Training in progress, step 250, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5f88a9fa30dd7505f503970b2abf2fd6ac48f3a588c5e6da642021a6524766a
+oid sha256:b727edaef991a3a15cc32eab3c7047ead733ece64ad7db72666300fc6b70eae4
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a49e2b3c24625bdce5451b55df19b0b5ae04803c93166233c400b404ef7e856a
+oid sha256:9d8e7b35bc70805daae2984e8c89e70106ef48b8780f2b0f5c51579210ff1a63
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36b0297810eacea031ac0de5e0025036897e50a710949862b7604ca0173e490d
+oid sha256:3ea2bf0a34221e8bebf26496bafc8f3fe6a6ef5d7f7e43883d9c09d47debb643
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b846236f686f34a315088700cd866bd66ffc165610b7eec245275ac6103428
+oid sha256:0b764a7feea336c9409f04ca3df4d8b4349bea019384446d21739ad3565001bd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2688231468200684,
-  "best_model_checkpoint": "miner_id_24/checkpoint-200",
-  "epoch": 0.0033675135963361453,
+  "best_metric": 1.2357275485992432,
+  "best_model_checkpoint": "miner_id_24/checkpoint-250",
+  "epoch": 0.004209391995420182,
   "eval_steps": 50,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -187,6 +187,49 @@
       "eval_samples_per_second": 14.813,
       "eval_steps_per_second": 3.703,
       "step": 200
+    },
+    {
+      "epoch": 0.0035358892761529525,
+      "grad_norm": 1.4451912641525269,
+      "learning_rate": 0.00015390571270643128,
+      "loss": 1.0993,
+      "step": 210
+    },
+    {
+      "epoch": 0.0037042649559697596,
+      "grad_norm": 1.5819648504257202,
+      "learning_rate": 0.0001470829054955026,
+      "loss": 1.113,
+      "step": 220
+    },
+    {
+      "epoch": 0.003872640635786567,
+      "grad_norm": 2.1583080291748047,
+      "learning_rate": 0.00014006481839811937,
+      "loss": 1.2436,
+      "step": 230
+    },
+    {
+      "epoch": 0.004041016315603374,
+      "grad_norm": 2.5022051334381104,
+      "learning_rate": 0.00013288564282916442,
+      "loss": 1.3693,
+      "step": 240
+    },
+    {
+      "epoch": 0.004209391995420182,
+      "grad_norm": 4.059680461883545,
+      "learning_rate": 0.00012558035501036158,
+      "loss": 1.63,
+      "step": 250
+    },
+    {
+      "epoch": 0.004209391995420182,
+      "eval_loss": 1.2357275485992432,
+      "eval_runtime": 1686.4416,
+      "eval_samples_per_second": 14.828,
+      "eval_steps_per_second": 3.707,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -215,7 +258,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.109999479455744e+16,
+  "total_flos": 5.116529964220416e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null