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:d659de3cdc83f437a2be750ae14b7180e7a63124e6934944608875f7a4707ea0
+oid sha256:6b397565e4e9a9f74d6794199b902737ca99ad41545d079f441e78470f9908b4
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc0648028c33a96e4a57e48986cb4be411f47636178c07cfd41addf5cc4f4831
+oid sha256:66dc0b8bca72ec33ca5d6706c243f4f586da1f69e21a8ecd0ab649666f9296bb
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed24157843733a720e9b3d1b006fa11ac517dab21a9d332b9aa678dbbf520076
+oid sha256:53857b31065290226097899a29c43817f42b59cc1033072766ec46b6e8e362ce
 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": 4.582190990447998,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0009886796183696672,
+  "best_metric": 4.2419514656066895,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0019773592367393344,
   "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": 3.772,
       "eval_steps_per_second": 1.887,
       "step": 10
+    },
+    {
+      "epoch": 0.001087547580206634,
+      "grad_norm": 8.830248832702637,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.7394,
+      "step": 11
+    },
+    {
+      "epoch": 0.0011864155420436007,
+      "grad_norm": 9.814061164855957,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 4.3392,
+      "step": 12
+    },
+    {
+      "epoch": 0.0012852835038805676,
+      "grad_norm": 9.087082862854004,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.4741,
+      "step": 13
+    },
+    {
+      "epoch": 0.0013841514657175343,
+      "grad_norm": 8.418217658996582,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 4.065,
+      "step": 14
+    },
+    {
+      "epoch": 0.001483019427554501,
+      "grad_norm": 9.908651351928711,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 4.3679,
+      "step": 15
+    },
+    {
+      "epoch": 0.001483019427554501,
+      "eval_loss": 4.397404193878174,
+      "eval_runtime": 1118.2098,
+      "eval_samples_per_second": 3.809,
+      "eval_steps_per_second": 1.905,
+      "step": 15
+    },
+    {
+      "epoch": 0.0015818873893914678,
+      "grad_norm": 9.443998336791992,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.4487,
+      "step": 16
+    },
+    {
+      "epoch": 0.0016807553512284345,
+      "grad_norm": 12.183076858520508,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 4.3741,
+      "step": 17
+    },
+    {
+      "epoch": 0.0017796233130654012,
+      "grad_norm": 12.255166053771973,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 3.8147,
+      "step": 18
+    },
+    {
+      "epoch": 0.001878491274902368,
+      "grad_norm": 8.746517181396484,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 3.8452,
+      "step": 19
+    },
+    {
+      "epoch": 0.0019773592367393344,
+      "grad_norm": 7.476744174957275,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.9029,
+      "step": 20
+    },
+    {
+      "epoch": 0.0019773592367393344,
+      "eval_loss": 4.2419514656066895,
+      "eval_runtime": 1136.2772,
+      "eval_samples_per_second": 3.748,
+      "eval_steps_per_second": 1.875,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1911091416268800.0,
+  "total_flos": 3822182832537600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null