Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0bc703a3d6edbe7aa5dd1bb0cad4d807f2af64e82be89b9e7fae786b179cb9ee
+oid sha256:498e3bac1b0de02857fa6c3ef90bad3fbda583e08034b38127390fcc9c223ed5
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46601b6fbdaa21cafa63534d19a4e0d3635fdfba36cabba56586518ce5ae0a77
+oid sha256:fb55d6d9186c7897352e6772a96c4aa4162074e6bf356a0ac46c29bc07cfc262
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:532b536a81134d5bc2b750d30a3d879511824bd598e80dc7c0ad0f92b4b320f2
+oid sha256:38b68e0a36c1c75e079352fca6aa78485951994f525c243e096e424e3152ccc9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa9f2acef8684dcade77e44472654e837b79fd8675e562f565d90fd994267dd3
+oid sha256:3f34a53fed40eb8f7e89945ca4c487314e1c268a6251a2715da1ea4fde06c649
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b5ad3bb991cde6533109c4e3242e200b2371bd5ff9170e99333d8891bb2a4c5
+oid sha256:13eaeb7c2ad727f63f115b2cf2c599413cfd4772962080142538e6bc2e338273
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:128dfa04445acdfcdeed21281f41f7223d56fdc7ab632a8a76c1ced6f66e7db4
+oid sha256:9b7e4a063a6f0794316f0c122a6036b445b59eae2cedbd87e1fc1f3847ce625b
 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": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.31286664059444663,
+  "epoch": 0.6257332811888933,
   "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": 32.454,
       "eval_steps_per_second": 8.438,
       "step": 25
+    },
+    {
+      "epoch": 0.3253813062182245,
+      "grad_norm": 1.8852589130401611,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9857,
+      "step": 26
+    },
+    {
+      "epoch": 0.3378959718420024,
+      "grad_norm": 1.9653517007827759,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.352,
+      "step": 27
+    },
+    {
+      "epoch": 0.3504106374657802,
+      "grad_norm": 1.741631031036377,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.5297,
+      "step": 28
+    },
+    {
+      "epoch": 0.36292530308955806,
+      "grad_norm": 1.4939073324203491,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.1796,
+      "step": 29
+    },
+    {
+      "epoch": 0.37543996871333596,
+      "grad_norm": 1.9613261222839355,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.2641,
+      "step": 30
+    },
+    {
+      "epoch": 0.3879546343371138,
+      "grad_norm": 2.448169231414795,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.088,
+      "step": 31
+    },
+    {
+      "epoch": 0.40046929996089164,
+      "grad_norm": 1.9696348905563354,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.2429,
+      "step": 32
+    },
+    {
+      "epoch": 0.41298396558466954,
+      "grad_norm": 1.830755591392517,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.3355,
+      "step": 33
+    },
+    {
+      "epoch": 0.4254986312084474,
+      "grad_norm": 1.900875210762024,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.2828,
+      "step": 34
+    },
+    {
+      "epoch": 0.4380132968322253,
+      "grad_norm": 2.263303518295288,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.1999,
+      "step": 35
+    },
+    {
+      "epoch": 0.45052796245600313,
+      "grad_norm": 2.3293285369873047,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.0375,
+      "step": 36
+    },
+    {
+      "epoch": 0.46304262807978097,
+      "grad_norm": 2.2211854457855225,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.2903,
+      "step": 37
+    },
+    {
+      "epoch": 0.47555729370355887,
+      "grad_norm": 1.6142629384994507,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9743,
+      "step": 38
+    },
+    {
+      "epoch": 0.4880719593273367,
+      "grad_norm": 1.505129098892212,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.8478,
+      "step": 39
+    },
+    {
+      "epoch": 0.5005866249511146,
+      "grad_norm": 1.8305461406707764,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.5612,
+      "step": 40
+    },
+    {
+      "epoch": 0.5131012905748924,
+      "grad_norm": 1.6045444011688232,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.1132,
+      "step": 41
+    },
+    {
+      "epoch": 0.5256159561986703,
+      "grad_norm": 1.7376651763916016,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.1452,
+      "step": 42
+    },
+    {
+      "epoch": 0.5381306218224482,
+      "grad_norm": 1.6962471008300781,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.0739,
+      "step": 43
+    },
+    {
+      "epoch": 0.5506452874462261,
+      "grad_norm": 1.7979378700256348,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.1389,
+      "step": 44
+    },
+    {
+      "epoch": 0.5631599530700039,
+      "grad_norm": 1.698608160018921,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.1921,
+      "step": 45
+    },
+    {
+      "epoch": 0.5756746186937818,
+      "grad_norm": 1.2694196701049805,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6618,
+      "step": 46
+    },
+    {
+      "epoch": 0.5881892843175597,
+      "grad_norm": 1.769540786743164,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.9457,
+      "step": 47
+    },
+    {
+      "epoch": 0.6007039499413375,
+      "grad_norm": 2.079148292541504,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.996,
+      "step": 48
+    },
+    {
+      "epoch": 0.6132186155651154,
+      "grad_norm": 1.7896637916564941,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.9705,
+      "step": 49
+    },
+    {
+      "epoch": 0.6257332811888933,
+      "grad_norm": 2.5797500610351562,
+      "learning_rate": 1e-05,
+      "loss": 1.6221,
+      "step": 50
+    },
+    {
+      "epoch": 0.6257332811888933,
+      "eval_loss": NaN,
+      "eval_runtime": 1.5472,
+      "eval_samples_per_second": 32.316,
+      "eval_steps_per_second": 8.402,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -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