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:f4fa71450755db8eb8a68a7284d43cc25f27546e6c437f11b99ec33a0f557bc3
+oid sha256:e5dd857376f98dbed81392a4bae1aa8e25c67147586817e7a47d84676c736148
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e2a21d586e1c936555ac9c0f9dec05d14e5fc80dd2f68b7ecc6e8550a4c604
+oid sha256:d1665749d77cd47c558a0104ea052627aee88b82e9d4a2c96f4a3618684b3a9f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db4f07d67d54d274733037462f8faee8b30015e5139a87d25c24433dc3738223
+oid sha256:e8aca73e736cdfe4a02c655642e6856f680aa1ada63c0b15390da1d6102698d3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a1ea1a741912726e5d67a4046d240c06c8e1e0dc62cbece4df1a7d5ffa63c8c8
+oid sha256:35f65f586c8c381722b6bc6e9c57617f69522e9e99b6a479588f49df74b48e24
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f36b439d6303b7be97384489e87064e76295923812cf8337b599104fe588b49
+oid sha256:13d2a47b30fe9a151a186948006919707308f3eed49642acec1abeec00f15691
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42e7576cc1038aa508f94802bd82a38fa5fc55c2ef5fc04ba208298b303fc8d3
+oid sha256:0be6fc10d5009ac21fda134640c52d86130294a0fef3fe64ff434c1559fa2fe9
 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": 0.0913226529955864,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.4700352526439483,
+  "best_metric": 0.07823102176189423,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.9400705052878966,
   "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": 9.409,
       "eval_steps_per_second": 2.446,
       "step": 25
+    },
+    {
+      "epoch": 0.4888366627497062,
+      "grad_norm": 0.07355140149593353,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0664,
+      "step": 26
+    },
+    {
+      "epoch": 0.5076380728554641,
+      "grad_norm": 0.09695981442928314,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0782,
+      "step": 27
+    },
+    {
+      "epoch": 0.5264394829612221,
+      "grad_norm": 0.10992906242609024,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0901,
+      "step": 28
+    },
+    {
+      "epoch": 0.54524089306698,
+      "grad_norm": 0.12939049303531647,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0932,
+      "step": 29
+    },
+    {
+      "epoch": 0.564042303172738,
+      "grad_norm": 0.13968101143836975,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0948,
+      "step": 30
+    },
+    {
+      "epoch": 0.5828437132784959,
+      "grad_norm": 0.13001416623592377,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0851,
+      "step": 31
+    },
+    {
+      "epoch": 0.6016451233842538,
+      "grad_norm": 0.12713101506233215,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0955,
+      "step": 32
+    },
+    {
+      "epoch": 0.6204465334900118,
+      "grad_norm": 0.12246720492839813,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0975,
+      "step": 33
+    },
+    {
+      "epoch": 0.6392479435957696,
+      "grad_norm": 0.14322993159294128,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.1107,
+      "step": 34
+    },
+    {
+      "epoch": 0.6580493537015276,
+      "grad_norm": 0.13620127737522125,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0914,
+      "step": 35
+    },
+    {
+      "epoch": 0.6768507638072856,
+      "grad_norm": 0.15739606320858002,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.1033,
+      "step": 36
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 0.1808631420135498,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0984,
+      "step": 37
+    },
+    {
+      "epoch": 0.7144535840188014,
+      "grad_norm": 0.04972299933433533,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0567,
+      "step": 38
+    },
+    {
+      "epoch": 0.7332549941245593,
+      "grad_norm": 0.05645684152841568,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0602,
+      "step": 39
+    },
+    {
+      "epoch": 0.7520564042303173,
+      "grad_norm": 0.06678657978773117,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0685,
+      "step": 40
+    },
+    {
+      "epoch": 0.7708578143360753,
+      "grad_norm": 0.08744647353887558,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0779,
+      "step": 41
+    },
+    {
+      "epoch": 0.7896592244418331,
+      "grad_norm": 0.10616064816713333,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0799,
+      "step": 42
+    },
+    {
+      "epoch": 0.8084606345475911,
+      "grad_norm": 0.11365273594856262,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.0825,
+      "step": 43
+    },
+    {
+      "epoch": 0.827262044653349,
+      "grad_norm": 0.09806361794471741,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0878,
+      "step": 44
+    },
+    {
+      "epoch": 0.8460634547591069,
+      "grad_norm": 0.11302643269300461,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0881,
+      "step": 45
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 0.10468102991580963,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0962,
+      "step": 46
+    },
+    {
+      "epoch": 0.8836662749706228,
+      "grad_norm": 0.11554855108261108,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0893,
+      "step": 47
+    },
+    {
+      "epoch": 0.9024676850763808,
+      "grad_norm": 0.10484100878238678,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0817,
+      "step": 48
+    },
+    {
+      "epoch": 0.9212690951821386,
+      "grad_norm": 0.14057570695877075,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.094,
+      "step": 49
+    },
+    {
+      "epoch": 0.9400705052878966,
+      "grad_norm": 0.2136404663324356,
+      "learning_rate": 1e-05,
+      "loss": 0.0722,
+      "step": 50
+    },
+    {
+      "epoch": 0.9400705052878966,
+      "eval_loss": 0.07823102176189423,
+      "eval_runtime": 5.3305,
+      "eval_samples_per_second": 9.38,
+      "eval_steps_per_second": 2.439,
+      "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": 3.09221331952468e+17,
+  "total_flos": 6.196549313091338e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null