Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a13ba1721a32a0c718580180ff3afcbed344dd725f76896bc2cd5c76363c65f
+oid sha256:bb58cf24d1c2b679003ec78192452664a239f4a537d231f9063e1aacc9490334
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31613e0bdebf3c01b5c34fb2eef9576559fe0d7f957995dcd7a47467ad6871ba
+oid sha256:290fc752c84e29af7ac74adbd30521e1c107924a8d6a5c7b923144466ba58dea
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59b93cdd8404fa6c5c93f97840c82e00602fd2befdc79d7c0790f4c7ac62e001
+oid sha256:13fd98cdcf9be56904beac25ff0dc8dfc4d708e9a2713402b1f28556041307fa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c98b66a779d3626e8313447b4a116cb4f3c1d070e4880a6ae9f8f6f8df979f
+oid sha256:c31b11f44781e0ed88832f4b223ab8d03311d6e9ea1499da774413ef761d8dc2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdfcf88767a17b955d4ecfe2611a35a03d2b486c35bb189501f823506cca36c4
+oid sha256:e670733df1c39e6cb979a67370ef94a8361e3e50934ca9a4beeae4600a5e3ba6
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e4849e6078b24e5eaee4179ca07220afb983a06ac615983067b0fc2ddce1047
+oid sha256:368ae150f927ade1fa46a7f67ca662cc5fa398ff9ed42018a6837f79e14ded4a
 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": 11.931870460510254,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5641748942172073,
+  "best_metric": 11.931014060974121,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1283497884344147,
   "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": 299.204,
       "eval_steps_per_second": 77.793,
       "step": 25
+    },
+    {
+      "epoch": 0.5867418899858956,
+      "grad_norm": 0.032059792429208755,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9294,
+      "step": 26
+    },
+    {
+      "epoch": 0.609308885754584,
+      "grad_norm": 0.028178269043564796,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9301,
+      "step": 27
+    },
+    {
+      "epoch": 0.6318758815232722,
+      "grad_norm": 0.031542014330625534,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9307,
+      "step": 28
+    },
+    {
+      "epoch": 0.6544428772919605,
+      "grad_norm": 0.029014427214860916,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9318,
+      "step": 29
+    },
+    {
+      "epoch": 0.6770098730606487,
+      "grad_norm": 0.03503303602337837,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9302,
+      "step": 30
+    },
+    {
+      "epoch": 0.6995768688293371,
+      "grad_norm": 0.03429326042532921,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9303,
+      "step": 31
+    },
+    {
+      "epoch": 0.7221438645980254,
+      "grad_norm": 0.03715181350708008,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9305,
+      "step": 32
+    },
+    {
+      "epoch": 0.7447108603667136,
+      "grad_norm": 0.038947250694036484,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9309,
+      "step": 33
+    },
+    {
+      "epoch": 0.767277856135402,
+      "grad_norm": 0.030063152313232422,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9303,
+      "step": 34
+    },
+    {
+      "epoch": 0.7898448519040903,
+      "grad_norm": 0.028033409267663956,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9287,
+      "step": 35
+    },
+    {
+      "epoch": 0.8124118476727785,
+      "grad_norm": 0.028053291141986847,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9305,
+      "step": 36
+    },
+    {
+      "epoch": 0.8349788434414669,
+      "grad_norm": 0.028353266417980194,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.9292,
+      "step": 37
+    },
+    {
+      "epoch": 0.8575458392101551,
+      "grad_norm": 0.03844644874334335,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.9292,
+      "step": 38
+    },
+    {
+      "epoch": 0.8801128349788434,
+      "grad_norm": 0.038593534380197525,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.9305,
+      "step": 39
+    },
+    {
+      "epoch": 0.9026798307475318,
+      "grad_norm": 0.03276919573545456,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.932,
+      "step": 40
+    },
+    {
+      "epoch": 0.92524682651622,
+      "grad_norm": 0.03799021989107132,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9316,
+      "step": 41
+    },
+    {
+      "epoch": 0.9478138222849083,
+      "grad_norm": 0.03997742384672165,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9304,
+      "step": 42
+    },
+    {
+      "epoch": 0.9703808180535967,
+      "grad_norm": 0.043088801205158234,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.9287,
+      "step": 43
+    },
+    {
+      "epoch": 0.9929478138222849,
+      "grad_norm": 0.04122375696897507,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9302,
+      "step": 44
+    },
+    {
+      "epoch": 1.0155148095909732,
+      "grad_norm": 0.06158071011304855,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 21.1064,
+      "step": 45
+    },
+    {
+      "epoch": 1.0380818053596614,
+      "grad_norm": 0.029533565044403076,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.4006,
+      "step": 46
+    },
+    {
+      "epoch": 1.0606488011283497,
+      "grad_norm": 0.036127302795648575,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.6845,
+      "step": 47
+    },
+    {
+      "epoch": 1.0832157968970382,
+      "grad_norm": 0.03641054779291153,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9889,
+      "step": 48
+    },
+    {
+      "epoch": 1.1057827926657264,
+      "grad_norm": 0.03584923967719078,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.8621,
+      "step": 49
+    },
+    {
+      "epoch": 1.1283497884344147,
+      "grad_norm": 0.04079252853989601,
+      "learning_rate": 1e-05,
+      "loss": 11.7881,
+      "step": 50
+    },
+    {
+      "epoch": 1.1283497884344147,
+      "eval_loss": 11.931014060974121,
+      "eval_runtime": 0.1717,
+      "eval_samples_per_second": 291.157,
+      "eval_steps_per_second": 75.701,
+      "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": 521572909056.0,
+  "total_flos": 1043471597568.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null