Training in progress, step 203, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad666b86b139114843e6387e24af26157b938f210b5a90a0dbd7dfc69288645b
+oid sha256:808c4f782273009bc7d5e123764f8173007ba1f183c7c31c2f68850ccdddbcba
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83760bdb6e06b4f72fc799a47fae8075e9ef8eaa08f01a1a7080fef1d2770585
+oid sha256:1a01986773b4b8ceab6052d090c3081d1e961e06bbf9fa0803428990272b5a1a
 size 170920084

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2077fbebb3b57119eb881a10a206c01b69c507aed3d8aa947064d01b97b8ccc1
+oid sha256:de5239eff1f2d8ff451112658f26d1b5c61b81da50d6460962c3cb9ebe1a6793
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad9d713402818babdb8f091baee35ed4ccf44ceb7da5916ccb017adc10bc53d3
+oid sha256:0a1bd27e7159fdb46bc339fa4287a931a87599457f6b0651c1f3f5ef3ac6ecd2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.007178535684943199,
   "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 2.2222222222222223,
+  "epoch": 3.0074074074074075,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 203,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 13.368,
       "eval_steps_per_second": 3.401,
       "step": 150
+    },
+    {
+      "epoch": 2.3703703703703702,
+      "grad_norm": 0.1319075971841812,
+      "learning_rate": 2.3511937499075508e-05,
+      "loss": 0.0143,
+      "step": 160
+    },
+    {
+      "epoch": 2.5185185185185186,
+      "grad_norm": 0.2327166497707367,
+      "learning_rate": 1.4083642978043277e-05,
+      "loss": 0.0191,
+      "step": 170
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.19548346102237701,
+      "learning_rate": 6.9267914241362585e-06,
+      "loss": 0.0226,
+      "step": 180
+    },
+    {
+      "epoch": 2.814814814814815,
+      "grad_norm": 0.1185711920261383,
+      "learning_rate": 2.230594539204489e-06,
+      "loss": 0.0134,
+      "step": 190
+    },
+    {
+      "epoch": 2.962962962962963,
+      "grad_norm": 0.09321712702512741,
+      "learning_rate": 1.192096287513711e-07,
+      "loss": 0.0152,
+      "step": 200
+    },
+    {
+      "epoch": 2.962962962962963,
+      "eval_loss": 0.006627695634961128,
+      "eval_runtime": 8.5391,
+      "eval_samples_per_second": 13.35,
+      "eval_steps_per_second": 3.396,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -167,12 +210,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.1456277793773978e+17,
+  "total_flos": 2.90017796878762e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null