.5474783778190613,
+      "eval_runtime": 245.5626,
+      "eval_samples_per_second": 5.363,
+      "eval_steps_per_second": 2.684,
+      "step": 15
+    },
+    {
+      "epoch": 0.005118362124120281,
+      "grad_norm": 1.2331067323684692,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 2.0977,
+      "step": 16
+    },
+    {
+      "epoch": 0.005438259756877799,
+      "grad_norm": 1.1161530017852783,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.5612,
+      "step": 17
+    },
+    {
+      "epoch": 0.005758157389635317,
+      "grad_norm": 1.1801851987838745,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 2.2411,
+      "step": 18
+    },
+    {
+      "epoch": 0.006078055022392835,
+      "grad_norm": 1.5758033990859985,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.1463,
+      "step": 19
+    },
+    {
+      "epoch": 0.006397952655150352,
+      "grad_norm": 4.761112689971924,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 2.25,
+      "step": 20
+    },
+    {
+      "epoch": 0.006397952655150352,
+      "eval_loss": 0.5206258296966553,
+      "eval_runtime": 246.1719,
+      "eval_samples_per_second": 5.35,
+      "eval_steps_per_second": 2.677,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4331643391180800.0,
+  "total_flos": 8578352598220800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null