Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5739d00792ce9fdb7b25909758525bc9b0db351ba6dab459b99a86c8ad333b
+oid sha256:b272dfc1af283de869b53c47122a97573473439e25cc864ec36879d322170e08
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd51d5bb1de558726a97ed4547c50d374da9930a2648d5fa6c98300c63a71583
+oid sha256:b73594681fd5a9a6fafa87226094e191d45bc1e3ff2e7c04dc2326a203b25f97
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda37c45fd02147ff3efaf37c7052da7f0fd772a1db6f46f152ce23a00cf8b19
+oid sha256:0b50d6dfd4c67766a87d7126cc5d993e88a1ae9d35d4c78be754e5e87bc7a27f
 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": 2.158656358718872,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004253056884635832,
+  "best_metric": 2.1466376781463623,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.008506113769271665,
   "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": 3.187,
       "eval_steps_per_second": 1.593,
       "step": 10
+    },
+    {
+      "epoch": 0.004678362573099415,
+      "grad_norm": 4.688698768615723,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 8.5195,
+      "step": 11
+    },
+    {
+      "epoch": 0.005103668261562998,
+      "grad_norm": 4.8131794929504395,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 9.5152,
+      "step": 12
+    },
+    {
+      "epoch": 0.005528973950026581,
+      "grad_norm": 4.646464824676514,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 7.5373,
+      "step": 13
+    },
+    {
+      "epoch": 0.005954279638490165,
+      "grad_norm": 5.341791152954102,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 9.2033,
+      "step": 14
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "grad_norm": 4.57265567779541,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 8.2836,
+      "step": 15
+    },
+    {
+      "epoch": 0.006379585326953748,
+      "eval_loss": 2.1536974906921387,
+      "eval_runtime": 312.2097,
+      "eval_samples_per_second": 3.171,
+      "eval_steps_per_second": 1.585,
+      "step": 15
+    },
+    {
+      "epoch": 0.006804891015417331,
+      "grad_norm": 4.516714572906494,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.0979,
+      "step": 16
+    },
+    {
+      "epoch": 0.007230196703880914,
+      "grad_norm": 4.64660120010376,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 8.7766,
+      "step": 17
+    },
+    {
+      "epoch": 0.007655502392344498,
+      "grad_norm": 4.283811569213867,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 8.0383,
+      "step": 18
+    },
+    {
+      "epoch": 0.00808080808080808,
+      "grad_norm": 5.0667643547058105,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 8.5667,
+      "step": 19
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "grad_norm": 4.93750524520874,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 7.8461,
+      "step": 20
+    },
+    {
+      "epoch": 0.008506113769271665,
+      "eval_loss": 2.1466376781463623,
+      "eval_runtime": 308.6858,
+      "eval_samples_per_second": 3.207,
+      "eval_steps_per_second": 1.604,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3373889337950208.0,
+  "total_flos": 6879228909846528.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null