Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9121826d33ebd598c968d50701792d563318c05fa9b2858edfe93d5265ae3916
+oid sha256:31c5b9326d9898e1b9c5b0becdc9e3d51c79a8afe07dbf71a34471af756f6939
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d3b9d32b3788dc61307a4ad157fdfcf125fc91a1bfe6530fc285db7eeb182c
+oid sha256:017ed0293517e2d9c2b0312d60708d5673169a6c8235431849a71eceea99f596
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c09b2735482504615d656988c37c635cdf807c6c0454a68276c7868a4ad2e49
+oid sha256:ca51a253b30a94665ba0969d350751067e906e17d78c8b32be5f5e96010cd838
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c25b338fe4bd7810a7c01aeaa982af11293f744e66d4fdfb998663437760d032
+oid sha256:6bbb45a05c3f0a5a6baee13b8216f061763cb18c47ce49d000b20f3c0ea903b4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf0006324355a51daa9a2fdeac7b66cd65d431212b16d65a6ddabaa77915412c
+oid sha256:2793dcea11c20e8a8815f7ba541b68e14b0c3540c6c47954f18d7b8f91de74dc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:063f95908ae59d1b25200ee58881adbd05537eed68e61a319eed50107fe67baf
+oid sha256:a053f17dcb5d73967e78dba2ecf92e9043f4b126b73c2cb300a2162ca844b349
 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": 0.922303318977356,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.33585222502099077,
+  "best_metric": 0.9089703559875488,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6717044500419815,
   "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": 83.903,
       "eval_steps_per_second": 21.815,
       "step": 25
+    },
+    {
+      "epoch": 0.3492863140218304,
+      "grad_norm": 0.2772812247276306,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.9499,
+      "step": 26
+    },
+    {
+      "epoch": 0.36272040302267,
+      "grad_norm": 0.2742224931716919,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.9397,
+      "step": 27
+    },
+    {
+      "epoch": 0.37615449202350965,
+      "grad_norm": 0.249447762966156,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.915,
+      "step": 28
+    },
+    {
+      "epoch": 0.3895885810243493,
+      "grad_norm": 0.24550966918468475,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.9255,
+      "step": 29
+    },
+    {
+      "epoch": 0.40302267002518893,
+      "grad_norm": 0.22773662209510803,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.8901,
+      "step": 30
+    },
+    {
+      "epoch": 0.4164567590260285,
+      "grad_norm": 0.22250418365001678,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.9029,
+      "step": 31
+    },
+    {
+      "epoch": 0.42989084802686817,
+      "grad_norm": 0.2120346873998642,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.9311,
+      "step": 32
+    },
+    {
+      "epoch": 0.4433249370277078,
+      "grad_norm": 0.22748982906341553,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.8937,
+      "step": 33
+    },
+    {
+      "epoch": 0.45675902602854745,
+      "grad_norm": 0.24521538615226746,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8982,
+      "step": 34
+    },
+    {
+      "epoch": 0.47019311502938704,
+      "grad_norm": 0.2516072690486908,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.9221,
+      "step": 35
+    },
+    {
+      "epoch": 0.4836272040302267,
+      "grad_norm": 0.23325960338115692,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8955,
+      "step": 36
+    },
+    {
+      "epoch": 0.49706129303106633,
+      "grad_norm": 0.25947290658950806,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.8837,
+      "step": 37
+    },
+    {
+      "epoch": 0.5104953820319059,
+      "grad_norm": 0.22557468712329865,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.9096,
+      "step": 38
+    },
+    {
+      "epoch": 0.5239294710327456,
+      "grad_norm": 0.20343045890331268,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.9161,
+      "step": 39
+    },
+    {
+      "epoch": 0.5373635600335852,
+      "grad_norm": 0.20457938313484192,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.9176,
+      "step": 40
+    },
+    {
+      "epoch": 0.5507976490344249,
+      "grad_norm": 0.20346155762672424,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.9319,
+      "step": 41
+    },
+    {
+      "epoch": 0.5642317380352645,
+      "grad_norm": 0.20841321349143982,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.8758,
+      "step": 42
+    },
+    {
+      "epoch": 0.5776658270361041,
+      "grad_norm": 0.20341482758522034,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.8818,
+      "step": 43
+    },
+    {
+      "epoch": 0.5910999160369438,
+      "grad_norm": 0.20321235060691833,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.9079,
+      "step": 44
+    },
+    {
+      "epoch": 0.6045340050377834,
+      "grad_norm": 0.20054325461387634,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.894,
+      "step": 45
+    },
+    {
+      "epoch": 0.617968094038623,
+      "grad_norm": 0.21549059450626373,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.8953,
+      "step": 46
+    },
+    {
+      "epoch": 0.6314021830394626,
+      "grad_norm": 0.2093229442834854,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.8795,
+      "step": 47
+    },
+    {
+      "epoch": 0.6448362720403022,
+      "grad_norm": 0.21790167689323425,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.9229,
+      "step": 48
+    },
+    {
+      "epoch": 0.6582703610411419,
+      "grad_norm": 0.22668731212615967,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.8744,
+      "step": 49
+    },
+    {
+      "epoch": 0.6717044500419815,
+      "grad_norm": 0.2757410407066345,
+      "learning_rate": 1e-05,
+      "loss": 0.9385,
+      "step": 50
+    },
+    {
+      "epoch": 0.6717044500419815,
+      "eval_loss": 0.9089703559875488,
+      "eval_runtime": 0.5908,
+      "eval_samples_per_second": 84.633,
+      "eval_steps_per_second": 22.004,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null