Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe44c517da3b5bd49d65e70a45d1f2330968467f6c86711c23e261ea94095838
+oid sha256:408d807c4a4e1016af795f390739d62d4ffa53e618d4d8c0e8da349782d714b3
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:255a84c5916c4acc56ccf3b9954409101345bc0fdfc1d6850b4c6fcd56cb3409
+oid sha256:fb5b0f60e3646c23e1d8b76910215f1c36f34cee31982446d57251428b427c0a
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88691174dc7b4d1b5f34720787a5bbfb15ccc6e25d4fae280e7d1bd81b4aa685
+oid sha256:31112f726e67575ead0d56e7de6e437584408f03ff8e9c41cdf27988e74b5b0a
 size 14180

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b2fd30f3b354b607634e22c75b4493073ee958ea49022a57afc742673e42d76
+oid sha256:cb28bb8cf2be6d829bc7d8d43fa28bbbd84fb8993a66e3e97cef2580889f0f5e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.524364948272705,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.00042161893237653943,
+  "best_metric": 1.4387811422348022,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.0008432378647530789,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 14.666,
       "eval_steps_per_second": 3.667,
       "step": 50
+    },
+    {
+      "epoch": 0.0005059427188518473,
+      "grad_norm": 0.6090065240859985,
+      "learning_rate": 0.00020974422527728155,
+      "loss": 1.4874,
+      "step": 60
+    },
+    {
+      "epoch": 0.0005902665053271552,
+      "grad_norm": 0.6349875926971436,
+      "learning_rate": 0.0002089781472178649,
+      "loss": 1.241,
+      "step": 70
+    },
+    {
+      "epoch": 0.0006745902918024631,
+      "grad_norm": 0.7745322585105896,
+      "learning_rate": 0.0002077054980770496,
+      "loss": 1.0923,
+      "step": 80
+    },
+    {
+      "epoch": 0.000758914078277771,
+      "grad_norm": 1.1790937185287476,
+      "learning_rate": 0.00020593247807352348,
+      "loss": 1.1274,
+      "step": 90
+    },
+    {
+      "epoch": 0.0008432378647530789,
+      "grad_norm": 3.3187856674194336,
+      "learning_rate": 0.00020366772518252038,
+      "loss": 2.0574,
+      "step": 100
+    },
+    {
+      "epoch": 0.0008432378647530789,
+      "eval_loss": 1.4387811422348022,
+      "eval_runtime": 3420.3676,
+      "eval_samples_per_second": 14.599,
+      "eval_steps_per_second": 3.65,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -86,7 +129,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.093076926857216e+16,
+  "total_flos": 2.195040657997824e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null