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:f4bde64c2c8a0d8a303ac85e37ca66c0bf0ffc1d73155ee7e933539324b5cdc9
+oid sha256:4debf178ee15f14a197fbabec920ac2ce85a1c9cdc29e4f3138f46023eb37581
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa33b34bea9a574d755eec112be0cbf4375ff9af9f9afe1d62507fb36d697375
+oid sha256:8f4bb931e31246b51b4175d22de699125daae33fadb06f1ff24591bc6b96b4f7
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e23f8e22f6c245c6438d7fb861687ce26d591287a286d614164e1e0c6d84656
+oid sha256:cb43a1f1b073b4cf93add74404432e7ffc493c608655ce5a3d8d3811296bee8a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce091ebfd8af42ec91c7d82c88aaa4a82ebdb1cbf4c13369b8cc6a3e8958ad11
+oid sha256:9ef99c01e0affd5de27185394d47b9cc326e92873aa8cdde07ecf6dcd1abb5ff
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:759880a4da7f411f233050cdc026df16334eb5d7a56e6bf97e8b06afa6e84f1b
+oid sha256:46658ed7ccf5952f5a4f4add6a1f87eb8141a9a925fd15b933532736b4988865
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cf0e95b8f01678c2b27775c93868eccb97b9fa2b883c36967c1a71662f05054
+oid sha256:f8b6d0548dbce6e373356f0b89dc1731d23be5efc10fecde7f034e067abfd40c
 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": 2.3962597846984863,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.009206407659731172,
+  "best_metric": 2.300698757171631,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.018412815319462345,
   "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": 33.898,
       "eval_steps_per_second": 8.813,
       "step": 25
+    },
+    {
+      "epoch": 0.00957466396612042,
+      "grad_norm": 0.6010366678237915,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.6247,
+      "step": 26
+    },
+    {
+      "epoch": 0.009942920272509667,
+      "grad_norm": 0.8184590935707092,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.8737,
+      "step": 27
+    },
+    {
+      "epoch": 0.010311176578898913,
+      "grad_norm": 0.7789363265037537,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.0136,
+      "step": 28
+    },
+    {
+      "epoch": 0.010679432885288161,
+      "grad_norm": 0.6929258108139038,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.0049,
+      "step": 29
+    },
+    {
+      "epoch": 0.011047689191677408,
+      "grad_norm": 0.6341331601142883,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.0244,
+      "step": 30
+    },
+    {
+      "epoch": 0.011415945498066654,
+      "grad_norm": 0.6360584497451782,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.0533,
+      "step": 31
+    },
+    {
+      "epoch": 0.0117842018044559,
+      "grad_norm": 0.6871073246002197,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.193,
+      "step": 32
+    },
+    {
+      "epoch": 0.012152458110845149,
+      "grad_norm": 0.7307798862457275,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.1686,
+      "step": 33
+    },
+    {
+      "epoch": 0.012520714417234395,
+      "grad_norm": 0.8923740386962891,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.2811,
+      "step": 34
+    },
+    {
+      "epoch": 0.012888970723623642,
+      "grad_norm": 1.1610867977142334,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.533,
+      "step": 35
+    },
+    {
+      "epoch": 0.01325722703001289,
+      "grad_norm": 1.322665810585022,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.8074,
+      "step": 36
+    },
+    {
+      "epoch": 0.013625483336402136,
+      "grad_norm": 1.953356385231018,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.9117,
+      "step": 37
+    },
+    {
+      "epoch": 0.013993739642791382,
+      "grad_norm": 0.6058061122894287,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.6222,
+      "step": 38
+    },
+    {
+      "epoch": 0.014361995949180629,
+      "grad_norm": 0.48876795172691345,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.7171,
+      "step": 39
+    },
+    {
+      "epoch": 0.014730252255569877,
+      "grad_norm": 0.5596562623977661,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.8393,
+      "step": 40
+    },
+    {
+      "epoch": 0.015098508561959123,
+      "grad_norm": 0.540923535823822,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.9241,
+      "step": 41
+    },
+    {
+      "epoch": 0.01546676486834837,
+      "grad_norm": 0.6124505996704102,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.9227,
+      "step": 42
+    },
+    {
+      "epoch": 0.015835021174737618,
+      "grad_norm": 0.6569370031356812,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.9246,
+      "step": 43
+    },
+    {
+      "epoch": 0.016203277481126863,
+      "grad_norm": 0.6232062578201294,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.0976,
+      "step": 44
+    },
+    {
+      "epoch": 0.01657153378751611,
+      "grad_norm": 0.7638946175575256,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.0661,
+      "step": 45
+    },
+    {
+      "epoch": 0.01693979009390536,
+      "grad_norm": 0.7543624639511108,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.2258,
+      "step": 46
+    },
+    {
+      "epoch": 0.017308046400294604,
+      "grad_norm": 0.8359889984130859,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.2464,
+      "step": 47
+    },
+    {
+      "epoch": 0.01767630270668385,
+      "grad_norm": 0.983206033706665,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.4463,
+      "step": 48
+    },
+    {
+      "epoch": 0.0180445590130731,
+      "grad_norm": 1.324151873588562,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.7316,
+      "step": 49
+    },
+    {
+      "epoch": 0.018412815319462345,
+      "grad_norm": 3.246047258377075,
+      "learning_rate": 1e-05,
+      "loss": 3.102,
+      "step": 50
+    },
+    {
+      "epoch": 0.018412815319462345,
+      "eval_loss": 2.300698757171631,
+      "eval_runtime": 1.4858,
+      "eval_samples_per_second": 33.653,
+      "eval_steps_per_second": 8.75,
+      "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": 7.952285976808653e+16,
+  "total_flos": 1.5899604877626573e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null