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:c284367fa4427d3c2ca6dc912ca03075acf1ae681b3e8856e40c64b2f23534d6
+oid sha256:60ef27f6a93931f26d99c56faeff9bb6b958134c4dbfbd81eb30b29f0337d1b7
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f87c0627a5f1c9621e2fbc16823e92a4fb2cdf9fa6c3b595d186bdbc0d95e80
+oid sha256:9314638698c4af844ad8a76f67b3a566a1b5d229d405db9d0a7fc45b4a745539
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df8c6fc31ac199e6c243ffe062905a7862052130540b4f8afa1589a29fe97b6d
+oid sha256:bd53346fd5a654d3e32df025210c49ec943f00f49e54c4d7d1fb40b5ae52d930
 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": 11.074006080627441,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00017630543152958184,
+  "best_metric": 11.060052871704102,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0003526108630591637,
   "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": 154.159,
       "eval_steps_per_second": 77.08,
       "step": 10
+    },
+    {
+      "epoch": 0.00019393597468254003,
+      "grad_norm": 1.1925216913223267,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 44.2824,
+      "step": 11
+    },
+    {
+      "epoch": 0.00021156651783549822,
+      "grad_norm": 1.1967883110046387,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 44.287,
+      "step": 12
+    },
+    {
+      "epoch": 0.0002291970609884564,
+      "grad_norm": 1.1843236684799194,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 44.2499,
+      "step": 13
+    },
+    {
+      "epoch": 0.0002468276041414146,
+      "grad_norm": 1.2098557949066162,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 44.2345,
+      "step": 14
+    },
+    {
+      "epoch": 0.0002644581472943728,
+      "grad_norm": 1.283496379852295,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 44.2413,
+      "step": 15
+    },
+    {
+      "epoch": 0.0002644581472943728,
+      "eval_loss": 11.064728736877441,
+      "eval_runtime": 155.3564,
+      "eval_samples_per_second": 153.724,
+      "eval_steps_per_second": 76.862,
+      "step": 15
+    },
+    {
+      "epoch": 0.000282088690447331,
+      "grad_norm": 1.2000702619552612,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 44.2442,
+      "step": 16
+    },
+    {
+      "epoch": 0.0002997192336002891,
+      "grad_norm": 1.1320544481277466,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 44.2807,
+      "step": 17
+    },
+    {
+      "epoch": 0.0003173497767532473,
+      "grad_norm": 1.0614330768585205,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 44.2788,
+      "step": 18
+    },
+    {
+      "epoch": 0.0003349803199062055,
+      "grad_norm": 1.0958316326141357,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 44.2804,
+      "step": 19
+    },
+    {
+      "epoch": 0.0003526108630591637,
+      "grad_norm": 1.0989373922348022,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 44.2736,
+      "step": 20
+    },
+    {
+      "epoch": 0.0003526108630591637,
+      "eval_loss": 11.060052871704102,
+      "eval_runtime": 156.1013,
+      "eval_samples_per_second": 152.99,
+      "eval_steps_per_second": 76.495,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 14942208000.0,
+  "total_flos": 29884416000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null