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:c3eb2ed91b0373817fde5fcfa2076eb4a3d94fea0d49aac042fe5bcc55d4f7be
+oid sha256:2da984e0d5eb8b75c69588783b787576367fce9639778e0d2e364ac7e05126d0
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79a406a2af918ae33ef5c04eef31c029e03966a0735141aca7ec0f68bbc98e8a
+oid sha256:d24e2c3b61d2076c78c4e8ff727bd1b64b9e94e8ef70444cc7745a457ad0d659
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91d22b688cf66283ee087d9f1e8f64f84fca6694cbe460a2583a0af6942fdb67
+oid sha256:9ee4d92c96f053939859e1de9b125afd2001c96b616097b758f007963c9b97d2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cebd162aba18f860f51e2cc1ee5936648cae7b887a6a1f05cf77f1291d5c859b
+oid sha256:00e6ca730b683b5b228be5c4e973697d55f1249d83ba96868efc19ba82ad088c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aadddfe7c61a55a44e273bbb3a7a37cae1e95a431be61cbeeb3000151f9499b2
+oid sha256:4960f1e1dd22d2b4fe1c3e43db66eaac5e947eb69645665c06cba704231b2594
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:295014528a02b2db72edd87d2b4deaec8abb404c50d476b52f4741079de8eca6
+oid sha256:d4392c9d2176dde701259aa7803af164f1fab53fb034001e9577ccf3bcaa286f
 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": 1.7811026573181152,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3421727972626176,
+  "best_metric": 1.7397328615188599,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6843455945252352,
   "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": 34.21,
       "eval_steps_per_second": 8.895,
       "step": 25
+    },
+    {
+      "epoch": 0.3558597091531223,
+      "grad_norm": 0.7591701149940491,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.0127,
+      "step": 26
+    },
+    {
+      "epoch": 0.369546621043627,
+      "grad_norm": 0.9103983044624329,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.9637,
+      "step": 27
+    },
+    {
+      "epoch": 0.38323353293413176,
+      "grad_norm": 0.8943213820457458,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.9139,
+      "step": 28
+    },
+    {
+      "epoch": 0.39692044482463645,
+      "grad_norm": 0.8365579843521118,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.9006,
+      "step": 29
+    },
+    {
+      "epoch": 0.41060735671514115,
+      "grad_norm": 0.8076335787773132,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.9083,
+      "step": 30
+    },
+    {
+      "epoch": 0.42429426860564584,
+      "grad_norm": 0.7735624313354492,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.8956,
+      "step": 31
+    },
+    {
+      "epoch": 0.43798118049615054,
+      "grad_norm": 0.7214319705963135,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.8705,
+      "step": 32
+    },
+    {
+      "epoch": 0.4516680923866553,
+      "grad_norm": 0.7641725540161133,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.8121,
+      "step": 33
+    },
+    {
+      "epoch": 0.46535500427716,
+      "grad_norm": 0.7683237195014954,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.7478,
+      "step": 34
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "grad_norm": 0.8942069411277771,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.7379,
+      "step": 35
+    },
+    {
+      "epoch": 0.49272882805816937,
+      "grad_norm": 1.1086134910583496,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.6556,
+      "step": 36
+    },
+    {
+      "epoch": 0.5064157399486741,
+      "grad_norm": 1.8508061170578003,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.7596,
+      "step": 37
+    },
+    {
+      "epoch": 0.5201026518391788,
+      "grad_norm": 0.5953439474105835,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.9416,
+      "step": 38
+    },
+    {
+      "epoch": 0.5337895637296834,
+      "grad_norm": 0.5514473915100098,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.9681,
+      "step": 39
+    },
+    {
+      "epoch": 0.5474764756201882,
+      "grad_norm": 0.5643142461776733,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.9015,
+      "step": 40
+    },
+    {
+      "epoch": 0.561163387510693,
+      "grad_norm": 0.6523820161819458,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.9157,
+      "step": 41
+    },
+    {
+      "epoch": 0.5748502994011976,
+      "grad_norm": 0.6224381923675537,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.8996,
+      "step": 42
+    },
+    {
+      "epoch": 0.5885372112917023,
+      "grad_norm": 0.6665676236152649,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.831,
+      "step": 43
+    },
+    {
+      "epoch": 0.602224123182207,
+      "grad_norm": 0.7095207571983337,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.8424,
+      "step": 44
+    },
+    {
+      "epoch": 0.6159110350727117,
+      "grad_norm": 0.6559857726097107,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.7975,
+      "step": 45
+    },
+    {
+      "epoch": 0.6295979469632165,
+      "grad_norm": 0.7268767952919006,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.8395,
+      "step": 46
+    },
+    {
+      "epoch": 0.6432848588537211,
+      "grad_norm": 0.7550267577171326,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.7475,
+      "step": 47
+    },
+    {
+      "epoch": 0.6569717707442259,
+      "grad_norm": 0.9330142140388489,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.7608,
+      "step": 48
+    },
+    {
+      "epoch": 0.6706586826347305,
+      "grad_norm": 1.2081230878829956,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.7007,
+      "step": 49
+    },
+    {
+      "epoch": 0.6843455945252352,
+      "grad_norm": 2.4048612117767334,
+      "learning_rate": 1e-05,
+      "loss": 1.7784,
+      "step": 50
+    },
+    {
+      "epoch": 0.6843455945252352,
+      "eval_loss": 1.7397328615188599,
+      "eval_runtime": 1.4629,
+      "eval_samples_per_second": 34.18,
+      "eval_steps_per_second": 8.887,
+      "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": 7.94731890081792e+16,
+  "total_flos": 1.589463780163584e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null