Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9992574d02015a02dc2537e2e9f8c8e29c0c8e80b592a2b22c90235beee72df0
+oid sha256:210b7a6a64211e7edd3b04aa17a525d18542b95008c192bbad5d5ed63e9c42c9
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ceaa1872897d10e22671b263541a0959c87f1cc749601d6e18028b7ab24ddad
+oid sha256:f2ddb0852fd923e39b240ef4b109befc5f5a927052df3c4eb5f50cc48de4df56
 size 75471860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bea86a4dfa27c1d04b20acac5ca8be51cf18d7d3aeb4f7aec3c3a9c75f1757e7
+oid sha256:c7d40c1b6fca5153a06f6840eb50f3344d1f474ef4114a82f55c44040f9c13d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87bb1aa192c7f9c0516bbbf45e738ece50573944baeb2415a4a135a1ac346045
+oid sha256:5220d0af0ff98b2d6e04334f1c29842da7230747bf3383cf1f883a4d2eb6d4f2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.6573541164398193,
-  "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.0011061946902654867,
+  "best_metric": 2.5786044597625732,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.00165929203539823,
   "eval_steps": 50,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 31.108,
       "eval_steps_per_second": 7.777,
       "step": 100
+    },
+    {
+      "epoch": 0.0012168141592920354,
+      "grad_norm": 3.749699115753174,
+      "learning_rate": 5.095e-06,
+      "loss": 2.7189,
+      "step": 110
+    },
+    {
+      "epoch": 0.001327433628318584,
+      "grad_norm": 7.6131815910339355,
+      "learning_rate": 4.5288888888888885e-06,
+      "loss": 2.6359,
+      "step": 120
+    },
+    {
+      "epoch": 0.0014380530973451327,
+      "grad_norm": 4.680475234985352,
+      "learning_rate": 3.9627777777777784e-06,
+      "loss": 2.5536,
+      "step": 130
+    },
+    {
+      "epoch": 0.0015486725663716814,
+      "grad_norm": 4.758671283721924,
+      "learning_rate": 3.3966666666666666e-06,
+      "loss": 2.5424,
+      "step": 140
+    },
+    {
+      "epoch": 0.00165929203539823,
+      "grad_norm": 8.027587890625,
+      "learning_rate": 2.830555555555556e-06,
+      "loss": 2.7179,
+      "step": 150
+    },
+    {
+      "epoch": 0.00165929203539823,
+      "eval_loss": 2.5786044597625732,
+      "eval_runtime": 914.8862,
+      "eval_samples_per_second": 31.204,
+      "eval_steps_per_second": 7.801,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4966576658841600.0,
+  "total_flos": 7449864988262400.0,
   "train_batch_size": 6,
   "trial_name": null,
   "trial_params": null