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:c19861aeacdbd078275e698c97c3c3f3bf87081d80bf419cd3f640faecd016a1
+oid sha256:f333413eaad33ef0cbe3bef0d4c99b72825777b97cd9654b3a90d4dddeb05001
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7297eb27cf4905e5fac722ac8997530653f8d4de28cb148e2c99d89c34b578a0
+oid sha256:ab1faf8fb8ec0323b376df14d85557e044c16fa21ce28dd88e1b62ec0ba56b02
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb0e26782acb0826ede0a5e776762f7eaf8947688b0bc8761f179b021189eb67
+oid sha256:c52074dca786f209dcdb45a318dfc8cbc56c99429fb21aceb0e37efcfedcd108
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9de507506c771e7e793f25f90986233f2be6946b3ca506edb9fcb62cb2347059
+oid sha256:759ff61a7e29bf5e9b79df79d45590277fdd9323b5d669eddb1854ea4065a2fc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e89bdf79a6ffc0f7ce7623e855e7d0af6339ef5d4b3b9c0f63f92f3513381553
+oid sha256:4603d7b74b45aab0fa1c19bf403a6f044149911ddbca01fdc7330137179a2094
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8918904f2bb4053ea4015450b3f2ea1e1e974ec341caa6b85c03b6ee6d081b3
+oid sha256:eb15db80ba65bdce3f532b0d0d05c47e8548aac02f24a99639d279007f9163bb
 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": 3.8601596355438232,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6339144215530903,
+  "best_metric": 3.570333957672119,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2725832012678289,
   "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": 15.443,
       "eval_steps_per_second": 4.015,
       "step": 25
+    },
+    {
+      "epoch": 0.659270998415214,
+      "grad_norm": 0.9849798083305359,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 4.8352,
+      "step": 26
+    },
+    {
+      "epoch": 0.6846275752773375,
+      "grad_norm": 0.7620542645454407,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.7772,
+      "step": 27
+    },
+    {
+      "epoch": 0.7099841521394612,
+      "grad_norm": 0.659827470779419,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.4214,
+      "step": 28
+    },
+    {
+      "epoch": 0.7353407290015848,
+      "grad_norm": 0.6697689294815063,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.421,
+      "step": 29
+    },
+    {
+      "epoch": 0.7606973058637084,
+      "grad_norm": 0.277683287858963,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.0666,
+      "step": 30
+    },
+    {
+      "epoch": 0.786053882725832,
+      "grad_norm": 0.2757035493850708,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.1096,
+      "step": 31
+    },
+    {
+      "epoch": 0.8114104595879557,
+      "grad_norm": 0.44613122940063477,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.8999,
+      "step": 32
+    },
+    {
+      "epoch": 0.8367670364500792,
+      "grad_norm": 0.7326236963272095,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.7005,
+      "step": 33
+    },
+    {
+      "epoch": 0.8621236133122029,
+      "grad_norm": 0.7507456541061401,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.7567,
+      "step": 34
+    },
+    {
+      "epoch": 0.8874801901743264,
+      "grad_norm": 1.190097451210022,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.3884,
+      "step": 35
+    },
+    {
+      "epoch": 0.9128367670364501,
+      "grad_norm": 1.2896158695220947,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 4.5575,
+      "step": 36
+    },
+    {
+      "epoch": 0.9381933438985737,
+      "grad_norm": 1.1473909616470337,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.5029,
+      "step": 37
+    },
+    {
+      "epoch": 0.9635499207606973,
+      "grad_norm": 0.797999918460846,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 4.4227,
+      "step": 38
+    },
+    {
+      "epoch": 0.9889064976228209,
+      "grad_norm": 0.9181230664253235,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.3552,
+      "step": 39
+    },
+    {
+      "epoch": 1.0190174326465926,
+      "grad_norm": 0.5703205466270447,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.0124,
+      "step": 40
+    },
+    {
+      "epoch": 1.0443740095087164,
+      "grad_norm": 0.3020019829273224,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.13,
+      "step": 41
+    },
+    {
+      "epoch": 1.06973058637084,
+      "grad_norm": 0.4112301766872406,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.0526,
+      "step": 42
+    },
+    {
+      "epoch": 1.0950871632329635,
+      "grad_norm": 0.6388920545578003,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.3546,
+      "step": 43
+    },
+    {
+      "epoch": 1.120443740095087,
+      "grad_norm": 0.6673762798309326,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.6732,
+      "step": 44
+    },
+    {
+      "epoch": 1.1458003169572109,
+      "grad_norm": 0.7496306896209717,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.2136,
+      "step": 45
+    },
+    {
+      "epoch": 1.1711568938193344,
+      "grad_norm": 0.8316301107406616,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.3503,
+      "step": 46
+    },
+    {
+      "epoch": 1.196513470681458,
+      "grad_norm": 0.7724796533584595,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.3197,
+      "step": 47
+    },
+    {
+      "epoch": 1.2218700475435815,
+      "grad_norm": 0.7230962514877319,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.207,
+      "step": 48
+    },
+    {
+      "epoch": 1.2472266244057053,
+      "grad_norm": 0.33317622542381287,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.4657,
+      "step": 49
+    },
+    {
+      "epoch": 1.2725832012678289,
+      "grad_norm": 0.5080307722091675,
+      "learning_rate": 1e-05,
+      "loss": 3.2126,
+      "step": 50
+    },
+    {
+      "epoch": 1.2725832012678289,
+      "eval_loss": 3.570333957672119,
+      "eval_runtime": 3.2238,
+      "eval_samples_per_second": 15.51,
+      "eval_steps_per_second": 4.033,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null