Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a4b6a9b253f7f5c3f08ebaaec1752afb817b77a919c5b4de1e340274194eb32
+oid sha256:0f25778d0ded37f81f1b43903c00004e687866e01f4cf1f2d5681e4fe78081a2
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d091d109bdb4da8a2aa06fb0a59321d12f49f8501e90a2e1ceb371b23e3d199
+oid sha256:85bb1194d37f09ebc88c77635eb8c7677a2d0fda9e305f3b474167c860bd1823
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8810876ec70366ff78dfe47bca9a9ccd165393c11d36bc8ba1b3d5f40ad9cd47
+oid sha256:93608443aa1a4e247da46a4ff1e94dc4f53b056fef3243903ce3e04dddde005a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c199d44e0948e0693c7adfc31e6dcd6a3dc95d790d65188ed34a9a865d3c38e7
+oid sha256:c5866de4cbc71db968263c1348cdd8f6192d16d28d611af9030473c2242f3c97
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64e4d4b399f46410e19b34be80eff4132b867ff8e99e1633db5a70287d980f02
+oid sha256:a32e99bd70aa1f1bfe023021d325bece78ce7280729ba9b5bcd261db87f14d6a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e248a56b95a5a06aac8d1d92617a786e9f9537c6398119cb0885e4956684ae1a
+oid sha256:bd3a72f2126afb82a66476e1cb540604f4bb09462d8c2eaf14ea8b59ee1499f2
 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": 4.229829788208008,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0648403306856865,
+  "best_metric": 4.0636701583862305,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.129680661371373,
   "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": 43.278,
       "eval_steps_per_second": 11.252,
       "step": 25
+    },
+    {
+      "epoch": 0.06743394391311396,
+      "grad_norm": 1.1068377494812012,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 4.0776,
+      "step": 26
+    },
+    {
+      "epoch": 0.07002755714054142,
+      "grad_norm": 1.0573188066482544,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 4.0905,
+      "step": 27
+    },
+    {
+      "epoch": 0.07262117036796888,
+      "grad_norm": 1.0603560209274292,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 4.1695,
+      "step": 28
+    },
+    {
+      "epoch": 0.07521478359539634,
+      "grad_norm": 1.1383318901062012,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 4.2141,
+      "step": 29
+    },
+    {
+      "epoch": 0.0778083968228238,
+      "grad_norm": 1.0839500427246094,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 4.2506,
+      "step": 30
+    },
+    {
+      "epoch": 0.08040201005025126,
+      "grad_norm": 0.967460036277771,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 4.1442,
+      "step": 31
+    },
+    {
+      "epoch": 0.08299562327767872,
+      "grad_norm": 0.9629656672477722,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 4.0578,
+      "step": 32
+    },
+    {
+      "epoch": 0.08558923650510618,
+      "grad_norm": 1.2750022411346436,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.2702,
+      "step": 33
+    },
+    {
+      "epoch": 0.08818284973253364,
+      "grad_norm": 1.3888616561889648,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.2641,
+      "step": 34
+    },
+    {
+      "epoch": 0.0907764629599611,
+      "grad_norm": 1.6543223857879639,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.3656,
+      "step": 35
+    },
+    {
+      "epoch": 0.09337007618738856,
+      "grad_norm": 1.957236409187317,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 4.3184,
+      "step": 36
+    },
+    {
+      "epoch": 0.09596368941481602,
+      "grad_norm": 2.900848627090454,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.1326,
+      "step": 37
+    },
+    {
+      "epoch": 0.09855730264224348,
+      "grad_norm": 1.2549171447753906,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.9195,
+      "step": 38
+    },
+    {
+      "epoch": 0.10115091586967094,
+      "grad_norm": 0.8486330509185791,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 4.0072,
+      "step": 39
+    },
+    {
+      "epoch": 0.1037445290970984,
+      "grad_norm": 0.8748946189880371,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 4.1093,
+      "step": 40
+    },
+    {
+      "epoch": 0.10633814232452586,
+      "grad_norm": 0.8913637399673462,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.9297,
+      "step": 41
+    },
+    {
+      "epoch": 0.10893175555195332,
+      "grad_norm": 0.9824759364128113,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.9566,
+      "step": 42
+    },
+    {
+      "epoch": 0.11152536877938077,
+      "grad_norm": 0.8479898571968079,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 4.084,
+      "step": 43
+    },
+    {
+      "epoch": 0.11411898200680823,
+      "grad_norm": 0.8927655816078186,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.0899,
+      "step": 44
+    },
+    {
+      "epoch": 0.11671259523423569,
+      "grad_norm": 0.931806743144989,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.1325,
+      "step": 45
+    },
+    {
+      "epoch": 0.11930620846166315,
+      "grad_norm": 1.0513771772384644,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.1224,
+      "step": 46
+    },
+    {
+      "epoch": 0.12189982168909061,
+      "grad_norm": 1.2372894287109375,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 4.293,
+      "step": 47
+    },
+    {
+      "epoch": 0.12449343491651807,
+      "grad_norm": 1.6081628799438477,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.1659,
+      "step": 48
+    },
+    {
+      "epoch": 0.12708704814394553,
+      "grad_norm": 2.187530040740967,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.1753,
+      "step": 49
+    },
+    {
+      "epoch": 0.129680661371373,
+      "grad_norm": 4.7116546630859375,
+      "learning_rate": 1e-05,
+      "loss": 3.9957,
+      "step": 50
+    },
+    {
+      "epoch": 0.129680661371373,
+      "eval_loss": 4.0636701583862305,
+      "eval_runtime": 1.1579,
+      "eval_samples_per_second": 43.181,
+      "eval_steps_per_second": 11.227,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null