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:a036ba276059da60f4a74fb0e2b79bcd3c16041e5950f90f67120c9b6db3dadd
+oid sha256:01634338c1a6edf56a231530221a36ccd3e4d46859f49102c8e604aa7a17b2e3
 size 100690288

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:302befebab68c89204a1a32acbf4ee02d8f99e6dc578d076cc29e6f7cfbcfcd2
+oid sha256:66ccb97e599d47c0c4e11b0e46c19368d2650a54fd7f0eddca75dedf9f41252f
 size 201488570

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a25d0d3b3d316bf7b2a8d1e8b852753387b8b93581fbd1d31bfbde98f7df33c7
+oid sha256:ac8163dcc04101ff47f01af7b9b3f08bfb0bf38687802e20ddd14722d6a028ed
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:614acb9aea55b745fb331b0d208ce4ab5b24f5d9696bf6d40869ed1941be3e05
+oid sha256:304039defc6827c6e3fc39a4db250c26f261f4c2b1aa7a324831c79960daeb8c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e842fb5769900b5014fd0fb0223117d2231469de7a68ed9ba6402cab3a2402
+oid sha256:3d28522bacc90b4de679a1d6ca573f03ee60fbab1ebac84baba4fb521dd7c7ea
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f22541ae3ed5c84cf6601708921673cb0c1bf89b46763a3afba68a4280a6584d
+oid sha256:be0938802d6625267044e1ff278b21928938d314a8ffaa42e14609cd9df487c0
 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": 0.9815108776092529,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03518029903254178,
+  "best_metric": 0.7248497605323792,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.07036059806508356,
   "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": 13.291,
       "eval_steps_per_second": 3.456,
       "step": 25
+    },
+    {
+      "epoch": 0.03658751099384345,
+      "grad_norm": 48.5167236328125,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 18.746,
+      "step": 26
+    },
+    {
+      "epoch": 0.03799472295514512,
+      "grad_norm": 17.335498809814453,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 14.3354,
+      "step": 27
+    },
+    {
+      "epoch": 0.03940193491644679,
+      "grad_norm": 18.078523635864258,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 14.9835,
+      "step": 28
+    },
+    {
+      "epoch": 0.04080914687774846,
+      "grad_norm": 16.168596267700195,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 14.3585,
+      "step": 29
+    },
+    {
+      "epoch": 0.04221635883905013,
+      "grad_norm": 13.818469047546387,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 14.2727,
+      "step": 30
+    },
+    {
+      "epoch": 0.043623570800351806,
+      "grad_norm": 14.244519233703613,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 13.6869,
+      "step": 31
+    },
+    {
+      "epoch": 0.045030782761653475,
+      "grad_norm": 15.645011901855469,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 13.199,
+      "step": 32
+    },
+    {
+      "epoch": 0.04643799472295514,
+      "grad_norm": 13.092461585998535,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 12.9738,
+      "step": 33
+    },
+    {
+      "epoch": 0.04784520668425682,
+      "grad_norm": 12.56582260131836,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.5423,
+      "step": 34
+    },
+    {
+      "epoch": 0.04925241864555849,
+      "grad_norm": 13.258774757385254,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 12.0315,
+      "step": 35
+    },
+    {
+      "epoch": 0.050659630606860157,
+      "grad_norm": 18.495140075683594,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 12.7495,
+      "step": 36
+    },
+    {
+      "epoch": 0.05206684256816183,
+      "grad_norm": 21.639209747314453,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 12.4928,
+      "step": 37
+    },
+    {
+      "epoch": 0.0534740545294635,
+      "grad_norm": 31.71373176574707,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 13.5311,
+      "step": 38
+    },
+    {
+      "epoch": 0.05488126649076517,
+      "grad_norm": 17.908649444580078,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 12.2981,
+      "step": 39
+    },
+    {
+      "epoch": 0.056288478452066845,
+      "grad_norm": 15.319343566894531,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 12.4738,
+      "step": 40
+    },
+    {
+      "epoch": 0.057695690413368514,
+      "grad_norm": 13.30446720123291,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 12.2285,
+      "step": 41
+    },
+    {
+      "epoch": 0.05910290237467018,
+      "grad_norm": 11.534811019897461,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9249,
+      "step": 42
+    },
+    {
+      "epoch": 0.06051011433597186,
+      "grad_norm": 11.204651832580566,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.4523,
+      "step": 43
+    },
+    {
+      "epoch": 0.06191732629727353,
+      "grad_norm": 10.370817184448242,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.8992,
+      "step": 44
+    },
+    {
+      "epoch": 0.0633245382585752,
+      "grad_norm": 11.466197967529297,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.8682,
+      "step": 45
+    },
+    {
+      "epoch": 0.06473175021987687,
+      "grad_norm": 11.244982719421387,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3643,
+      "step": 46
+    },
+    {
+      "epoch": 0.06613896218117854,
+      "grad_norm": 10.749483108520508,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 9.9213,
+      "step": 47
+    },
+    {
+      "epoch": 0.06754617414248021,
+      "grad_norm": 12.371052742004395,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.5542,
+      "step": 48
+    },
+    {
+      "epoch": 0.06895338610378188,
+      "grad_norm": 14.235132217407227,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.6824,
+      "step": 49
+    },
+    {
+      "epoch": 0.07036059806508356,
+      "grad_norm": 23.322162628173828,
+      "learning_rate": 1e-05,
+      "loss": 10.2417,
+      "step": 50
+    },
+    {
+      "epoch": 0.07036059806508356,
+      "eval_loss": 0.7248497605323792,
+      "eval_runtime": 3.7634,
+      "eval_samples_per_second": 13.286,
+      "eval_steps_per_second": 3.454,
+      "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": 5.145489549610189e+16,
+  "total_flos": 1.0336460735932006e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null