Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9a556dc38c8f85adcfe659f1d0a508b0917de94c7eab0aacc9363a84d22ababd
+oid sha256:83c9f43fbe4007e346cf69cec66b72240d50121f410a962d5685213437ea4e1c
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d133150a86c43a4041c455a90de1ae83ac2478142ceee66c56daafc2e8f3eda5
+oid sha256:d024d548f2b8c6ed9a7558cdd0fef616f413c07057e40a3ec1bac4c948cf0a87
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6d539fe4d67d4d8fda2e72f75d140391a0aaf6f7ce2131b7b9f8701adbd03b4
+oid sha256:c9aa6c608a81787329a84d496a75a6af4537d84b5394af8e31b80a1e586e6921
 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": 0.22240450978279114,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0016909744240118367,
+  "best_metric": 0.12360001355409622,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0033819488480236735,
   "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": 7.321,
       "eval_steps_per_second": 3.661,
       "step": 10
+    },
+    {
+      "epoch": 0.0018600718664130206,
+      "grad_norm": 1.8090850114822388,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 0.8868,
+      "step": 11
+    },
+    {
+      "epoch": 0.002029169308814204,
+      "grad_norm": 1.3949517011642456,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 0.7729,
+      "step": 12
+    },
+    {
+      "epoch": 0.002198266751215388,
+      "grad_norm": 1.1241109371185303,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.5519,
+      "step": 13
+    },
+    {
+      "epoch": 0.0023673641936165714,
+      "grad_norm": 0.6692907810211182,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 0.4599,
+      "step": 14
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "grad_norm": 0.9926350712776184,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 0.5148,
+      "step": 15
+    },
+    {
+      "epoch": 0.0025364616360177552,
+      "eval_loss": 0.13447795808315277,
+      "eval_runtime": 350.1072,
+      "eval_samples_per_second": 7.112,
+      "eval_steps_per_second": 3.556,
+      "step": 15
+    },
+    {
+      "epoch": 0.002705559078418939,
+      "grad_norm": 1.3928656578063965,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.5929,
+      "step": 16
+    },
+    {
+      "epoch": 0.0028746565208201224,
+      "grad_norm": 1.48099684715271,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 0.6033,
+      "step": 17
+    },
+    {
+      "epoch": 0.0030437539632213063,
+      "grad_norm": 0.833182156085968,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 0.5041,
+      "step": 18
+    },
+    {
+      "epoch": 0.00321285140562249,
+      "grad_norm": 0.5916072130203247,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.5098,
+      "step": 19
+    },
+    {
+      "epoch": 0.0033819488480236735,
+      "grad_norm": 0.5035240650177002,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.4717,
+      "step": 20
+    },
+    {
+      "epoch": 0.0033819488480236735,
+      "eval_loss": 0.12360001355409622,
+      "eval_runtime": 334.5636,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.721,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1628749242040320.0,
+  "total_flos": 3298217215131648.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null