Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:199b133bd3a8329640d5ebf42d4583f90ceead3efc1eab9f6ef0d9d4f88dd0a6
+oid sha256:5945f06c3216ae06581911ec7cec068649a020e45af1930ec95e0cbd6be00e9f
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cba8fa49b8487ed1c818ac296c237a49960f5a7ac893d9db2da958b787efc5fe
+oid sha256:5fe03004dbc39f8b110a600cb4ddb64125e8e668b7553d6cf9c11c5d3ceb10ad
 size 64219860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:565c117b0554bcadbb2962d5778f478da838b047d26cc08e6b3663c916f71fed
+oid sha256:e4b82d94a3f3ba4658ccb6aa5c8b6ba7ae6394ee1ce2647f24e42e072d6200c3
 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": 0.5423365831375122,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.01942690626517727,
+  "best_metric": 0.37839406728744507,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.03885381253035454,
   "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": 1.259,
       "eval_steps_per_second": 0.633,
       "step": 10
+    },
+    {
+      "epoch": 0.021369596891694997,
+      "grad_norm": 1.6877245903015137,
+      "learning_rate": 0.00019781476007338058,
+      "loss": 2.6654,
+      "step": 11
+    },
+    {
+      "epoch": 0.023312287518212724,
+      "grad_norm": 1.4581409692764282,
+      "learning_rate": 0.0001913545457642601,
+      "loss": 2.2367,
+      "step": 12
+    },
+    {
+      "epoch": 0.02525497814473045,
+      "grad_norm": 1.5118839740753174,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 1.9142,
+      "step": 13
+    },
+    {
+      "epoch": 0.027197668771248178,
+      "grad_norm": 1.1800850629806519,
+      "learning_rate": 0.00016691306063588583,
+      "loss": 1.2975,
+      "step": 14
+    },
+    {
+      "epoch": 0.029140359397765905,
+      "grad_norm": 1.4285818338394165,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.2237,
+      "step": 15
+    },
+    {
+      "epoch": 0.029140359397765905,
+      "eval_loss": 0.4246327877044678,
+      "eval_runtime": 171.5923,
+      "eval_samples_per_second": 1.265,
+      "eval_steps_per_second": 0.635,
+      "step": 15
+    },
+    {
+      "epoch": 0.03108305002428363,
+      "grad_norm": 1.5692723989486694,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.7107,
+      "step": 16
+    },
+    {
+      "epoch": 0.03302574065080136,
+      "grad_norm": 1.3358412981033325,
+      "learning_rate": 0.00011045284632676536,
+      "loss": 1.194,
+      "step": 17
+    },
+    {
+      "epoch": 0.034968431277319086,
+      "grad_norm": 1.3867946863174438,
+      "learning_rate": 8.954715367323468e-05,
+      "loss": 1.6543,
+      "step": 18
+    },
+    {
+      "epoch": 0.036911121903836816,
+      "grad_norm": 1.57295823097229,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.9915,
+      "step": 19
+    },
+    {
+      "epoch": 0.03885381253035454,
+      "grad_norm": 3.227126359939575,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.4304,
+      "step": 20
+    },
+    {
+      "epoch": 0.03885381253035454,
+      "eval_loss": 0.37839406728744507,
+      "eval_runtime": 169.5612,
+      "eval_samples_per_second": 1.28,
+      "eval_steps_per_second": 0.643,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -129,7 +215,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3166224305356800.0,
+  "total_flos": 6332448610713600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null