Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c94825170a2092eb886ce2ce537e81e385f4c8ab29c742662f317b2284300fe
+oid sha256:0c35b9ac6d0d8971f3757c009211f5509139451e2c9a3488f654f1ae247545e1
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2df7438766f689b5ea7fa46c29ec326623cc7f2ed4d7f3fd68e21da1dc1d8230
+oid sha256:e353f7ba27daa25438aedd003dfa890a5d30cbff7742ec67855885b758d810e4
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee47716e7a07b0cb24ec46c4b00c4f94d0357ac526ff10a3c87247b4d0f80aed
+oid sha256:824529825332a2c7d7729b711c474655fc634345060d3fcc137b224627e0839c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.348448395729065,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.00046078702423739745,
+  "best_metric": 1.2183318138122559,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.0009215740484747949,
   "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": 4.835,
       "eval_steps_per_second": 2.417,
       "step": 10
+    },
+    {
+      "epoch": 0.000552944429084877,
+      "grad_norm": 0.7286670804023743,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 5.7504,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006911805363560963,
+      "grad_norm": 0.8415332436561584,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 5.1408,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006911805363560963,
+      "eval_loss": 1.2483679056167603,
+      "eval_runtime": 1884.6621,
+      "eval_samples_per_second": 4.849,
+      "eval_steps_per_second": 2.424,
+      "step": 15
+    },
+    {
+      "epoch": 0.0008294166436273154,
+      "grad_norm": 1.1995240449905396,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.1321,
+      "step": 18
+    },
+    {
+      "epoch": 0.0009215740484747949,
+      "eval_loss": 1.2183318138122559,
+      "eval_runtime": 1883.2865,
+      "eval_samples_per_second": 4.852,
+      "eval_steps_per_second": 2.426,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7617395954810880.0,
+  "total_flos": 1.412392166621184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null