Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c43b89866f55ad0c43daa96608f86bba99067d5f253ac4d3fa11d246101bd4b
+oid sha256:02bbdc360cbb830f85d05e9ac028118b9ca4752aacfbb134aa61809d90f843b5
 size 608282672

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b694daad8dd6a1e76ad5cd92ae5c7aa0bb47c73e661fe8b7c16bfef6971ed8
+oid sha256:9eb94cdfb1ed5e40eb9f4399ccd35e5eebc44a8a00d58c868825d15d571e1829
 size 168149074

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e82278b08455a8f7c8b61ef2099af2970dd8dfd4792846ed0ec0e4a58ddc43f6
+oid sha256:48c9c3cc04dc8dae936a8ffd4ecbcd94617b17b93d527a7200c9ff2943f1f4eb
 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": 0.7650104761123657,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.2691790040376851,
+  "best_metric": 0.7424979209899902,
+  "best_model_checkpoint": "miner_id_24/checkpoint-300",
+  "epoch": 0.5383580080753702,
   "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": 9.858,
       "eval_steps_per_second": 1.239,
       "step": 150
+    },
+    {
+      "epoch": 0.2871242709735307,
+      "grad_norm": 2.056764841079712,
+      "learning_rate": 2.9576011832620583e-05,
+      "loss": 2.7666,
+      "step": 160
+    },
+    {
+      "epoch": 0.3050695379093764,
+      "grad_norm": 2.3999085426330566,
+      "learning_rate": 2.9495873291870436e-05,
+      "loss": 2.8254,
+      "step": 170
+    },
+    {
+      "epoch": 0.32301480484522205,
+      "grad_norm": 2.938490390777588,
+      "learning_rate": 2.940893033074948e-05,
+      "loss": 3.0781,
+      "step": 180
+    },
+    {
+      "epoch": 0.34096007178106774,
+      "grad_norm": 3.2307329177856445,
+      "learning_rate": 2.9315223760628224e-05,
+      "loss": 3.2347,
+      "step": 190
+    },
+    {
+      "epoch": 0.35890533871691344,
+      "grad_norm": 10.07883358001709,
+      "learning_rate": 2.9214797567742036e-05,
+      "loss": 3.3451,
+      "step": 200
+    },
+    {
+      "epoch": 0.3768506056527591,
+      "grad_norm": 2.220188617706299,
+      "learning_rate": 2.9107698892543862e-05,
+      "loss": 2.5911,
+      "step": 210
+    },
+    {
+      "epoch": 0.39479587258860477,
+      "grad_norm": 2.3011841773986816,
+      "learning_rate": 2.8993978007576263e-05,
+      "loss": 2.6557,
+      "step": 220
+    },
+    {
+      "epoch": 0.4127411395244504,
+      "grad_norm": 2.9171500205993652,
+      "learning_rate": 2.8873688293873336e-05,
+      "loss": 2.9965,
+      "step": 230
+    },
+    {
+      "epoch": 0.4306864064602961,
+      "grad_norm": 3.5936508178710938,
+      "learning_rate": 2.874688621590339e-05,
+      "loss": 3.2309,
+      "step": 240
+    },
+    {
+      "epoch": 0.4486316733961418,
+      "grad_norm": 15.465261459350586,
+      "learning_rate": 2.861363129506436e-05,
+      "loss": 3.3962,
+      "step": 250
+    },
+    {
+      "epoch": 0.46657694033198743,
+      "grad_norm": 2.3160524368286133,
+      "learning_rate": 2.847398608174417e-05,
+      "loss": 2.676,
+      "step": 260
+    },
+    {
+      "epoch": 0.4845222072678331,
+      "grad_norm": 2.586505651473999,
+      "learning_rate": 2.832801612595937e-05,
+      "loss": 2.7848,
+      "step": 270
+    },
+    {
+      "epoch": 0.5024674742036788,
+      "grad_norm": 3.1157450675964355,
+      "learning_rate": 2.8175789946585697e-05,
+      "loss": 2.9969,
+      "step": 280
+    },
+    {
+      "epoch": 0.5204127411395244,
+      "grad_norm": 3.554219961166382,
+      "learning_rate": 2.801737899919502e-05,
+      "loss": 3.2118,
+      "step": 290
+    },
+    {
+      "epoch": 0.5383580080753702,
+      "grad_norm": 11.838674545288086,
+      "learning_rate": 2.7852857642513838e-05,
+      "loss": 3.19,
+      "step": 300
+    },
+    {
+      "epoch": 0.5383580080753702,
+      "eval_loss": 0.7424979209899902,
+      "eval_runtime": 95.2404,
+      "eval_samples_per_second": 9.859,
+      "eval_steps_per_second": 1.239,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -156,7 +269,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7762337244617114e+17,
+  "total_flos": 5.555972794535117e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null