Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93a99c5b2cade393f7717ad17a266c40b08c4e552ba086a5b0d8b2d4583d1a46
+oid sha256:e5267572b8b64a73cec83b37e51e4f28cfb96b6de8c31ea935ec121a9193bfc1
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39527f4b378bc4e823a19c18b34bf33cb288315eec935d97bf5829494e3f68b6
+oid sha256:65f0de1586dcdc6a96891c9fd37d779a7baaa744a3d4c582167eb696b56e152d
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f476f38c40308300e25a08aaaf5ec0407fd41415ab123af85405e94fe7d1e1f
+oid sha256:9dc821a4f62575115d95bb6fcc9693ee06bea8b5de152974e4e57fcc4e122d15
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b1c41a5d01b21bed203c7f4ca62e2110aa1b5cc0ec1b40dcdf4c80d4a2172ec
+oid sha256:c44d12db03c74bb3d3a93f84ed348368d6ef02283c7e7ccd94838540924f8724
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a500fdac37951d7407ac53a1699ea107e419558c9b2e80f077999370b81458e1
+oid sha256:64eb2177a7ca7560c03e51f33cf7f79033155983bddc4e6963dd5449fb2b10c0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4167ddb12e979c43932e7cc77fd219c7776d021a7ec931043ea540a30932839
+oid sha256:eaf8b77a4b1f8563bcb567c53f6ceae071db0dd3dcbdccaf72d64849845d6879
 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": 2.184957981109619,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.043936731107205626,
+  "best_metric": 2.1184535026550293,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08787346221441125,
   "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": 24.437,
       "eval_steps_per_second": 6.354,
       "step": 25
+    },
+    {
+      "epoch": 0.04569420035149385,
+      "grad_norm": 6.682544231414795,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 35.104,
+      "step": 26
+    },
+    {
+      "epoch": 0.04745166959578207,
+      "grad_norm": 5.638045787811279,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 35.0024,
+      "step": 27
+    },
+    {
+      "epoch": 0.0492091388400703,
+      "grad_norm": 5.364726543426514,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 34.663,
+      "step": 28
+    },
+    {
+      "epoch": 0.050966608084358524,
+      "grad_norm": 5.238322734832764,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 35.3332,
+      "step": 29
+    },
+    {
+      "epoch": 0.05272407732864675,
+      "grad_norm": 4.853617191314697,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 34.6261,
+      "step": 30
+    },
+    {
+      "epoch": 0.054481546572934976,
+      "grad_norm": 4.672550678253174,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 34.2556,
+      "step": 31
+    },
+    {
+      "epoch": 0.056239015817223195,
+      "grad_norm": 5.044317722320557,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 35.2622,
+      "step": 32
+    },
+    {
+      "epoch": 0.05799648506151142,
+      "grad_norm": 4.753660202026367,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 34.329,
+      "step": 33
+    },
+    {
+      "epoch": 0.05975395430579965,
+      "grad_norm": 5.342644691467285,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 33.9036,
+      "step": 34
+    },
+    {
+      "epoch": 0.061511423550087874,
+      "grad_norm": 5.310150146484375,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 34.2209,
+      "step": 35
+    },
+    {
+      "epoch": 0.0632688927943761,
+      "grad_norm": 5.2009806632995605,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 34.3841,
+      "step": 36
+    },
+    {
+      "epoch": 0.06502636203866433,
+      "grad_norm": 6.031763076782227,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 34.0815,
+      "step": 37
+    },
+    {
+      "epoch": 0.06678383128295255,
+      "grad_norm": 6.2134504318237305,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 34.21,
+      "step": 38
+    },
+    {
+      "epoch": 0.06854130052724078,
+      "grad_norm": 5.3948974609375,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 34.3695,
+      "step": 39
+    },
+    {
+      "epoch": 0.070298769771529,
+      "grad_norm": 5.243184566497803,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 33.6793,
+      "step": 40
+    },
+    {
+      "epoch": 0.07205623901581722,
+      "grad_norm": 4.971773624420166,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 34.1816,
+      "step": 41
+    },
+    {
+      "epoch": 0.07381370826010544,
+      "grad_norm": 4.651072025299072,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 33.9473,
+      "step": 42
+    },
+    {
+      "epoch": 0.07557117750439367,
+      "grad_norm": 4.51092529296875,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 34.2455,
+      "step": 43
+    },
+    {
+      "epoch": 0.0773286467486819,
+      "grad_norm": 4.373141288757324,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 34.1921,
+      "step": 44
+    },
+    {
+      "epoch": 0.07908611599297012,
+      "grad_norm": 4.692596912384033,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 34.3758,
+      "step": 45
+    },
+    {
+      "epoch": 0.08084358523725835,
+      "grad_norm": 4.683785438537598,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 33.96,
+      "step": 46
+    },
+    {
+      "epoch": 0.08260105448154657,
+      "grad_norm": 5.398478031158447,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 34.4189,
+      "step": 47
+    },
+    {
+      "epoch": 0.0843585237258348,
+      "grad_norm": 5.291502952575684,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 34.3325,
+      "step": 48
+    },
+    {
+      "epoch": 0.08611599297012303,
+      "grad_norm": 5.439122200012207,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 33.6364,
+      "step": 49
+    },
+    {
+      "epoch": 0.08787346221441125,
+      "grad_norm": 7.769702434539795,
+      "learning_rate": 1e-05,
+      "loss": 33.6672,
+      "step": 50
+    },
+    {
+      "epoch": 0.08787346221441125,
+      "eval_loss": 2.1184535026550293,
+      "eval_runtime": 2.0483,
+      "eval_samples_per_second": 24.411,
+      "eval_steps_per_second": 6.347,
+      "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": 1.483568811343872e+17,
+  "total_flos": 2.967137622687744e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null