Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f60d5ea24b334326b8bbdcbb98a49e17010269da1575885d3da1693eed37768
+oid sha256:c869cfbb0be6f682dedcd663dd515338f3e718734e31f76ecf92e5a1cd5dcf4b
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d241dfb8c42c0233788403e8a008365fea46d9b9cbe3e47f59f9a0cf91d1628d
+oid sha256:4d5a5dcd206e467a75906cbc5936da5833f7a91717c164db16644b1ccc7b4166
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67181d8ac020ecdb06f9d2150c624ed4555b4e57a855dfc38684112421673c06
+oid sha256:7f6124624006fedec2b8d1806e4464d2fd4f9358f20465c6cb91d88a2ce29817
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d8c8f9e5e9e3d4cced3f8609a32ba012d2c6265550a8d76ac818a0fa4013fd8
+oid sha256:14afbb21d918c14a8c120f42f3adbd41f2af58895749043210d8b477e99abaed
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b726040d99e33eaf6daad6979d296e4cd914e0a4676f4bd5f583add6381c9a
+oid sha256:54ea5c6f87b88604fb65d153fec47c7ab2de7940d7f36671910a6596c0c2d1b1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4fc72f464c5de4db05c8f623645edcd74c78e8d72ec4a624074a540144f49bd6
+oid sha256:6b78c0f361570d90545ed7a538bde80f4261ab2d6b7cb67952f7cae37f679168
 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": 0.07700011134147644,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.33444816053511706,
+  "best_metric": 0.06487244367599487,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6688963210702341,
   "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": 14.183,
       "eval_steps_per_second": 3.688,
       "step": 25
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.22771090269088745,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0283,
+      "step": 26
+    },
+    {
+      "epoch": 0.3612040133779264,
+      "grad_norm": 0.2608717083930969,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0373,
+      "step": 27
+    },
+    {
+      "epoch": 0.3745819397993311,
+      "grad_norm": 0.2930333912372589,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0429,
+      "step": 28
+    },
+    {
+      "epoch": 0.3879598662207358,
+      "grad_norm": 0.30178168416023254,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0445,
+      "step": 29
+    },
+    {
+      "epoch": 0.4013377926421405,
+      "grad_norm": 0.30688875913619995,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0455,
+      "step": 30
+    },
+    {
+      "epoch": 0.41471571906354515,
+      "grad_norm": 0.5287408828735352,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0754,
+      "step": 31
+    },
+    {
+      "epoch": 0.4280936454849498,
+      "grad_norm": 0.37477612495422363,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0662,
+      "step": 32
+    },
+    {
+      "epoch": 0.4414715719063545,
+      "grad_norm": 0.5867549777030945,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0705,
+      "step": 33
+    },
+    {
+      "epoch": 0.45484949832775917,
+      "grad_norm": 0.6077295541763306,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0764,
+      "step": 34
+    },
+    {
+      "epoch": 0.4682274247491639,
+      "grad_norm": 0.658654510974884,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0878,
+      "step": 35
+    },
+    {
+      "epoch": 0.4816053511705686,
+      "grad_norm": 1.0412871837615967,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1088,
+      "step": 36
+    },
+    {
+      "epoch": 0.49498327759197325,
+      "grad_norm": 0.7272098660469055,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.1308,
+      "step": 37
+    },
+    {
+      "epoch": 0.5083612040133779,
+      "grad_norm": 0.2913189232349396,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0425,
+      "step": 38
+    },
+    {
+      "epoch": 0.5217391304347826,
+      "grad_norm": 0.26089587807655334,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.039,
+      "step": 39
+    },
+    {
+      "epoch": 0.5351170568561873,
+      "grad_norm": 0.33181023597717285,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0471,
+      "step": 40
+    },
+    {
+      "epoch": 0.5484949832775919,
+      "grad_norm": 0.2511487603187561,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0398,
+      "step": 41
+    },
+    {
+      "epoch": 0.5618729096989966,
+      "grad_norm": 0.31910496950149536,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0458,
+      "step": 42
+    },
+    {
+      "epoch": 0.5752508361204013,
+      "grad_norm": 0.3598118722438812,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0537,
+      "step": 43
+    },
+    {
+      "epoch": 0.5886287625418061,
+      "grad_norm": 0.31725427508354187,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0458,
+      "step": 44
+    },
+    {
+      "epoch": 0.6020066889632107,
+      "grad_norm": 0.4152943789958954,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0663,
+      "step": 45
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.47436490654945374,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0669,
+      "step": 46
+    },
+    {
+      "epoch": 0.6287625418060201,
+      "grad_norm": 0.5078362822532654,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0858,
+      "step": 47
+    },
+    {
+      "epoch": 0.6421404682274248,
+      "grad_norm": 0.6469860076904297,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.1093,
+      "step": 48
+    },
+    {
+      "epoch": 0.6555183946488294,
+      "grad_norm": 0.6910544633865356,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.0934,
+      "step": 49
+    },
+    {
+      "epoch": 0.6688963210702341,
+      "grad_norm": 0.681873619556427,
+      "learning_rate": 1e-05,
+      "loss": 0.106,
+      "step": 50
+    },
+    {
+      "epoch": 0.6688963210702341,
+      "eval_loss": 0.06487244367599487,
+      "eval_runtime": 3.4726,
+      "eval_samples_per_second": 14.398,
+      "eval_steps_per_second": 3.744,
+      "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