Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:343a485276cec8294a6a73fc290d9e025ddcc4caaa675127b115bae9632c3c80
+oid sha256:7f7366d7d30d7276a3abccc09a3f0242e9600720ba0147bfdceaddb30751dfc7
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3439376efa7bec5a60751f21c11fe2918162f1a5f7f9209c23d4f6b23b9fcfae
+oid sha256:23facc7b8621615f5b564401b6cfafbe3c41508dfc444fe47e190da8d061256f
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
+oid sha256:a8d0ca5f94c74be21f7e258f478e4f1bcf339ab697a95d852a0fd9b800d39d6b
 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": 0.8738162517547607,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0021831677764436196,
+  "best_metric": 0.8042117357254028,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.004366335552887239,
   "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": 4.99,
       "eval_steps_per_second": 2.496,
       "step": 10
+    },
+    {
+      "epoch": 0.002401484554087982,
+      "grad_norm": 0.6236119270324707,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 3.4257,
+      "step": 11
+    },
+    {
+      "epoch": 0.0026198013317323436,
+      "grad_norm": 0.5396324396133423,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.8704,
+      "step": 12
+    },
+    {
+      "epoch": 0.0028381181093767058,
+      "grad_norm": 0.6194649338722229,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 2.6484,
+      "step": 13
+    },
+    {
+      "epoch": 0.0030564348870210675,
+      "grad_norm": 0.5360026955604553,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 3.3599,
+      "step": 14
+    },
+    {
+      "epoch": 0.0032747516646654297,
+      "grad_norm": 0.6152706146240234,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.6307,
+      "step": 15
+    },
+    {
+      "epoch": 0.0032747516646654297,
+      "eval_loss": 0.8243345618247986,
+      "eval_runtime": 387.5187,
+      "eval_samples_per_second": 4.978,
+      "eval_steps_per_second": 2.49,
+      "step": 15
+    },
+    {
+      "epoch": 0.0034930684423097914,
+      "grad_norm": 0.6975443959236145,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.3202,
+      "step": 16
+    },
+    {
+      "epoch": 0.0037113852199541536,
+      "grad_norm": 0.7146017551422119,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 3.0276,
+      "step": 17
+    },
+    {
+      "epoch": 0.003929701997598516,
+      "grad_norm": 0.781614363193512,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 3.4729,
+      "step": 18
+    },
+    {
+      "epoch": 0.0041480187752428775,
+      "grad_norm": 0.7023319602012634,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.08,
+      "step": 19
+    },
+    {
+      "epoch": 0.004366335552887239,
+      "grad_norm": 0.6755356788635254,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.0765,
+      "step": 20
+    },
+    {
+      "epoch": 0.004366335552887239,
+      "eval_loss": 0.8042117357254028,
+      "eval_runtime": 386.4152,
+      "eval_samples_per_second": 4.992,
+      "eval_steps_per_second": 2.497,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3257498484080640.0,
+  "total_flos": 6514996968161280.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null