Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25406734dc72a72c891d2e5780ce663877de541194943f6e8f10b0efc05e824b
+oid sha256:d0ab7abf7803c25269b6fd9d5ee32af7e52822ac46284f7742a44349e86eafcb
 size 25192592

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a711953bef90d69ba37b8652de939f944e03f54532a2d91a83cbf16380a258a
+oid sha256:989afc27af9d2b2c4e25a0d39dcdadbf30bfadaf4caae2749c02b991a7adc209
 size 50445306

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec134605e1e781fc705a3279e09b0cbaee66f077da601816e59f2b3169ff7952
+oid sha256:326b940c26441f9cc805b55861d6ba1368323749e2ade38b0a118c4c7d409c57
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d46ef0f8a7945706ef65ae5e8be31402361869b6b4c8ecb8ef0263696377404
+oid sha256:e2eb657255baf6b1420bbcfab19529abd45c6011f0c415bddb3c278a51f7f142
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.565830945968628,
-  "best_model_checkpoint": "miner_id_24/checkpoint-10",
-  "epoch": 0.004545971133083305,
+  "best_metric": 1.7551437616348267,
+  "best_model_checkpoint": "miner_id_24/checkpoint-20",
+  "epoch": 0.00909194226616661,
   "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": 56.558,
       "eval_steps_per_second": 28.31,
       "step": 10
+    },
+    {
+      "epoch": 0.005455165359699966,
+      "grad_norm": 34.001976013183594,
+      "learning_rate": 8.18711994874345e-05,
+      "loss": 9.7167,
+      "step": 12
+    },
+    {
+      "epoch": 0.006818956699624957,
+      "grad_norm": 35.41960525512695,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 9.2473,
+      "step": 15
+    },
+    {
+      "epoch": 0.006818956699624957,
+      "eval_loss": 2.0683515071868896,
+      "eval_runtime": 16.6989,
+      "eval_samples_per_second": 55.513,
+      "eval_steps_per_second": 27.786,
+      "step": 15
+    },
+    {
+      "epoch": 0.008182748039549948,
+      "grad_norm": 44.34693908691406,
+      "learning_rate": 4.6860474023534335e-05,
+      "loss": 8.1237,
+      "step": 18
+    },
+    {
+      "epoch": 0.00909194226616661,
+      "eval_loss": 1.7551437616348267,
+      "eval_runtime": 16.3435,
+      "eval_samples_per_second": 56.72,
+      "eval_steps_per_second": 28.391,
+      "step": 20
     }
   ],
   "logging_steps": 3,
@@ -80,7 +117,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 177003319787520.0,
+  "total_flos": 354006639575040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null