Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3053443f29950e51ad823d1ee91bc3bb3062ffe3484865726f5eb5fc5f69c72f
+oid sha256:8e15be16ca9a8b7e10973501ae21366c6ea679cb13dcbebdbc0c5cce6b138bd8
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d401b94408de98052df4304b8e1eaa8b92823ce4a1a7a797ad8eafc2db32124
+oid sha256:d5e1fc06fd6e7ae4d7d978213db8b9b94d9313116ef2d1740129d25af8e9644f
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f49cc70e43698962a43ee5f1e5ea93c76dbe4ce826f81dfbb789efeb8adbd88f
+oid sha256:0e0a757ffe6c9fcd3b1bf3120b902f92c3aa5d6542e79c5ea824ded072ba2b1f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e210a21e913c947efb876777b0844134f18a0e5dd3ba1625ccf5a578844563e
+oid sha256:2cd62d399a2450f21c7bec0f65f92f467b6df40bae3ff61b19e25062ffc80260
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2856680154800415,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.06983240223463687,
+  "best_metric": 1.2346261739730835,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.10474860335195531,
   "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": 11.684,
       "eval_steps_per_second": 2.926,
       "step": 100
+    },
+    {
+      "epoch": 0.07681564245810056,
+      "grad_norm": 0.5764887928962708,
+      "learning_rate": 0.00020761968215422217,
+      "loss": 0.9639,
+      "step": 110
+    },
+    {
+      "epoch": 0.08379888268156424,
+      "grad_norm": 0.45929816365242004,
+      "learning_rate": 0.00020429981382519356,
+      "loss": 0.9454,
+      "step": 120
+    },
+    {
+      "epoch": 0.09078212290502793,
+      "grad_norm": 0.5289813280105591,
+      "learning_rate": 0.00020051321843297219,
+      "loss": 0.8689,
+      "step": 130
+    },
+    {
+      "epoch": 0.09776536312849161,
+      "grad_norm": 0.5550933480262756,
+      "learning_rate": 0.0001962783438896818,
+      "loss": 0.8495,
+      "step": 140
+    },
+    {
+      "epoch": 0.10474860335195531,
+      "grad_norm": 1.3829443454742432,
+      "learning_rate": 0.0001916158220784091,
+      "loss": 2.1619,
+      "step": 150
+    },
+    {
+      "epoch": 0.10474860335195531,
+      "eval_loss": 1.2346261739730835,
+      "eval_runtime": 51.8194,
+      "eval_samples_per_second": 11.637,
+      "eval_steps_per_second": 2.914,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -115,7 +158,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 1
+        "early_stopping_patience_counter": 0
       }
     },
     "TrainerControl": {
@@ -129,7 +172,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.817116957835264e+16,
+  "total_flos": 4.212345230327808e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null