Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79ef9c768288875ba42105c9b7e33c6c74b287d5bc89681f1e65a465e8b2f071
+oid sha256:50e78a0422f480faab99c58675f93e887f23f11718409fb42b343a3f90a032ed
 size 159712

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0416923b5ba8eb5712edf4cb6581a7627d06051cf03619e0acd1ba949bf26c2d
+oid sha256:0d4a8e09ca4c9c14e71f908d3c3c4ee2bbf676ccb4bd200eca027e6f329959e1
 size 336202

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5288ed9323916daf49e9e619b5ce81ab40c19e01021e3ee0c12210ac8bab7de
+oid sha256:4542ee77b862586921f712605c9da4a157f7c6fb74687d0b6cef8d69e7a87363
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 10.82991886138916,
-  "best_model_checkpoint": "miner_id_24/checkpoint-20",
-  "epoch": 0.0010803948843302227,
+  "best_metric": 10.827816009521484,
+  "best_model_checkpoint": "miner_id_24/checkpoint-30",
+  "epoch": 0.0016205923264953342,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 192.54,
       "eval_steps_per_second": 96.282,
       "step": 20
+    },
+    {
+      "epoch": 0.0011344146285467338,
+      "grad_norm": 0.14477704465389252,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 10.8313,
+      "step": 21
+    },
+    {
+      "epoch": 0.0012964738611962673,
+      "grad_norm": 0.14507289230823517,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 10.8301,
+      "step": 24
+    },
+    {
+      "epoch": 0.0013504936054127784,
+      "eval_loss": 10.828169822692871,
+      "eval_runtime": 43.1769,
+      "eval_samples_per_second": 180.536,
+      "eval_steps_per_second": 90.28,
+      "step": 25
+    },
+    {
+      "epoch": 0.0014585330938458006,
+      "grad_norm": 0.13749462366104126,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 10.8264,
+      "step": 27
+    },
+    {
+      "epoch": 0.0016205923264953342,
+      "grad_norm": 0.15239441394805908,
+      "learning_rate": 0.0,
+      "loss": 10.826,
+      "step": 30
+    },
+    {
+      "epoch": 0.0016205923264953342,
+      "eval_loss": 10.827816009521484,
+      "eval_runtime": 40.5608,
+      "eval_samples_per_second": 192.181,
+      "eval_steps_per_second": 96.103,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -112,12 +156,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3382881288192.0,
+  "total_flos": 5074321932288.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null