Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7df253e5fedce791752aa6b49bfd7c0dbd81095fe092289e64b48430eb5a5e8
+oid sha256:b6e24aabddf40843a162afb813ceac2af6f75d160d89a331c309fcc411148f32
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ed1e586e68b4e71427ce2db391ff7cfee3faa4bcb848ebb73a3c208b38a0f55
-size 325339796
+oid sha256:413f8f0dba780c2795c8c5f425624b1677480e26c5854f7d3ae1159de63a58a7
+size 325340244

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3905c330d3db07e1ad9a2babbeb1b45bd3d7e496270c18ee0deb04dc17f2c73
+oid sha256:0f209ebe6b7ad32497f4bcecad7acd9f307fe601e3a12883130313e5fe53bf40
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b6a94df7ac3a40cdfc424c44e0aa20bf2a24b7a45dca0fa2ca12977070a7cde
+oid sha256:8fce8e677bb7386f80f19f2b52163f28d827949784afc431a846b58d7c09959b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.25602078437805176,
-  "best_model_checkpoint": "miner_id_24/checkpoint-250",
-  "epoch": 0.22172949002217296,
+  "best_metric": 0.23859120905399323,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.2660753880266075,
   "eval_steps": 50,
-  "global_step": 250,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -230,6 +230,49 @@
       "eval_samples_per_second": 12.329,
       "eval_steps_per_second": 3.089,
       "step": 250
+    },
+    {
+      "epoch": 0.23059866962305986,
+      "grad_norm": 0.9151793718338013,
+      "learning_rate": 0.00011100511055839919,
+      "loss": 0.2358,
+      "step": 260
+    },
+    {
+      "epoch": 0.2394678492239468,
+      "grad_norm": 4.036000728607178,
+      "learning_rate": 0.00010400739941860137,
+      "loss": 0.2748,
+      "step": 270
+    },
+    {
+      "epoch": 0.24833702882483372,
+      "grad_norm": 0.6628141403198242,
+      "learning_rate": 9.699260058139868e-05,
+      "loss": 0.2109,
+      "step": 280
+    },
+    {
+      "epoch": 0.2572062084257206,
+      "grad_norm": 0.4428306818008423,
+      "learning_rate": 8.999488944160085e-05,
+      "loss": 0.1508,
+      "step": 290
+    },
+    {
+      "epoch": 0.2660753880266075,
+      "grad_norm": 1.0661782026290894,
+      "learning_rate": 8.30483581444735e-05,
+      "loss": 0.1516,
+      "step": 300
+    },
+    {
+      "epoch": 0.2660753880266075,
+      "eval_loss": 0.23859120905399323,
+      "eval_runtime": 38.2194,
+      "eval_samples_per_second": 12.428,
+      "eval_steps_per_second": 3.114,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -258,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.257264513620378e+16,
+  "total_flos": 7.515427619576218e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null