Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06bd13775091bac21a9849e08147f2039ba9d7368b30f2e3a871b2e913b2e7e7
+oid sha256:db40573913cba1370a979b39b69a849f5ccf4378c1b901cafc3a8687c04d9afe
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ab2d8f7ba4b8c74715576947a48f7a28d05b39ed8939f8096d971d7b83dc28
+oid sha256:5d3ebd163439a33a6350cc811ad8e1100efe97bfa961828709ffee15269433c5
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2bddb21602b550d34cde3f5dfc325262caec1e60327e7a97f2594093cb1bbdc
+oid sha256:e40381e776ffe295c644a558c211a4101a275cfc17038dc7033c2deb88c39a48
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0edbce2371902c55bd5d26338517a28c0e78cd080304c9eab37c2e2ecb64e257
+oid sha256:13a666fb4c30ca91debde2a9cbee964f97f52d5f0d49ec619de44b308bd3a414
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354e19d2c13fbeb59894a99ca14355abc2b096a266edc88803abd697aefdb7e5
+oid sha256:81ef6216ca30c518377e79090e1eea81677e608cffab50d0061db6128fed9620
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f595a6b155501a84675c3b07e4f62f91bb29e05b947119334c454ae644f3822
+oid sha256:8e5ec9fb22108aea189fe543413642a5029739685464b59fcc1095fcd9349d3d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.9117090702056885,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.027987685418415897,
+  "best_metric": 2.8374502658843994,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.055975370836831795,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 45.439,
       "eval_steps_per_second": 11.814,
       "step": 25
+    },
+    {
+      "epoch": 0.029107192835152534,
+      "grad_norm": 1.6625885963439941,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.7708,
+      "step": 26
+    },
+    {
+      "epoch": 0.030226700251889168,
+      "grad_norm": 1.8415322303771973,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.8309,
+      "step": 27
+    },
+    {
+      "epoch": 0.0313462076686258,
+      "grad_norm": 1.7591997385025024,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.9998,
+      "step": 28
+    },
+    {
+      "epoch": 0.03246571508536244,
+      "grad_norm": 1.868369221687317,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.9777,
+      "step": 29
+    },
+    {
+      "epoch": 0.033585222502099076,
+      "grad_norm": 1.7001196146011353,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.9426,
+      "step": 30
+    },
+    {
+      "epoch": 0.03470472991883571,
+      "grad_norm": 1.6648975610733032,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.961,
+      "step": 31
+    },
+    {
+      "epoch": 0.03582423733557235,
+      "grad_norm": 1.6528427600860596,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.9583,
+      "step": 32
+    },
+    {
+      "epoch": 0.036943744752308987,
+      "grad_norm": 1.6447185277938843,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.9051,
+      "step": 33
+    },
+    {
+      "epoch": 0.03806325216904562,
+      "grad_norm": 1.9467555284500122,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.89,
+      "step": 34
+    },
+    {
+      "epoch": 0.039182759585782254,
+      "grad_norm": 2.022052764892578,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.9331,
+      "step": 35
+    },
+    {
+      "epoch": 0.04030226700251889,
+      "grad_norm": 2.3610732555389404,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.8858,
+      "step": 36
+    },
+    {
+      "epoch": 0.04142177441925553,
+      "grad_norm": 2.525616407394409,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.7781,
+      "step": 37
+    },
+    {
+      "epoch": 0.042541281835992165,
+      "grad_norm": 1.4379932880401611,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.8147,
+      "step": 38
+    },
+    {
+      "epoch": 0.0436607892527288,
+      "grad_norm": 1.3367565870285034,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.7604,
+      "step": 39
+    },
+    {
+      "epoch": 0.04478029666946544,
+      "grad_norm": 1.3029029369354248,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.8715,
+      "step": 40
+    },
+    {
+      "epoch": 0.04589980408620207,
+      "grad_norm": 1.3365355730056763,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.9184,
+      "step": 41
+    },
+    {
+      "epoch": 0.047019311502938706,
+      "grad_norm": 1.3175362348556519,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.8455,
+      "step": 42
+    },
+    {
+      "epoch": 0.04813881891967534,
+      "grad_norm": 1.5100023746490479,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.8966,
+      "step": 43
+    },
+    {
+      "epoch": 0.04925832633641198,
+      "grad_norm": 1.5187021493911743,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.9616,
+      "step": 44
+    },
+    {
+      "epoch": 0.05037783375314862,
+      "grad_norm": 1.5786397457122803,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.9971,
+      "step": 45
+    },
+    {
+      "epoch": 0.051497341169885254,
+      "grad_norm": 1.468232274055481,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.9048,
+      "step": 46
+    },
+    {
+      "epoch": 0.052616848586621884,
+      "grad_norm": 1.6899412870407104,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.0045,
+      "step": 47
+    },
+    {
+      "epoch": 0.05373635600335852,
+      "grad_norm": 1.7791612148284912,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.874,
+      "step": 48
+    },
+    {
+      "epoch": 0.05485586342009516,
+      "grad_norm": 1.8675801753997803,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.8556,
+      "step": 49
+    },
+    {
+      "epoch": 0.055975370836831795,
+      "grad_norm": 2.566417694091797,
+      "learning_rate": 1e-05,
+      "loss": 2.7583,
+      "step": 50
+    },
+    {
+      "epoch": 0.055975370836831795,
+      "eval_loss": 2.8374502658843994,
+      "eval_runtime": 1.0997,
+      "eval_samples_per_second": 45.467,
+      "eval_steps_per_second": 11.821,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.129122235790131e+16,
+  "total_flos": 1.625316696124293e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null