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:c0c7267cf5d1b699642501461cff9534570d56f1c25b27578b32bbbf959567fa
+oid sha256:ee64cd270bf1082cd954c27fe5633ac166a9ae0f5ec1ce82f471cbb771a19764
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3decac44d46175dfa642ed3b211a3475dcdfbc938159336b8aea24a3d6bd2a90
+oid sha256:ceecc3d5add95e9d4fd1d7770a5ae6d8f6584171ed2786595df018010e217426
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79866ae3485779da1ea36aaf60045f59bbedbe5e94919f509609008f6614b13a
+oid sha256:d21070d0393054c9f55bc3d50b00bd0b11944af1376ec32be3f92ddf66173fca
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2d4cddd37346296738e3c4439ab61fa91587765d69d5019cd363e28124a5192
+oid sha256:2b5503856dead21bafa7c388515430c4fb05a63663322b79ed69bf598ce60794
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7f20265c8933d28ac7b44fa879c2b30286644ceaae2f32c7615278f9a95a7ae
+oid sha256:395a648687b80df3648809f80e30aebc9cefc043041f32c66db2b5fe00bfb889
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbfee8a9b54dfcc7637666787a1b861529746dafb5b36fba925ffecc1457c980
+oid sha256:bc8643c52ab1322de3f9dae787505af36060f1669eb519a54ad2e1eac7f4d95c
 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": 1.0936610698699951,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.312256049960968,
+  "best_metric": 0.9218409657478333,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.624512099921936,
   "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": 14.412,
       "eval_steps_per_second": 3.747,
       "step": 25
+    },
+    {
+      "epoch": 0.32474629195940674,
+      "grad_norm": 1.5570573806762695,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.1832,
+      "step": 26
+    },
+    {
+      "epoch": 0.3372365339578454,
+      "grad_norm": 1.3983771800994873,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.044,
+      "step": 27
+    },
+    {
+      "epoch": 0.34972677595628415,
+      "grad_norm": 1.282069444656372,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.0703,
+      "step": 28
+    },
+    {
+      "epoch": 0.3622170179547229,
+      "grad_norm": 1.3308384418487549,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.0034,
+      "step": 29
+    },
+    {
+      "epoch": 0.3747072599531616,
+      "grad_norm": 1.311693787574768,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.9713,
+      "step": 30
+    },
+    {
+      "epoch": 0.3871975019516003,
+      "grad_norm": 1.3370124101638794,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9209,
+      "step": 31
+    },
+    {
+      "epoch": 0.39968774395003903,
+      "grad_norm": 1.313528299331665,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.8721,
+      "step": 32
+    },
+    {
+      "epoch": 0.41217798594847777,
+      "grad_norm": 1.3581171035766602,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.8682,
+      "step": 33
+    },
+    {
+      "epoch": 0.4246682279469165,
+      "grad_norm": 1.265177845954895,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8279,
+      "step": 34
+    },
+    {
+      "epoch": 0.4371584699453552,
+      "grad_norm": 1.4047905206680298,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.9059,
+      "step": 35
+    },
+    {
+      "epoch": 0.4496487119437939,
+      "grad_norm": 1.6240432262420654,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.9126,
+      "step": 36
+    },
+    {
+      "epoch": 0.46213895394223264,
+      "grad_norm": 1.7853037118911743,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.8382,
+      "step": 37
+    },
+    {
+      "epoch": 0.4746291959406714,
+      "grad_norm": 1.212027907371521,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.047,
+      "step": 38
+    },
+    {
+      "epoch": 0.48711943793911006,
+      "grad_norm": 1.175856113433838,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9885,
+      "step": 39
+    },
+    {
+      "epoch": 0.4996096799375488,
+      "grad_norm": 1.1697721481323242,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.9376,
+      "step": 40
+    },
+    {
+      "epoch": 0.5120999219359875,
+      "grad_norm": 1.0764572620391846,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.921,
+      "step": 41
+    },
+    {
+      "epoch": 0.5245901639344263,
+      "grad_norm": 1.1662276983261108,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.8766,
+      "step": 42
+    },
+    {
+      "epoch": 0.537080405932865,
+      "grad_norm": 1.0305904150009155,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.823,
+      "step": 43
+    },
+    {
+      "epoch": 0.5495706479313037,
+      "grad_norm": 1.1411957740783691,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.8284,
+      "step": 44
+    },
+    {
+      "epoch": 0.5620608899297423,
+      "grad_norm": 1.1754179000854492,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.8136,
+      "step": 45
+    },
+    {
+      "epoch": 0.5745511319281811,
+      "grad_norm": 1.0738892555236816,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.7073,
+      "step": 46
+    },
+    {
+      "epoch": 0.5870413739266198,
+      "grad_norm": 1.1244994401931763,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.7384,
+      "step": 47
+    },
+    {
+      "epoch": 0.5995316159250585,
+      "grad_norm": 1.3134185075759888,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.8129,
+      "step": 48
+    },
+    {
+      "epoch": 0.6120218579234973,
+      "grad_norm": 1.5741225481033325,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.7561,
+      "step": 49
+    },
+    {
+      "epoch": 0.624512099921936,
+      "grad_norm": 1.8192217350006104,
+      "learning_rate": 1e-05,
+      "loss": 0.8404,
+      "step": 50
+    },
+    {
+      "epoch": 0.624512099921936,
+      "eval_loss": 0.9218409657478333,
+      "eval_runtime": 3.4665,
+      "eval_samples_per_second": 14.424,
+      "eval_steps_per_second": 3.75,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null