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:e90b987879ddf480be0ca4703eefea597215d15c71ab1ef1fb817ce4ed32ec57
+oid sha256:07d192aa1c9ce20fd264be177399627c549841ba4a3dcbe785cfdc6ff6e4acf4
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2af4a2686e254f4f87cd7bd27743c9d282b16715e9d9a2349888409f80d297a
-size 170920084
+oid sha256:3a08f49a47f3ea1d7622dfb86c37c67c48b24de609d9cf949a91fafec68666c5
+size 170920532

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a355a58987eda105cf552ad712e56925deafbd21c52f01db6bb79781434e2f1
+oid sha256:616d5591fe2815fb845a002baa0bbc69990e73ea586e4a98cd405180dd111c49
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e080d0e7c071615c66cdfbd19fb773bb51f3a695898c5afa82d7150c8b34389
+oid sha256:35792e2ed51bf6bc8a2a5bf1bcfa90fe1bca1ed12b3ff3e83b15d68253c4d18f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.9399939775466919,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 1.2765957446808511,
+  "best_metric": 0.7150752544403076,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 2.5531914893617023,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,135 @@
       "eval_samples_per_second": 13.215,
       "eval_steps_per_second": 3.337,
       "step": 150
+    },
+    {
+      "epoch": 1.3617021276595744,
+      "grad_norm": 1.4046274423599243,
+      "learning_rate": 0.00011956517382403321,
+      "loss": 0.7635,
+      "step": 160
+    },
+    {
+      "epoch": 1.4468085106382977,
+      "grad_norm": 1.1550798416137695,
+      "learning_rate": 0.00011051357095705101,
+      "loss": 0.6612,
+      "step": 170
+    },
+    {
+      "epoch": 1.5319148936170213,
+      "grad_norm": 1.0277212858200073,
+      "learning_rate": 0.00010137383111821266,
+      "loss": 0.9006,
+      "step": 180
+    },
+    {
+      "epoch": 1.6170212765957448,
+      "grad_norm": 0.9155287742614746,
+      "learning_rate": 9.22225742301153e-05,
+      "loss": 0.7741,
+      "step": 190
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 1.3166751861572266,
+      "learning_rate": 8.313651676464923e-05,
+      "loss": 0.6244,
+      "step": 200
+    },
+    {
+      "epoch": 1.702127659574468,
+      "eval_loss": 0.7949697375297546,
+      "eval_runtime": 14.9637,
+      "eval_samples_per_second": 13.232,
+      "eval_steps_per_second": 3.341,
+      "step": 200
+    },
+    {
+      "epoch": 1.7872340425531914,
+      "grad_norm": 0.9204571843147278,
+      "learning_rate": 7.419182861636218e-05,
+      "loss": 0.8257,
+      "step": 210
+    },
+    {
+      "epoch": 1.872340425531915,
+      "grad_norm": 1.011165976524353,
+      "learning_rate": 6.546349455786926e-05,
+      "loss": 0.6789,
+      "step": 220
+    },
+    {
+      "epoch": 1.9574468085106385,
+      "grad_norm": 1.240622878074646,
+      "learning_rate": 5.702468563033306e-05,
+      "loss": 0.5821,
+      "step": 230
+    },
+    {
+      "epoch": 2.0425531914893615,
+      "grad_norm": 0.803183913230896,
+      "learning_rate": 4.894614573874877e-05,
+      "loss": 0.8176,
+      "step": 240
+    },
+    {
+      "epoch": 2.127659574468085,
+      "grad_norm": 0.8154023289680481,
+      "learning_rate": 4.129559859430573e-05,
+      "loss": 0.4854,
+      "step": 250
+    },
+    {
+      "epoch": 2.127659574468085,
+      "eval_loss": 0.7357346415519714,
+      "eval_runtime": 14.9479,
+      "eval_samples_per_second": 13.246,
+      "eval_steps_per_second": 3.345,
+      "step": 250
+    },
+    {
+      "epoch": 2.2127659574468086,
+      "grad_norm": 1.3029338121414185,
+      "learning_rate": 3.413717997552376e-05,
+      "loss": 0.3565,
+      "step": 260
+    },
+    {
+      "epoch": 2.297872340425532,
+      "grad_norm": 1.1356505155563354,
+      "learning_rate": 2.7530900067611577e-05,
+      "loss": 0.6265,
+      "step": 270
+    },
+    {
+      "epoch": 2.382978723404255,
+      "grad_norm": 1.0218287706375122,
+      "learning_rate": 2.1532140387343735e-05,
+      "loss": 0.43,
+      "step": 280
+    },
+    {
+      "epoch": 2.4680851063829787,
+      "grad_norm": 0.9909137487411499,
+      "learning_rate": 1.619118951081594e-05,
+      "loss": 0.3348,
+      "step": 290
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "grad_norm": 1.1617368459701538,
+      "learning_rate": 1.1552821496149135e-05,
+      "loss": 0.6773,
+      "step": 300
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "eval_loss": 0.7150752544403076,
+      "eval_runtime": 14.938,
+      "eval_samples_per_second": 13.255,
+      "eval_steps_per_second": 3.347,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -172,7 +301,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.2543503351349248e+17,
+  "total_flos": 4.5087006702698496e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null