Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c856ea4b6c832f7ba54f25c496aebd99325bcaee82f2533345e8dc51e31c566
+oid sha256:d0edec704cc3cf137d263612f6266fe677925538f687788ba70b7e7750efef03
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc9dbc868fa21da0847482f80e57537543678a772b6afdef9a98560a1db0f972
+oid sha256:dea4c217f861c02acc2c40e6855119ce4e2517d29df450e2f5f3600b638e3ef9
 size 320194002

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4250bda87bda5caa38b4998394739682e0ccba207a0ccf23e007353626c1b46d
+oid sha256:0b489ab217670b0897760f1cb7b62a84212cde2f16f26fd39cc6bcc4ddcee88a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
+oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.2935600280761719,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0002796655200380345,
+  "best_metric": 1.2142143249511719,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.000559331040076069,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,43 @@
       "eval_samples_per_second": 5.546,
       "eval_steps_per_second": 2.773,
       "step": 10
+    },
+    {
+      "epoch": 0.00033559862404564144,
+      "grad_norm": 0.6358433365821838,
+      "learning_rate": 0.000163742398974869,
+      "loss": 1.2783,
+      "step": 12
+    },
+    {
+      "epoch": 0.00041949828005705174,
+      "grad_norm": 0.5158620476722717,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 1.2647,
+      "step": 15
+    },
+    {
+      "epoch": 0.00041949828005705174,
+      "eval_loss": 1.245732307434082,
+      "eval_runtime": 2713.0572,
+      "eval_samples_per_second": 5.549,
+      "eval_steps_per_second": 2.775,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005033979360684622,
+      "grad_norm": 0.6106576919555664,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 1.1921,
+      "step": 18
+    },
+    {
+      "epoch": 0.000559331040076069,
+      "eval_loss": 1.2142143249511719,
+      "eval_runtime": 2710.3078,
+      "eval_samples_per_second": 5.555,
+      "eval_steps_per_second": 2.778,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3388107349032960.0,
+  "total_flos": 6693577933455360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null