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:cd9021904dd153d1711a5ded245066166b715ecc230cdd68359dd9f2c0a398b1
+oid sha256:774ad79bea2ca844138f99e4dd479e8d8d22f47dba38e30d5478d33cce1ef2a1
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d690d646d429dd1562742c3060ed34fcfe600393255d70f4484d4bd612c86cf
+oid sha256:bfb8ba6c8f0c7a0c5ed02806c8b42773c20042e04b9ddc4efeed4c1c552dfc37
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7274372b653b3b4ec33d7b782ad3407c4974f5657c7e4f46634fe9c7e18974e3
+oid sha256:fb825deb93738339ea8f6f1fa6d043ed4efe540c68e3b76e5d2ea4c67f5c810e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e632471e9faa68e552b5c7075c8b12e58487a8a1f16703abc189d53617256bb8
+oid sha256:7d062f3f62503160ddf877022d1e13af24aa2ff1bff4514618deb7e3d26c9bfc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b61fd13755906a5c9fdc620dd8a2a7156b1d01eff4fc31846788b175a18aeb3
+oid sha256:06f39b7b078c97096bacdf3280b3895a093e779b201e0c02812a9a6cc53d6097
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:533075d83f677c8a18b045353eaba90ebb7dec60cf7d837d98d9739caa8a2e4c
+oid sha256:d90493cf985adc318c3422746bdffd33faa1aa6f9c32a0f12f91c32063f2c935
 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": 0.3292239308357239,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.023859942139640312,
+  "best_metric": 0.2769263684749603,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.047719884279280624,
   "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": 11.419,
       "eval_steps_per_second": 2.969,
       "step": 25
+    },
+    {
+      "epoch": 0.024814339825225924,
+      "grad_norm": 1.6082409620285034,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.3021,
+      "step": 26
+    },
+    {
+      "epoch": 0.025768737510811535,
+      "grad_norm": 1.1714216470718384,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.2882,
+      "step": 27
+    },
+    {
+      "epoch": 0.026723135196397147,
+      "grad_norm": 1.1372226476669312,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.2209,
+      "step": 28
+    },
+    {
+      "epoch": 0.027677532881982762,
+      "grad_norm": 0.9055098295211792,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.1623,
+      "step": 29
+    },
+    {
+      "epoch": 0.028631930567568374,
+      "grad_norm": 0.9483652710914612,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.2163,
+      "step": 30
+    },
+    {
+      "epoch": 0.029586328253153986,
+      "grad_norm": 1.1060841083526611,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.2112,
+      "step": 31
+    },
+    {
+      "epoch": 0.030540725938739598,
+      "grad_norm": 1.0018855333328247,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.188,
+      "step": 32
+    },
+    {
+      "epoch": 0.03149512362432521,
+      "grad_norm": 1.0843490362167358,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.2795,
+      "step": 33
+    },
+    {
+      "epoch": 0.03244952130991082,
+      "grad_norm": 1.3921905755996704,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.2683,
+      "step": 34
+    },
+    {
+      "epoch": 0.03340391899549643,
+      "grad_norm": 1.2948616743087769,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.2528,
+      "step": 35
+    },
+    {
+      "epoch": 0.03435831668108205,
+      "grad_norm": 1.504824161529541,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.2593,
+      "step": 36
+    },
+    {
+      "epoch": 0.035312714366667664,
+      "grad_norm": 1.3747433423995972,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.3509,
+      "step": 37
+    },
+    {
+      "epoch": 0.036267112052253275,
+      "grad_norm": 1.1321784257888794,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.2478,
+      "step": 38
+    },
+    {
+      "epoch": 0.03722150973783889,
+      "grad_norm": 0.8461317420005798,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.1884,
+      "step": 39
+    },
+    {
+      "epoch": 0.0381759074234245,
+      "grad_norm": 0.9209880232810974,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.2451,
+      "step": 40
+    },
+    {
+      "epoch": 0.03913030510901011,
+      "grad_norm": 1.097226619720459,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.1921,
+      "step": 41
+    },
+    {
+      "epoch": 0.04008470279459572,
+      "grad_norm": 0.9732930660247803,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.231,
+      "step": 42
+    },
+    {
+      "epoch": 0.041039100480181334,
+      "grad_norm": 0.8967514038085938,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.2743,
+      "step": 43
+    },
+    {
+      "epoch": 0.041993498165766946,
+      "grad_norm": 1.1284832954406738,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.2349,
+      "step": 44
+    },
+    {
+      "epoch": 0.04294789585135256,
+      "grad_norm": 0.908921480178833,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.1719,
+      "step": 45
+    },
+    {
+      "epoch": 0.04390229353693817,
+      "grad_norm": 1.205191731452942,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.2746,
+      "step": 46
+    },
+    {
+      "epoch": 0.04485669122252379,
+      "grad_norm": 1.016750454902649,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.2213,
+      "step": 47
+    },
+    {
+      "epoch": 0.0458110889081094,
+      "grad_norm": 0.8877540826797485,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.2197,
+      "step": 48
+    },
+    {
+      "epoch": 0.04676548659369501,
+      "grad_norm": 1.3043239116668701,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3115,
+      "step": 49
+    },
+    {
+      "epoch": 0.047719884279280624,
+      "grad_norm": 1.060339331626892,
+      "learning_rate": 1e-05,
+      "loss": 0.2079,
+      "step": 50
+    },
+    {
+      "epoch": 0.047719884279280624,
+      "eval_loss": 0.2769263684749603,
+      "eval_runtime": 4.3858,
+      "eval_samples_per_second": 11.4,
+      "eval_steps_per_second": 2.964,
+      "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": 1,
   "trial_name": null,
   "trial_params": null