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:ead69c58462791e9b3b78649e3199d8362bfe863d885b05713f4f93206248f70
+oid sha256:5a21ac62dc05ecfe50d366197bcf226060053c4c6d70d32e4ffbdaa41cf6d511
 size 100690288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6e5cbf434d326825b6f2f5fea81711726224b549cb2294fae6ae309c76f07d1
+oid sha256:95e351282333d62e7084547a509e4d15bef761d4d443ce2134a41ce003cd149c
 size 201488570

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b65568bcafd41a616dec0332885bc21ab49fbb597d32c04eb043d5661fdccf1
+oid sha256:3877fb6bb8fb7a13455ce4c12ec1b2bae788e0ab73d742fe06aee03f905fbaff
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:821cd6b421da594373994386c7fa0163e3f798603925f08da2fe4b51dc81cc3e
+oid sha256:7fee770f8fa582bcd9e1bcd432c1163b1cbf45fc43c5b2d61509025565e2135d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b49f68e7a7ff73567ecf125220724cc0569ce466b64f806107efe47d5408ca7
+oid sha256:31ba91e4225d0b16bad3d40ae3ba674f580f22ac6e7e2a9f222010bbf991d1a5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26768d555d48908128af1a395a29cb28c1be24334007ecb3f9cac54142793141
+oid sha256:41db95822976490b7f7ac26131a4f2393755f6184626c8a73b04cdd6537aa7cc
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1853362321853638,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3147128245476003,
+  "best_metric": 0.9442797303199768,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6294256490952006,
   "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": 39.307,
       "eval_steps_per_second": 4.913,
       "step": 25
+    },
+    {
+      "epoch": 0.32730133752950435,
+      "grad_norm": 32.60086441040039,
+      "learning_rate": 5e-05,
+      "loss": 1.6508,
+      "step": 26
+    },
+    {
+      "epoch": 0.33988985051140835,
+      "grad_norm": 29.659774780273438,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.3073,
+      "step": 27
+    },
+    {
+      "epoch": 0.35247836349331235,
+      "grad_norm": 27.13357925415039,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.2718,
+      "step": 28
+    },
+    {
+      "epoch": 0.36506687647521635,
+      "grad_norm": 24.87796401977539,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2055,
+      "step": 29
+    },
+    {
+      "epoch": 0.3776553894571204,
+      "grad_norm": 24.10536003112793,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.16,
+      "step": 30
+    },
+    {
+      "epoch": 0.3902439024390244,
+      "grad_norm": 25.981910705566406,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0399,
+      "step": 31
+    },
+    {
+      "epoch": 0.4028324154209284,
+      "grad_norm": 36.10255813598633,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.135,
+      "step": 32
+    },
+    {
+      "epoch": 0.4154209284028324,
+      "grad_norm": 40.39674758911133,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1585,
+      "step": 33
+    },
+    {
+      "epoch": 0.42800944138473646,
+      "grad_norm": 34.2160758972168,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8405,
+      "step": 34
+    },
+    {
+      "epoch": 0.44059795436664045,
+      "grad_norm": 33.32962417602539,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.797,
+      "step": 35
+    },
+    {
+      "epoch": 0.45318646734854445,
+      "grad_norm": 27.23453140258789,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7851,
+      "step": 36
+    },
+    {
+      "epoch": 0.46577498033044845,
+      "grad_norm": 31.11690330505371,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9167,
+      "step": 37
+    },
+    {
+      "epoch": 0.4783634933123525,
+      "grad_norm": 31.77367401123047,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.096,
+      "step": 38
+    },
+    {
+      "epoch": 0.4909520062942565,
+      "grad_norm": 31.28978729248047,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.3097,
+      "step": 39
+    },
+    {
+      "epoch": 0.5035405192761605,
+      "grad_norm": 24.03819465637207,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.0327,
+      "step": 40
+    },
+    {
+      "epoch": 0.5161290322580645,
+      "grad_norm": 24.845369338989258,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.0824,
+      "step": 41
+    },
+    {
+      "epoch": 0.5287175452399685,
+      "grad_norm": 24.798585891723633,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.058,
+      "step": 42
+    },
+    {
+      "epoch": 0.5413060582218725,
+      "grad_norm": 24.77889633178711,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.9896,
+      "step": 43
+    },
+    {
+      "epoch": 0.5538945712037766,
+      "grad_norm": 24.031038284301758,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8687,
+      "step": 44
+    },
+    {
+      "epoch": 0.5664830841856806,
+      "grad_norm": 24.104299545288086,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9357,
+      "step": 45
+    },
+    {
+      "epoch": 0.5790715971675846,
+      "grad_norm": 24.142581939697266,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8889,
+      "step": 46
+    },
+    {
+      "epoch": 0.5916601101494886,
+      "grad_norm": 23.086729049682617,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6544,
+      "step": 47
+    },
+    {
+      "epoch": 0.6042486231313926,
+      "grad_norm": 24.28306770324707,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7109,
+      "step": 48
+    },
+    {
+      "epoch": 0.6168371361132966,
+      "grad_norm": 25.321258544921875,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7226,
+      "step": 49
+    },
+    {
+      "epoch": 0.6294256490952006,
+      "grad_norm": 40.5628776550293,
+      "learning_rate": 0.0,
+      "loss": 0.7491,
+      "step": 50
+    },
+    {
+      "epoch": 0.6294256490952006,
+      "eval_loss": 0.9442797303199768,
+      "eval_runtime": 13.6356,
+      "eval_samples_per_second": 39.309,
+      "eval_steps_per_second": 4.914,
+      "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": 4.85137494048768e+16,
+  "total_flos": 9.70274988097536e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null