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:a1873ccc80d76ae689d504e013af0779488cb34f698f6f527614a5729056b48e
+oid sha256:f836b0400f2ceeb7564fa71ad03ed22f31b21bd52ec8cca584d351bec17840cb
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98af9c656f66c4cfb376a7b615a35ae068c91300a618c3495660d67e5dc41979
+oid sha256:b329c5604044810ea10f9869194bdf4bb60a8f6a94e748aa5499b482fafa07b2
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28163f65f26c28f5c62cf4ba3e5b7d1e4f61abb279fbb214a5313a94e4dd3a14
+oid sha256:f5c4c88e724642a95704eb7a874a845b9c89ac24730430cc45e49bca3d8b4e9a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46faf8dc41226289080972d0a1fce346950cdc6cd3185de2dd224abacfc60fbe
+oid sha256:518cdefcb037d548ada20a383fbd7f349a68f3cb0252db1d2fbe4f956b34323a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38286669275030d493097e2d3f4559eedf1a0e24bc30852f10f1cff922e4dd7b
+oid sha256:edd82677a3c256ce1965e15fb2bd41976e7dd21bc2e1b47262bc810c06beff1f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57755f333af0a42cb3c8cfcee6258281861a86ab3a4de41f77378e89348e3134
+oid sha256:e124b0815d369b0e013f9199830535d960aff072be480bd75c011540957d74f6
 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": 0.9173004627227783,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.12543116964565695,
+  "best_metric": 0.8755273222923279,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2508623392913139,
   "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": 10.859,
       "eval_steps_per_second": 2.823,
       "step": 25
+    },
+    {
+      "epoch": 0.13044841643148322,
+      "grad_norm": 7.0074028968811035,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 14.6113,
+      "step": 26
+    },
+    {
+      "epoch": 0.1354656632173095,
+      "grad_norm": 7.817895412445068,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 15.3695,
+      "step": 27
+    },
+    {
+      "epoch": 0.14048291000313579,
+      "grad_norm": 6.956982612609863,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 15.822,
+      "step": 28
+    },
+    {
+      "epoch": 0.14550015678896205,
+      "grad_norm": 4.960094928741455,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 15.6277,
+      "step": 29
+    },
+    {
+      "epoch": 0.15051740357478832,
+      "grad_norm": 4.474605560302734,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 15.7418,
+      "step": 30
+    },
+    {
+      "epoch": 0.15553465036061462,
+      "grad_norm": 4.103686809539795,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 13.9589,
+      "step": 31
+    },
+    {
+      "epoch": 0.1605518971464409,
+      "grad_norm": 5.2068376541137695,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 13.031,
+      "step": 32
+    },
+    {
+      "epoch": 0.16556914393226718,
+      "grad_norm": 4.783890724182129,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 12.818,
+      "step": 33
+    },
+    {
+      "epoch": 0.17058639071809345,
+      "grad_norm": 4.218921661376953,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 13.144,
+      "step": 34
+    },
+    {
+      "epoch": 0.17560363750391972,
+      "grad_norm": 3.8665473461151123,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 13.379,
+      "step": 35
+    },
+    {
+      "epoch": 0.18062088428974601,
+      "grad_norm": 3.703275442123413,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 13.6023,
+      "step": 36
+    },
+    {
+      "epoch": 0.18563813107557228,
+      "grad_norm": 3.7159953117370605,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 13.6124,
+      "step": 37
+    },
+    {
+      "epoch": 0.19065537786139855,
+      "grad_norm": 3.394871950149536,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 14.1037,
+      "step": 38
+    },
+    {
+      "epoch": 0.19567262464722485,
+      "grad_norm": 4.415946960449219,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 14.1554,
+      "step": 39
+    },
+    {
+      "epoch": 0.20068987143305111,
+      "grad_norm": 4.950469970703125,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 15.051,
+      "step": 40
+    },
+    {
+      "epoch": 0.20570711821887738,
+      "grad_norm": 4.831371307373047,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 14.5962,
+      "step": 41
+    },
+    {
+      "epoch": 0.21072436500470368,
+      "grad_norm": 4.842825889587402,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 15.6923,
+      "step": 42
+    },
+    {
+      "epoch": 0.21574161179052995,
+      "grad_norm": 4.159366130828857,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 15.3636,
+      "step": 43
+    },
+    {
+      "epoch": 0.22075885857635622,
+      "grad_norm": 3.6262786388397217,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 13.3886,
+      "step": 44
+    },
+    {
+      "epoch": 0.2257761053621825,
+      "grad_norm": 2.7398009300231934,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 12.5319,
+      "step": 45
+    },
+    {
+      "epoch": 0.23079335214800878,
+      "grad_norm": 2.7315304279327393,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 12.5121,
+      "step": 46
+    },
+    {
+      "epoch": 0.23581059893383505,
+      "grad_norm": 3.2367587089538574,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 12.881,
+      "step": 47
+    },
+    {
+      "epoch": 0.24082784571966134,
+      "grad_norm": 3.7576241493225098,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 13.4895,
+      "step": 48
+    },
+    {
+      "epoch": 0.2458450925054876,
+      "grad_norm": 4.879652500152588,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 14.1439,
+      "step": 49
+    },
+    {
+      "epoch": 0.2508623392913139,
+      "grad_norm": 4.576759338378906,
+      "learning_rate": 1e-05,
+      "loss": 13.8784,
+      "step": 50
+    },
+    {
+      "epoch": 0.2508623392913139,
+      "eval_loss": 0.8755273222923279,
+      "eval_runtime": 4.9809,
+      "eval_samples_per_second": 10.038,
+      "eval_steps_per_second": 2.61,
+      "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": 3.949258989581107e+17,
+  "total_flos": 7.849213880612946e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null