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:d54c91590edf3b0927fb37c5390a89c2a0284ad20c18ed597b05e2eee89691b1
+oid sha256:143606272550ae056deaf751956899595619e4e754594e3c728faccc1a08db7f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:435d63c575689fdc9a0626dee4eac34e3f960b42ea56edb4cb2e1fcce02e7baa
+oid sha256:7ba9bad2a2e67cb14a6e3d1ab16b0608b728275a3c2edd29097d72d8d3252ad4
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0ee6fa147caf7f99e7c2c07afe4bdc3a92f25c8f50bb6fb7bcba6d34d70baa1
+oid sha256:7c62b0861877dcf1835f21a847b4f621aceb0e5a29ff0411f940e031cbe3ccc0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f88ae2ab0acf932b003fec6399494b16a0e951294aaf1d971b132a5e0ff644b6
+oid sha256:aec4f833cafad92101025ba04d07a12ef45e359710881ba3a74082c3b400620d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.803920328617096,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.32555615843733043,
+  "best_metric": 0.7168570756912231,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.6511123168746609,
   "eval_steps": 150,
-  "global_step": 150,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -128,6 +128,119 @@
       "eval_samples_per_second": 14.438,
       "eval_steps_per_second": 1.821,
       "step": 150
+    },
+    {
+      "epoch": 0.34725990233315246,
+      "grad_norm": 15.815438270568848,
+      "learning_rate": 2.9576011832620583e-05,
+      "loss": 3.6763,
+      "step": 160
+    },
+    {
+      "epoch": 0.3689636462289745,
+      "grad_norm": 17.322349548339844,
+      "learning_rate": 2.9495873291870436e-05,
+      "loss": 3.2852,
+      "step": 170
+    },
+    {
+      "epoch": 0.3906673901247965,
+      "grad_norm": 16.479698181152344,
+      "learning_rate": 2.940893033074948e-05,
+      "loss": 3.0177,
+      "step": 180
+    },
+    {
+      "epoch": 0.41237113402061853,
+      "grad_norm": 20.874675750732422,
+      "learning_rate": 2.9315223760628224e-05,
+      "loss": 2.676,
+      "step": 190
+    },
+    {
+      "epoch": 0.43407487791644056,
+      "grad_norm": 29.774669647216797,
+      "learning_rate": 2.9214797567742036e-05,
+      "loss": 3.227,
+      "step": 200
+    },
+    {
+      "epoch": 0.45577862181226264,
+      "grad_norm": 14.984698295593262,
+      "learning_rate": 2.9107698892543862e-05,
+      "loss": 3.4,
+      "step": 210
+    },
+    {
+      "epoch": 0.47748236570808467,
+      "grad_norm": 18.93448829650879,
+      "learning_rate": 2.8993978007576263e-05,
+      "loss": 2.9846,
+      "step": 220
+    },
+    {
+      "epoch": 0.4991861096039067,
+      "grad_norm": 17.96265411376953,
+      "learning_rate": 2.8873688293873336e-05,
+      "loss": 3.0037,
+      "step": 230
+    },
+    {
+      "epoch": 0.5208898534997287,
+      "grad_norm": 23.578723907470703,
+      "learning_rate": 2.874688621590339e-05,
+      "loss": 2.7363,
+      "step": 240
+    },
+    {
+      "epoch": 0.5425935973955507,
+      "grad_norm": 39.76424026489258,
+      "learning_rate": 2.861363129506436e-05,
+      "loss": 3.1817,
+      "step": 250
+    },
+    {
+      "epoch": 0.5642973412913728,
+      "grad_norm": 20.42775535583496,
+      "learning_rate": 2.847398608174417e-05,
+      "loss": 3.2541,
+      "step": 260
+    },
+    {
+      "epoch": 0.5860010851871947,
+      "grad_norm": 16.566482543945312,
+      "learning_rate": 2.832801612595937e-05,
+      "loss": 2.8651,
+      "step": 270
+    },
+    {
+      "epoch": 0.6077048290830168,
+      "grad_norm": 16.73906707763672,
+      "learning_rate": 2.8175789946585697e-05,
+      "loss": 2.8237,
+      "step": 280
+    },
+    {
+      "epoch": 0.6294085729788389,
+      "grad_norm": 23.292736053466797,
+      "learning_rate": 2.801737899919502e-05,
+      "loss": 3.0393,
+      "step": 290
+    },
+    {
+      "epoch": 0.6511123168746609,
+      "grad_norm": 38.29425048828125,
+      "learning_rate": 2.7852857642513838e-05,
+      "loss": 2.7109,
+      "step": 300
+    },
+    {
+      "epoch": 0.6511123168746609,
+      "eval_loss": 0.7168570756912231,
+      "eval_runtime": 53.8613,
+      "eval_samples_per_second": 14.426,
+      "eval_steps_per_second": 1.819,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -156,7 +269,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.103203743137792e+17,
+  "total_flos": 4.206407486275584e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null