Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:645687d45d6dc5000b638c86423ff6ed6bcaa256387b3cd0bd06ee5e813cf2f2
+oid sha256:83d0c9ce0c6afe04c77180fdd345b1316462c6e245d465762d95ae854153c366
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a38759f11ec79f95659038a38444edeeb01461c73f2de81e11e0833d6d9eb8b2
+oid sha256:1aa877516b9793af2eb9b9e40e379e9024c09c729109f4f927b8068db1b2f295
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e88443e707b134fbe02dd168a8c5638ccf4f80e4b6e036f10f9bbf5fa83765a
+oid sha256:8af2d47f608bf34555a9cf7a41fe4f5bfbe24b6c35606703851cc155c6e61d5f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0496538877487183,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0007082403767838804,
+  "best_metric": 0.9824416041374207,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0014164807535677608,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 7.867,
       "eval_steps_per_second": 3.933,
       "step": 10
+    },
+    {
+      "epoch": 0.0008498884521406565,
+      "grad_norm": 0.4180082380771637,
+      "learning_rate": 0.000163742398974869,
+      "loss": 0.9673,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010623605651758207,
+      "grad_norm": 0.5116729736328125,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.9065,
+      "step": 15
+    },
+    {
+      "epoch": 0.0010623605651758207,
+      "eval_loss": 1.0059510469436646,
+      "eval_runtime": 751.9391,
+      "eval_samples_per_second": 7.908,
+      "eval_steps_per_second": 3.954,
+      "step": 15
+    },
+    {
+      "epoch": 0.0012748326782109848,
+      "grad_norm": 0.5504330992698669,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 0.8902,
+      "step": 18
+    },
+    {
+      "epoch": 0.0014164807535677608,
+      "eval_loss": 0.9824416041374207,
+      "eval_runtime": 754.227,
+      "eval_samples_per_second": 7.884,
+      "eval_steps_per_second": 3.942,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3470744113643520.0,
+  "total_flos": 6941488227287040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null