Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a15e5eaa389f35c742b03db5ae488cbe36cba8b6d914659296be3b064f912e3
+oid sha256:257e824b7f312932cbaba48c576ec017f3e34949732e0318db181ec0e9033eb8
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d7e3079d90c08ffb06f53fad7348305b3a53c02bbd085e85ce018ed7de59243
+oid sha256:7fd25a243c5c10da794b54c5569edc75ecd66df85121d20f5d6a2b56abb689a5
 size 6332154

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8883664b798546ba4913ab36eb0b6436e78a544cfca23db87c61fbdd0eea8b6c
+oid sha256:a5a23cf47757f164f2cd7e8f37453fda648bb8645ab8bab7ab72c15aa0a34a05
 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": 9.088578224182129,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.07339449541284404,
+  "best_metric": 9.052206039428711,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.14678899082568808,
   "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": 292.984,
       "eval_steps_per_second": 73.883,
       "step": 10
+    },
+    {
+      "epoch": 0.08807339449541285,
+      "grad_norm": 601.4331665039062,
+      "learning_rate": 0.000163742398974869,
+      "loss": 29.1306,
+      "step": 12
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "grad_norm": 624.2897338867188,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 31.9976,
+      "step": 15
+    },
+    {
+      "epoch": 0.11009174311926606,
+      "eval_loss": 9.066068649291992,
+      "eval_runtime": 0.4276,
+      "eval_samples_per_second": 268.935,
+      "eval_steps_per_second": 67.818,
+      "step": 15
+    },
+    {
+      "epoch": 0.13211009174311927,
+      "grad_norm": 745.8872680664062,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 33.8825,
+      "step": 18
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "eval_loss": 9.052206039428711,
+      "eval_runtime": 0.4042,
+      "eval_samples_per_second": 284.524,
+      "eval_steps_per_second": 71.75,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 52506579173376.0,
+  "total_flos": 97193029533696.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null