Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d06c2ac659590f2d36cd369ebff8c07b04eb9f2accde744fc0fc8e8810a731b
+oid sha256:c428806e093f716af8dd1515923f715ad7e92b69cb2bf0e374dff26a180e72f1
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9984f492729106e7683b02918257faaf478b98e3aca501fcbcf761b19a3b7e0
+oid sha256:fa1fe64a0534828181806f4ef7aeb2b5d327772044f6d8b2d246d8fd7939b16b
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea790a6d7ded2d403b9f6bb0e490729d25eeb947822fcee7d950e6fe6a5a2385
+oid sha256:86d013c907ff188e94dfd0d1e7126019857ca06b44469974d820abeb40345f6f
 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": 3.9925918579101562,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0058326042578011085,
+  "best_metric": 3.7121365070343018,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.011665208515602217,
   "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": 4.534,
       "eval_steps_per_second": 2.273,
       "step": 10
+    },
+    {
+      "epoch": 0.006415864683581219,
+      "grad_norm": 5.318166732788086,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 4.6783,
+      "step": 11
+    },
+    {
+      "epoch": 0.00699912510936133,
+      "grad_norm": 2.3505146503448486,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.8806,
+      "step": 12
+    },
+    {
+      "epoch": 0.00758238553514144,
+      "grad_norm": 3.62709641456604,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 4.1199,
+      "step": 13
+    },
+    {
+      "epoch": 0.008165645960921552,
+      "grad_norm": 3.3935163021087646,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 2.8595,
+      "step": 14
+    },
+    {
+      "epoch": 0.008748906386701663,
+      "grad_norm": 2.9052529335021973,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 2.7348,
+      "step": 15
+    },
+    {
+      "epoch": 0.008748906386701663,
+      "eval_loss": 3.8251967430114746,
+      "eval_runtime": 81.2922,
+      "eval_samples_per_second": 4.441,
+      "eval_steps_per_second": 2.227,
+      "step": 15
+    },
+    {
+      "epoch": 0.009332166812481774,
+      "grad_norm": 4.136341571807861,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 3.9567,
+      "step": 16
+    },
+    {
+      "epoch": 0.009915427238261883,
+      "grad_norm": 3.814793825149536,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 4.6753,
+      "step": 17
+    },
+    {
+      "epoch": 0.010498687664041995,
+      "grad_norm": 2.465329170227051,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 2.6047,
+      "step": 18
+    },
+    {
+      "epoch": 0.011081948089822106,
+      "grad_norm": 2.647146701812744,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 2.8166,
+      "step": 19
+    },
+    {
+      "epoch": 0.011665208515602217,
+      "grad_norm": 2.982029676437378,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 3.3659,
+      "step": 20
+    },
+    {
+      "epoch": 0.011665208515602217,
+      "eval_loss": 3.7121365070343018,
+      "eval_runtime": 80.1379,
+      "eval_samples_per_second": 4.505,
+      "eval_steps_per_second": 2.259,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 38361901301760.0,
+  "total_flos": 76723802603520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null