Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:964ebd79d1fac7d863a16496f5d6a1097bedbe50485a101d70e12eea1ac8b732
+oid sha256:14bea63edb5e0f9a010c231bde78d4d138f667a68ef4fe551a8764dcff7f1411
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb6ea3d5d6cb0b90f6fd58506f840a99f839cc5fa1304244ddd28a19ea6e65d
+oid sha256:ed0ad9c0036459e2a043778bf1109ccccbca38df0f8d05e89ba175c4026b5d8d
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8dfa5266d4cabe44b6d7bb319437bd97d3dc8680c845fc7d40c95e8fba3241f
+oid sha256:56437b5e6b35a9967f7b3d332f9b346f8366397c5a9b8e64fb474ca3baeefa3e
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddbf032b81806b4b5dffaa8b60178c1ccd86a0dc6b797fe3dfe0d4b70df087b7
+oid sha256:54730b5855f77e8490e78d32044c3fef1ea8d6c0fe6ec316bd4d7cca1f56e2db
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:309dccb8a510f7de738419a3bb7a5e045fe8a4b85294604b246be84bb1ce2db4
+oid sha256:417c1cde77263cef27583ea5fe8bdc4c806bbf1ccb633e16850d6cbbdb55922f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b338a5570141f4e3d7bdf6865c471b220035e305f193a2a1e8b519c7f59deb62
+oid sha256:5c0d36ad9be798167d601e0fbd10dd20b801417364458420af7b5db6ef706b67
 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": 0.552042543888092,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5617977528089888,
+  "best_metric": 0.37203922867774963,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1235955056179776,
   "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": 58.207,
       "eval_steps_per_second": 15.134,
       "step": 25
+    },
+    {
+      "epoch": 0.5842696629213483,
+      "grad_norm": 2.733752727508545,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.4433,
+      "step": 26
+    },
+    {
+      "epoch": 0.6067415730337079,
+      "grad_norm": 4.73248291015625,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.5019,
+      "step": 27
+    },
+    {
+      "epoch": 0.6292134831460674,
+      "grad_norm": 3.2187206745147705,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.4837,
+      "step": 28
+    },
+    {
+      "epoch": 0.651685393258427,
+      "grad_norm": 2.7652924060821533,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.4799,
+      "step": 29
+    },
+    {
+      "epoch": 0.6741573033707865,
+      "grad_norm": 5.405097961425781,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.4394,
+      "step": 30
+    },
+    {
+      "epoch": 0.6966292134831461,
+      "grad_norm": 3.7862300872802734,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.4753,
+      "step": 31
+    },
+    {
+      "epoch": 0.7191011235955056,
+      "grad_norm": 3.122354030609131,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.4543,
+      "step": 32
+    },
+    {
+      "epoch": 0.7415730337078652,
+      "grad_norm": 5.204441547393799,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.4658,
+      "step": 33
+    },
+    {
+      "epoch": 0.7640449438202247,
+      "grad_norm": 3.460355043411255,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.4973,
+      "step": 34
+    },
+    {
+      "epoch": 0.7865168539325843,
+      "grad_norm": 5.4133172035217285,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.4528,
+      "step": 35
+    },
+    {
+      "epoch": 0.8089887640449438,
+      "grad_norm": 4.1577839851379395,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4119,
+      "step": 36
+    },
+    {
+      "epoch": 0.8314606741573034,
+      "grad_norm": 1.967371940612793,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.407,
+      "step": 37
+    },
+    {
+      "epoch": 0.8539325842696629,
+      "grad_norm": 2.243610382080078,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.395,
+      "step": 38
+    },
+    {
+      "epoch": 0.8764044943820225,
+      "grad_norm": 4.601099967956543,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4377,
+      "step": 39
+    },
+    {
+      "epoch": 0.898876404494382,
+      "grad_norm": 5.425273418426514,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.484,
+      "step": 40
+    },
+    {
+      "epoch": 0.9213483146067416,
+      "grad_norm": 4.3527936935424805,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.4335,
+      "step": 41
+    },
+    {
+      "epoch": 0.9438202247191011,
+      "grad_norm": 3.8460605144500732,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.434,
+      "step": 42
+    },
+    {
+      "epoch": 0.9662921348314607,
+      "grad_norm": 3.1695282459259033,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.4288,
+      "step": 43
+    },
+    {
+      "epoch": 0.9887640449438202,
+      "grad_norm": 5.085464000701904,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.4407,
+      "step": 44
+    },
+    {
+      "epoch": 1.0112359550561798,
+      "grad_norm": 5.431034564971924,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.635,
+      "step": 45
+    },
+    {
+      "epoch": 1.0337078651685394,
+      "grad_norm": 3.2243857383728027,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3833,
+      "step": 46
+    },
+    {
+      "epoch": 1.0561797752808988,
+      "grad_norm": 3.8108878135681152,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.348,
+      "step": 47
+    },
+    {
+      "epoch": 1.0786516853932584,
+      "grad_norm": 3.8203694820404053,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3689,
+      "step": 48
+    },
+    {
+      "epoch": 1.101123595505618,
+      "grad_norm": 2.19366455078125,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3809,
+      "step": 49
+    },
+    {
+      "epoch": 1.1235955056179776,
+      "grad_norm": 2.593107223510742,
+      "learning_rate": 1e-05,
+      "loss": 0.3927,
+      "step": 50
+    },
+    {
+      "epoch": 1.1235955056179776,
+      "eval_loss": 0.37203922867774963,
+      "eval_runtime": 0.8469,
+      "eval_samples_per_second": 59.04,
+      "eval_steps_per_second": 15.35,
+      "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": 2,
   "trial_name": null,
   "trial_params": null