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:d8ea25614d9527aee2416f569ad9d4af8765984ce7ed545b91b787ac4d54ef32
+oid sha256:66ae35d54eadc05b0cc2e4c63799d4aa3ee7f09b5011558c4ee362c661bc370f
 size 598799664

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a3ddc0bec23116b66d34935a53165b8645854534678c15f5cb6da531ec0c470
+oid sha256:6cb89a57283f79f07cb71f0e9f0c78af5f17fdd954d58987850117d5895e6165
 size 167987322

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c691bc6b98e7712e66fc2e35e98847903daf6e08dee56de3671f1e83638f9fa5
+oid sha256:35065c6e466e3b1a6e927aae2bc007780adcfae5e57fb17b718b3e1e775e7d48
 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": 2.4826228618621826,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.011296243998870376,
+  "best_metric": 2.3386573791503906,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.022592487997740753,
   "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": 36.302,
       "eval_steps_per_second": 9.1,
       "step": 10
+    },
+    {
+      "epoch": 0.013555492798644452,
+      "grad_norm": 2.089750051498413,
+      "learning_rate": 0.000163742398974869,
+      "loss": 7.7554,
+      "step": 12
+    },
+    {
+      "epoch": 0.016944365998305563,
+      "grad_norm": 2.362656831741333,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 8.1899,
+      "step": 15
+    },
+    {
+      "epoch": 0.016944365998305563,
+      "eval_loss": 2.393854856491089,
+      "eval_runtime": 20.626,
+      "eval_samples_per_second": 36.168,
+      "eval_steps_per_second": 9.066,
+      "step": 15
+    },
+    {
+      "epoch": 0.020333239197966677,
+      "grad_norm": 2.424359083175659,
+      "learning_rate": 9.372094804706867e-05,
+      "loss": 8.0077,
+      "step": 18
+    },
+    {
+      "epoch": 0.022592487997740753,
+      "eval_loss": 2.3386573791503906,
+      "eval_runtime": 20.5662,
+      "eval_samples_per_second": 36.273,
+      "eval_steps_per_second": 9.093,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2818763107860480.0,
+  "total_flos": 5440868324474880.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null