Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c7bde99a4b9ba2297f2c029e2b5b825318de6b0cab41d35be51706f86d3dc6b
+oid sha256:0b94119a569fd4e73635adbadf4a908812696655be08abac20484594c5f5a09e
 size 619632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9d230040489e267d8d057396ba8f62641c78eb141ad67541689730116aec476
+oid sha256:8beff5a1e0c6a1d48e4969a3b799ad3ca7354fe92ba8d84593078de4dfd1a5cd
 size 1389562

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95e62f01f54cc1bcb71f99a9ace341b312f01e9067a466200f2a1689e16123af
+oid sha256:5d28e5f5aa78cef16e62cc6537d3b81b1ea74dc330b0053f2dd2ab2d360377f3
 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": 11.92726993560791,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.0009479122233281199,
+  "best_metric": 11.918572425842285,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0018958244466562397,
   "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": 51.228,
       "eval_steps_per_second": 25.614,
       "step": 10
+    },
+    {
+      "epoch": 0.0011374946679937438,
+      "grad_norm": 0.15941640734672546,
+      "learning_rate": 0.000163742398974869,
+      "loss": 11.9275,
+      "step": 12
+    },
+    {
+      "epoch": 0.0014218683349921798,
+      "grad_norm": 0.2011900395154953,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 11.9244,
+      "step": 15
+    },
+    {
+      "epoch": 0.0014218683349921798,
+      "eval_loss": 11.922494888305664,
+      "eval_runtime": 86.3844,
+      "eval_samples_per_second": 51.421,
+      "eval_steps_per_second": 25.711,
+      "step": 15
+    },
+    {
+      "epoch": 0.0017062420019906157,
+      "grad_norm": 0.200108602643013,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 11.9242,
+      "step": 18
+    },
+    {
+      "epoch": 0.0018958244466562397,
+      "eval_loss": 11.918572425842285,
+      "eval_runtime": 86.7951,
+      "eval_samples_per_second": 51.178,
+      "eval_steps_per_second": 25.589,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2729454206976.0,
+  "total_flos": 5458908413952.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null