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:e923be7303a92401a3063147c7bb1868bfe28ec3ca1762e82acb7d14cec334e7
+oid sha256:f19914fcc03a09be5bb0aa60a215a69a61210290787d1afb11948b062027f8bb
 size 188784440

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35b8aed9eb9d47bb2d4a303949f4fdd95a04f941bd245feba353e0e0e3eb30c9
+oid sha256:02e70b739757098f9c0b2b7f02be609f9870d79e4d9512b614475bd0a419d48d
 size 377730170

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a96107c23e8d36adec1aadf2d8c952c9d0e6aca0e83fb7dda9d70c46276c410
+oid sha256:d10519610009c540670d3642510b46a0f6a5f528db3cc7a9cdbb98825023d8a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9860424995422363,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0017617264919621229,
+  "best_metric": 0.7788602709770203,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0035234529839242457,
   "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": 3.065,
       "eval_steps_per_second": 1.533,
       "step": 10
+    },
+    {
+      "epoch": 0.0021140717903545474,
+      "grad_norm": 1.7132139205932617,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 3.8929,
+      "step": 12
+    },
+    {
+      "epoch": 0.0026425897379431843,
+      "grad_norm": 1.8616305589675903,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.6906,
+      "step": 15
+    },
+    {
+      "epoch": 0.0026425897379431843,
+      "eval_loss": 0.8647217750549316,
+      "eval_runtime": 777.3119,
+      "eval_samples_per_second": 3.076,
+      "eval_steps_per_second": 1.539,
+      "step": 15
+    },
+    {
+      "epoch": 0.0031711076855318212,
+      "grad_norm": 1.8421508073806763,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 3.2375,
+      "step": 18
+    },
+    {
+      "epoch": 0.0035234529839242457,
+      "eval_loss": 0.7788602709770203,
+      "eval_runtime": 781.0425,
+      "eval_samples_per_second": 3.061,
+      "eval_steps_per_second": 1.531,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.14344142569472e+16,
+  "total_flos": 2.28688285138944e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null