Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e7ae4749f60c7baea7f966a0c5a0cd390950ccaaac8e3e79b6d8f5ca0bcfe23
+oid sha256:ba56eecb610e9b252dcf5ca838a8f498e40bf7f7a9d5fb130d2eeb31c7c8af83
 size 48552

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b4efc1decb8cb63559c7f9c84e9cd2ddf1b8362ef89c959b70e7375e0fdba3c
+oid sha256:d0c130f3debb63ed6c3c6129df83c3b85b409fb79a9a074e6cd41e6a47433824
 size 113994

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02e0f631e019db639b680205f7d960bde8c74570e90727b7debf5d42a0cb1fb2
+oid sha256:eabd47cac340e9dd45fa556fe481f88eeeefe3c34bc892c4d8f534c07dfed1d6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0bb295951b1388b1d0580c1b6c65e985bf29ab43521317ae38fcaead6e18a51
+oid sha256:93efa02e393fd82984c4d13f12da89697316bc0e07677200e59e96ced22aa1b2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0c554111e855cce9e68a81eb7dfe1417d2cd468f9551afe5818bc018c036ff
+oid sha256:a6c53d2dac467dde25cb51296eef067b3d957fce9b264b23b1748dce77a20bfe
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6608e82c5cbc4340d292eb223ba83977c80063a6611bd5efa28957a5e2c9be8d
+oid sha256:8489ae9d0efbb6cebbe8acd26e55abaafa1b68e13cf3c39ae20d015ff931d26b
 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": 11.929415702819824,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.014155283459551277,
+  "best_metric": 11.928899765014648,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.028310566919102553,
   "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": 277.931,
       "eval_steps_per_second": 72.262,
       "step": 25
+    },
+    {
+      "epoch": 0.014721494797933329,
+      "grad_norm": 0.012115604244172573,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.9298,
+      "step": 26
+    },
+    {
+      "epoch": 0.015287706136315379,
+      "grad_norm": 0.015809347853064537,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.9293,
+      "step": 27
+    },
+    {
+      "epoch": 0.01585391747469743,
+      "grad_norm": 0.01634780876338482,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.9297,
+      "step": 28
+    },
+    {
+      "epoch": 0.01642012881307948,
+      "grad_norm": 0.020341364666819572,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.9294,
+      "step": 29
+    },
+    {
+      "epoch": 0.016986340151461533,
+      "grad_norm": 0.01740851253271103,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.9284,
+      "step": 30
+    },
+    {
+      "epoch": 0.017552551489843585,
+      "grad_norm": 0.019351454451680183,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.9297,
+      "step": 31
+    },
+    {
+      "epoch": 0.018118762828225634,
+      "grad_norm": 0.021286247298121452,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.9289,
+      "step": 32
+    },
+    {
+      "epoch": 0.018684974166607686,
+      "grad_norm": 0.023984717205166817,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.9305,
+      "step": 33
+    },
+    {
+      "epoch": 0.019251185504989738,
+      "grad_norm": 0.02307896316051483,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.9313,
+      "step": 34
+    },
+    {
+      "epoch": 0.01981739684337179,
+      "grad_norm": 0.026456082239747047,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.9288,
+      "step": 35
+    },
+    {
+      "epoch": 0.02038360818175384,
+      "grad_norm": 0.0284335445612669,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.9304,
+      "step": 36
+    },
+    {
+      "epoch": 0.02094981952013589,
+      "grad_norm": 0.02930847555398941,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.929,
+      "step": 37
+    },
+    {
+      "epoch": 0.021516030858517943,
+      "grad_norm": 0.018983187153935432,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.93,
+      "step": 38
+    },
+    {
+      "epoch": 0.02208224219689999,
+      "grad_norm": 0.019949011504650116,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.9298,
+      "step": 39
+    },
+    {
+      "epoch": 0.022648453535282043,
+      "grad_norm": 0.016765393316745758,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.9298,
+      "step": 40
+    },
+    {
+      "epoch": 0.023214664873664095,
+      "grad_norm": 0.015138785354793072,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.9289,
+      "step": 41
+    },
+    {
+      "epoch": 0.023780876212046147,
+      "grad_norm": 0.01913069188594818,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.9286,
+      "step": 42
+    },
+    {
+      "epoch": 0.024347087550428196,
+      "grad_norm": 0.022110899910330772,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.9294,
+      "step": 43
+    },
+    {
+      "epoch": 0.024913298888810248,
+      "grad_norm": 0.022065572440624237,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.9296,
+      "step": 44
+    },
+    {
+      "epoch": 0.0254795102271923,
+      "grad_norm": 0.02415025234222412,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.9284,
+      "step": 45
+    },
+    {
+      "epoch": 0.026045721565574352,
+      "grad_norm": 0.02194690704345703,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.9289,
+      "step": 46
+    },
+    {
+      "epoch": 0.0266119329039564,
+      "grad_norm": 0.030053917318582535,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.9295,
+      "step": 47
+    },
+    {
+      "epoch": 0.027178144242338453,
+      "grad_norm": 0.02687782235443592,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.9293,
+      "step": 48
+    },
+    {
+      "epoch": 0.027744355580720505,
+      "grad_norm": 0.028278199955821037,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.9279,
+      "step": 49
+    },
+    {
+      "epoch": 0.028310566919102553,
+      "grad_norm": 0.03565681725740433,
+      "learning_rate": 1e-05,
+      "loss": 11.9283,
+      "step": 50
+    },
+    {
+      "epoch": 0.028310566919102553,
+      "eval_loss": 11.928899765014648,
+      "eval_runtime": 0.1799,
+      "eval_samples_per_second": 277.982,
+      "eval_steps_per_second": 72.275,
+      "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": 521247129600.0,
+  "total_flos": 1042494259200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null