Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09a8e7b4cb27b95bb7e8313421d913e75acde652ea88999d4e5e0f57f41aa852
+oid sha256:f93ff2fd76c37cd39b7adb036d39a1d6fdd2af916b608b1b5ff81ff589557e08
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ab037856d6464f48888f4ffe5b0f7f0f50a38645d60552e7a081d97158be434
+oid sha256:92d9de0af73538fe9dbf19ac25527e4f35858aaf7646623dd904abf767a3ec3f
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24d63d9bdc84440beb49bff8a3ee3a26f657c25d9390e379eb71dc1ff001decd
+oid sha256:382e85b2db969b26fd16ef957c2485de2f815a743d41a103a24f6c46902faa04
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e77722b8d792fccf2a0ced244e68ae15f5e4f61d33391538f6aaa8629cde6ad
+oid sha256:5a4390e9eea2b4831cb3c09c612d78ba50dc715879055e002261c4b2d5aa7bc1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b00dab97058c0c21aae9df278f6b9be750bfb5d571152841b3f63cfd54ab26c
+oid sha256:04a40adbfde1cf8d3b160d9b5c2005af4249273781a1b6f45396d3e5f37262ed
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e39342055ccf7e865a32d39233bde354759758a289aed7f3267bd309ff3560ad
+oid sha256:dfb7c9aa098f0e1dd7923487486e54e85fb19c106f82bfd41280d3cbade64e2a
 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": 0.5757180452346802,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5571030640668524,
+  "best_metric": 0.5159067511558533,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1142061281337048,
   "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": 68.769,
       "eval_steps_per_second": 8.625,
       "step": 25
+    },
+    {
+      "epoch": 0.5793871866295265,
+      "grad_norm": 5.951724529266357,
+      "learning_rate": 5e-05,
+      "loss": 0.563,
+      "step": 26
+    },
+    {
+      "epoch": 0.6016713091922006,
+      "grad_norm": 1.962470531463623,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5493,
+      "step": 27
+    },
+    {
+      "epoch": 0.6239554317548747,
+      "grad_norm": 1.5062148571014404,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5041,
+      "step": 28
+    },
+    {
+      "epoch": 0.6462395543175488,
+      "grad_norm": 3.15012264251709,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5864,
+      "step": 29
+    },
+    {
+      "epoch": 0.6685236768802229,
+      "grad_norm": 0.9960513114929199,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5485,
+      "step": 30
+    },
+    {
+      "epoch": 0.6908077994428969,
+      "grad_norm": 2.9807181358337402,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5871,
+      "step": 31
+    },
+    {
+      "epoch": 0.713091922005571,
+      "grad_norm": 0.8017144203186035,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5185,
+      "step": 32
+    },
+    {
+      "epoch": 0.7353760445682451,
+      "grad_norm": 1.2120144367218018,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4994,
+      "step": 33
+    },
+    {
+      "epoch": 0.7576601671309192,
+      "grad_norm": 2.6110732555389404,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.5343,
+      "step": 34
+    },
+    {
+      "epoch": 0.7799442896935933,
+      "grad_norm": 3.2504384517669678,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.5009,
+      "step": 35
+    },
+    {
+      "epoch": 0.8022284122562674,
+      "grad_norm": 2.49662446975708,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4935,
+      "step": 36
+    },
+    {
+      "epoch": 0.8245125348189415,
+      "grad_norm": 1.3326027393341064,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.541,
+      "step": 37
+    },
+    {
+      "epoch": 0.8467966573816156,
+      "grad_norm": 2.0869436264038086,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5217,
+      "step": 38
+    },
+    {
+      "epoch": 0.8690807799442897,
+      "grad_norm": 1.49491548538208,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5261,
+      "step": 39
+    },
+    {
+      "epoch": 0.8913649025069638,
+      "grad_norm": 3.31276273727417,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5595,
+      "step": 40
+    },
+    {
+      "epoch": 0.9136490250696379,
+      "grad_norm": 2.444161891937256,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.5109,
+      "step": 41
+    },
+    {
+      "epoch": 0.935933147632312,
+      "grad_norm": 3.385462522506714,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5329,
+      "step": 42
+    },
+    {
+      "epoch": 0.958217270194986,
+      "grad_norm": 1.8717201948165894,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5601,
+      "step": 43
+    },
+    {
+      "epoch": 0.9805013927576601,
+      "grad_norm": 2.7141246795654297,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5087,
+      "step": 44
+    },
+    {
+      "epoch": 1.0027855153203342,
+      "grad_norm": 2.526226758956909,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.5976,
+      "step": 45
+    },
+    {
+      "epoch": 1.0250696378830084,
+      "grad_norm": 1.1575802564620972,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5293,
+      "step": 46
+    },
+    {
+      "epoch": 1.0473537604456824,
+      "grad_norm": 0.5721626281738281,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5247,
+      "step": 47
+    },
+    {
+      "epoch": 1.0696378830083566,
+      "grad_norm": 3.1409993171691895,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4927,
+      "step": 48
+    },
+    {
+      "epoch": 1.0919220055710306,
+      "grad_norm": 0.9633862972259521,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4579,
+      "step": 49
+    },
+    {
+      "epoch": 1.1142061281337048,
+      "grad_norm": 2.3224472999572754,
+      "learning_rate": 0.0,
+      "loss": 0.4813,
+      "step": 50
+    },
+    {
+      "epoch": 1.1142061281337048,
+      "eval_loss": 0.5159067511558533,
+      "eval_runtime": 7.2968,
+      "eval_samples_per_second": 41.525,
+      "eval_steps_per_second": 5.208,
+      "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": 8.051627496623309e+16,
+  "total_flos": 1.6068485461311488e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null