Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0af59e3a7c47c26a6838d25064d1b26639bc53ffba87f2ce29b9cd80cea3c52b
+oid sha256:0b949dfb5355b24f1b8d268ed1be96fa7b43730be769c40dcd0c411ac727d0e5
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3994a3a867ddf7708ab1850c0f4596bf4aa0e20096c8f4b84222b27c46c4514
+oid sha256:3d5c7cfa093439ab704de326580465b59681fe3e26a34e4ac402b78ce6215c69
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec134605e1e781fc705a3279e09b0cbaee66f077da601816e59f2b3169ff7952
+oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:09a4d5a6254db6f62a1af88344fd48b32c05cdf78870a0f236ce09b217eefbf3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.473760187625885,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.46511627906976744,
+  "best_metric": 0.3455663323402405,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.9302325581395349,
   "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": 13.951,
       "eval_steps_per_second": 7.751,
       "step": 10
+    },
+    {
+      "epoch": 0.5116279069767442,
+      "grad_norm": 17.59303092956543,
+      "learning_rate": 0.00019659258262890683,
+      "loss": 2.5846,
+      "step": 11
+    },
+    {
+      "epoch": 0.5581395348837209,
+      "grad_norm": 16.672748565673828,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 1.8067,
+      "step": 12
+    },
+    {
+      "epoch": 0.6046511627906976,
+      "grad_norm": 16.875839233398438,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 1.2409,
+      "step": 13
+    },
+    {
+      "epoch": 0.6511627906976745,
+      "grad_norm": 19.30131721496582,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.5314,
+      "step": 14
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "grad_norm": 15.786406517028809,
+      "learning_rate": 0.00012588190451025207,
+      "loss": 1.229,
+      "step": 15
+    },
+    {
+      "epoch": 0.6976744186046512,
+      "eval_loss": 0.45458799600601196,
+      "eval_runtime": 0.6321,
+      "eval_samples_per_second": 14.239,
+      "eval_steps_per_second": 7.911,
+      "step": 15
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 16.67571449279785,
+      "learning_rate": 0.0001,
+      "loss": 1.517,
+      "step": 16
+    },
+    {
+      "epoch": 0.7906976744186046,
+      "grad_norm": 21.225812911987305,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.9907,
+      "step": 17
+    },
+    {
+      "epoch": 0.8372093023255814,
+      "grad_norm": 11.570257186889648,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.2278,
+      "step": 18
+    },
+    {
+      "epoch": 0.8837209302325582,
+      "grad_norm": 11.162030220031738,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.1246,
+      "step": 19
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 16.523731231689453,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.9212,
+      "step": 20
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "eval_loss": 0.3455663323402405,
+      "eval_runtime": 0.6454,
+      "eval_samples_per_second": 13.944,
+      "eval_steps_per_second": 7.747,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 298572369100800.0,
+  "total_flos": 597144738201600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null