Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:068579d0bd6a8c0376f41f0137bc0b655745b413a1a22b13fe8c0e34ca4b0e75
+oid sha256:c202dcb323e671dee620d79fad8fafcb9fca199178b032be345b234d151bd890
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1610cd41c7681b9e610b5fb3f002f92ca14b96f50439300caee43dfcf8d1b145
+oid sha256:108b82df65d3de846cf210651485202691852a65418881aa07e83a3bd933dce9
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:435f9c5515e5dadecfc3bb5ec27b943635e55f441836e96e6d2b428d3d0b5e23
+oid sha256:662b3af3afccb427bbaba8887715540fcc035c071a766681b89fd98d5564317d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9167cd7132c45892202ff4aa4dc3ac11f6ba15dc52495ccbb70003e17093e3e
+oid sha256:d769099072dc06b002ea2d79319d0419e115a16ca6771113aab51bff4a86191d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:967c052fdb274f96bfd1edc249fa586018e536d154ada9a041589fc9ecaf6b41
+oid sha256:854e2f104af2cd3fa0c2a3def4e117851e44cceb92866c22c5329853917d0b34
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b48312b00b92b67120e144c85aa15c95739a19bdacfde0e51bfd094c6b6a44d0
+oid sha256:3b1a5034fa093037c27b221b5d315a03298e6429f08019499f7e3fa828c90401
 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": 1.867378830909729,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22271714922049,
+  "best_metric": 1.733738899230957,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.44543429844098,
   "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": 58.887,
       "eval_steps_per_second": 15.311,
       "step": 25
+    },
+    {
+      "epoch": 0.23162583518930957,
+      "grad_norm": 0.33165210485458374,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.5981,
+      "step": 26
+    },
+    {
+      "epoch": 0.24053452115812918,
+      "grad_norm": 0.7488612532615662,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.6941,
+      "step": 27
+    },
+    {
+      "epoch": 0.24944320712694878,
+      "grad_norm": 0.861705482006073,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.9993,
+      "step": 28
+    },
+    {
+      "epoch": 0.2583518930957684,
+      "grad_norm": 1.0878539085388184,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.8833,
+      "step": 29
+    },
+    {
+      "epoch": 0.267260579064588,
+      "grad_norm": 0.8501808047294617,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.9919,
+      "step": 30
+    },
+    {
+      "epoch": 0.27616926503340755,
+      "grad_norm": 0.669116735458374,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.0127,
+      "step": 31
+    },
+    {
+      "epoch": 0.28507795100222716,
+      "grad_norm": 0.5088751316070557,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.9827,
+      "step": 32
+    },
+    {
+      "epoch": 0.29398663697104677,
+      "grad_norm": 0.4590938687324524,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.8001,
+      "step": 33
+    },
+    {
+      "epoch": 0.3028953229398664,
+      "grad_norm": 0.6814666986465454,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.8414,
+      "step": 34
+    },
+    {
+      "epoch": 0.311804008908686,
+      "grad_norm": 0.9811885356903076,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.7625,
+      "step": 35
+    },
+    {
+      "epoch": 0.3207126948775056,
+      "grad_norm": 1.4614307880401611,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.6748,
+      "step": 36
+    },
+    {
+      "epoch": 0.32962138084632514,
+      "grad_norm": 3.0398764610290527,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.637,
+      "step": 37
+    },
+    {
+      "epoch": 0.33853006681514475,
+      "grad_norm": 0.33289289474487305,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.6686,
+      "step": 38
+    },
+    {
+      "epoch": 0.34743875278396436,
+      "grad_norm": 0.26579251885414124,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.4826,
+      "step": 39
+    },
+    {
+      "epoch": 0.35634743875278396,
+      "grad_norm": 0.3095352053642273,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.7352,
+      "step": 40
+    },
+    {
+      "epoch": 0.36525612472160357,
+      "grad_norm": 0.3182210922241211,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.7885,
+      "step": 41
+    },
+    {
+      "epoch": 0.3741648106904232,
+      "grad_norm": 0.26366835832595825,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.9453,
+      "step": 42
+    },
+    {
+      "epoch": 0.3830734966592428,
+      "grad_norm": 0.3004477620124817,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.8818,
+      "step": 43
+    },
+    {
+      "epoch": 0.39198218262806234,
+      "grad_norm": 0.33916527032852173,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.9296,
+      "step": 44
+    },
+    {
+      "epoch": 0.40089086859688194,
+      "grad_norm": 0.3385569453239441,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.8835,
+      "step": 45
+    },
+    {
+      "epoch": 0.40979955456570155,
+      "grad_norm": 0.38246041536331177,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.8184,
+      "step": 46
+    },
+    {
+      "epoch": 0.41870824053452116,
+      "grad_norm": 0.5052685737609863,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.7671,
+      "step": 47
+    },
+    {
+      "epoch": 0.42761692650334077,
+      "grad_norm": 0.7465808987617493,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.8135,
+      "step": 48
+    },
+    {
+      "epoch": 0.4365256124721604,
+      "grad_norm": 1.7329742908477783,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.6015,
+      "step": 49
+    },
+    {
+      "epoch": 0.44543429844098,
+      "grad_norm": 4.2306718826293945,
+      "learning_rate": 1e-05,
+      "loss": 2.0812,
+      "step": 50
+    },
+    {
+      "epoch": 0.44543429844098,
+      "eval_loss": 1.733738899230957,
+      "eval_runtime": 0.8419,
+      "eval_samples_per_second": 59.39,
+      "eval_steps_per_second": 15.441,
+      "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": 5.314237029574246e+16,
+  "total_flos": 1.0621851957775565e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null