Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c2adc1ba00ad2384d443c42d9c5efb5f44f42d9cf9ba2128c7e2a6c72435a4
+oid sha256:e4e50b14f94da2daa79d306b02111126e283a698324941ee85f308a5702c0f95
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:221c1cc69fb8acb56a2372bd6526af7186749759fbaf15114ad038b4e8a41bb5
+oid sha256:fdf687708a0c83534885a39fbbdc3f4522a18cd4f5c6f62943b35f45c5a34c33
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1245b593cfd81eb5c4f50ea8dd9c2e6a47ae7ca0d4e08d182d5f36842ec93607
+oid sha256:f1839eb08ca6673cdfcb538c0b7551c22d894e7b6413e2e974d2e47522ec944e
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f06a03a0f7e432c77c5180a8debb5d1251a68dbfa302e144f7a9bc6ea1b5047
+oid sha256:b869c320a8f87f7c44c8b4aba24e436a06d89c5adcfc69fa5bc7a4911e4b3f60
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a4e35e8d2e82611c9eb6a4a27d6aece193eaec9bb3463d639f39117994bf3009
+oid sha256:159ca932fc6a352b7d45c3c17b5174315479802806bd2f1286d1b3d0fee3c92a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2815b44eb11f98051eaa3c3da29d41127294040d00e1cc5c12e73ac139bcc003
+oid sha256:ce005b4fe8c698a7192f226eb4b1a3645a38cce1df043d8645fda472c43ee044
 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": 0.33292338252067566,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.411946446961895,
+  "best_metric": 0.3155190348625183,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.82389289392379,
   "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": 14.668,
       "eval_steps_per_second": 3.814,
       "step": 25
+    },
+    {
+      "epoch": 0.42842430484037075,
+      "grad_norm": 0.18853461742401123,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.3328,
+      "step": 26
+    },
+    {
+      "epoch": 0.44490216271884653,
+      "grad_norm": 0.18606941401958466,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3313,
+      "step": 27
+    },
+    {
+      "epoch": 0.46138002059732236,
+      "grad_norm": 0.17483149468898773,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.3425,
+      "step": 28
+    },
+    {
+      "epoch": 0.47785787847579814,
+      "grad_norm": 0.16114626824855804,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.3457,
+      "step": 29
+    },
+    {
+      "epoch": 0.49433573635427397,
+      "grad_norm": 0.1405235081911087,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.3297,
+      "step": 30
+    },
+    {
+      "epoch": 0.5108135942327497,
+      "grad_norm": 0.14927256107330322,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.3449,
+      "step": 31
+    },
+    {
+      "epoch": 0.5272914521112255,
+      "grad_norm": 0.1491021066904068,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.3239,
+      "step": 32
+    },
+    {
+      "epoch": 0.5437693099897013,
+      "grad_norm": 0.16267071664333344,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.3352,
+      "step": 33
+    },
+    {
+      "epoch": 0.5602471678681772,
+      "grad_norm": 0.17398034036159515,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.337,
+      "step": 34
+    },
+    {
+      "epoch": 0.576725025746653,
+      "grad_norm": 0.17694611847400665,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.3431,
+      "step": 35
+    },
+    {
+      "epoch": 0.5932028836251287,
+      "grad_norm": 0.1907595545053482,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.3508,
+      "step": 36
+    },
+    {
+      "epoch": 0.6096807415036045,
+      "grad_norm": 0.19792760908603668,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.346,
+      "step": 37
+    },
+    {
+      "epoch": 0.6261585993820803,
+      "grad_norm": 0.14731112122535706,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.3419,
+      "step": 38
+    },
+    {
+      "epoch": 0.6426364572605562,
+      "grad_norm": 0.13974687457084656,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.3171,
+      "step": 39
+    },
+    {
+      "epoch": 0.659114315139032,
+      "grad_norm": 0.13829131424427032,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.3243,
+      "step": 40
+    },
+    {
+      "epoch": 0.6755921730175077,
+      "grad_norm": 0.14247848093509674,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.3243,
+      "step": 41
+    },
+    {
+      "epoch": 0.6920700308959835,
+      "grad_norm": 0.13794369995594025,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.3124,
+      "step": 42
+    },
+    {
+      "epoch": 0.7085478887744593,
+      "grad_norm": 0.14684930443763733,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.3349,
+      "step": 43
+    },
+    {
+      "epoch": 0.7250257466529351,
+      "grad_norm": 0.14855115115642548,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.3223,
+      "step": 44
+    },
+    {
+      "epoch": 0.741503604531411,
+      "grad_norm": 0.14544209837913513,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.3217,
+      "step": 45
+    },
+    {
+      "epoch": 0.7579814624098867,
+      "grad_norm": 0.14910568296909332,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.3327,
+      "step": 46
+    },
+    {
+      "epoch": 0.7744593202883625,
+      "grad_norm": 0.15653206408023834,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.32,
+      "step": 47
+    },
+    {
+      "epoch": 0.7909371781668383,
+      "grad_norm": 0.16259266436100006,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.3559,
+      "step": 48
+    },
+    {
+      "epoch": 0.8074150360453141,
+      "grad_norm": 0.17047616839408875,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.3474,
+      "step": 49
+    },
+    {
+      "epoch": 0.82389289392379,
+      "grad_norm": 0.20054012537002563,
+      "learning_rate": 1e-05,
+      "loss": 0.3683,
+      "step": 50
+    },
+    {
+      "epoch": 0.82389289392379,
+      "eval_loss": 0.3155190348625183,
+      "eval_runtime": 3.4182,
+      "eval_samples_per_second": 14.628,
+      "eval_steps_per_second": 3.803,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null