Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1333d8874db6768d3f67060d190c344d0729d80f6ed371445bdc52d4114728f3
+oid sha256:24bc710aac7cb220dc1b71998c97248b6d57c5ce7710ae3496a817e5f2d5d8a9
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21943f1c98304f406bf06cf8a3be30196cf381dad10b5cb5648920b79bcecd9e
+oid sha256:af553fa0452b5126d1315b7b13761378efa8cdf6cd1061e660f0faf3a097e2be
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc21a784a7373adfa626eb3dbef4a9d0fcded4d6eb421d820be33e7400bafa60
+oid sha256:a9d1314f0775f6d7ea7a6af51303e07fe500629e2b7f80f08ffccfbf26d59d0f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb6377336a0078218cb1159dc3a19adbdf2a71e60d6f52c8ba4abf9170256406
+oid sha256:f1c3295a68c7a8f7dc49b16501550372bd9d3e2c08143b24c6a968c87bf3872a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:202c8b95965dd4eda63189b06ebc2268576708716dc393c42660121e11812c92
+oid sha256:2596d00c52d374a24cb08c2d7a6dbeb56385223fc45e73f3809fa688314484eb
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da88adb554ad6c6d60435af6954d39ccf537b6e55ec10818ca6c902e98fa6d95
+oid sha256:3faa6b259716ae2b34aedbc78be194fa9cee852ecc9e1637eda5e59353d434b8
 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": 1.0104379653930664,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02304944105105451,
+  "best_metric": 0.983562707901001,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04609888210210902,
   "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": 16.342,
       "eval_steps_per_second": 4.249,
       "step": 25
+    },
+    {
+      "epoch": 0.023971418693096692,
+      "grad_norm": 0.1446598619222641,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7335,
+      "step": 26
+    },
+    {
+      "epoch": 0.024893396335138873,
+      "grad_norm": 0.16403502225875854,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.7692,
+      "step": 27
+    },
+    {
+      "epoch": 0.025815373977181054,
+      "grad_norm": 0.18820112943649292,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.8644,
+      "step": 28
+    },
+    {
+      "epoch": 0.026737351619223235,
+      "grad_norm": 0.19414544105529785,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.8491,
+      "step": 29
+    },
+    {
+      "epoch": 0.027659329261265415,
+      "grad_norm": 0.16365379095077515,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.9683,
+      "step": 30
+    },
+    {
+      "epoch": 0.028581306903307596,
+      "grad_norm": 0.16391751170158386,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.0038,
+      "step": 31
+    },
+    {
+      "epoch": 0.029503284545349777,
+      "grad_norm": 0.15574006736278534,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.9643,
+      "step": 32
+    },
+    {
+      "epoch": 0.030425262187391954,
+      "grad_norm": 0.1687910556793213,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.0626,
+      "step": 33
+    },
+    {
+      "epoch": 0.03134723982943414,
+      "grad_norm": 0.18482720851898193,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.1207,
+      "step": 34
+    },
+    {
+      "epoch": 0.03226921747147632,
+      "grad_norm": 0.22824575006961823,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.1453,
+      "step": 35
+    },
+    {
+      "epoch": 0.0331911951135185,
+      "grad_norm": 0.23433442413806915,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.2672,
+      "step": 36
+    },
+    {
+      "epoch": 0.03411317275556068,
+      "grad_norm": 0.34760910272598267,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.4551,
+      "step": 37
+    },
+    {
+      "epoch": 0.03503515039760286,
+      "grad_norm": 0.09731561690568924,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.7236,
+      "step": 38
+    },
+    {
+      "epoch": 0.035957128039645035,
+      "grad_norm": 0.09190354496240616,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.7556,
+      "step": 39
+    },
+    {
+      "epoch": 0.036879105681687216,
+      "grad_norm": 0.11261679977178574,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.8309,
+      "step": 40
+    },
+    {
+      "epoch": 0.0378010833237294,
+      "grad_norm": 0.13187381625175476,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.7903,
+      "step": 41
+    },
+    {
+      "epoch": 0.03872306096577158,
+      "grad_norm": 0.13414575159549713,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.9099,
+      "step": 42
+    },
+    {
+      "epoch": 0.03964503860781376,
+      "grad_norm": 0.1466209590435028,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.8833,
+      "step": 43
+    },
+    {
+      "epoch": 0.04056701624985594,
+      "grad_norm": 0.1413664072751999,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.9864,
+      "step": 44
+    },
+    {
+      "epoch": 0.04148899389189812,
+      "grad_norm": 0.13641425967216492,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.069,
+      "step": 45
+    },
+    {
+      "epoch": 0.0424109715339403,
+      "grad_norm": 0.14130431413650513,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0774,
+      "step": 46
+    },
+    {
+      "epoch": 0.04333294917598248,
+      "grad_norm": 0.1519637107849121,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.1186,
+      "step": 47
+    },
+    {
+      "epoch": 0.04425492681802466,
+      "grad_norm": 0.18100306391716003,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.2517,
+      "step": 48
+    },
+    {
+      "epoch": 0.04517690446006684,
+      "grad_norm": 0.21845021843910217,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.4335,
+      "step": 49
+    },
+    {
+      "epoch": 0.04609888210210902,
+      "grad_norm": 0.4103708267211914,
+      "learning_rate": 1e-05,
+      "loss": 1.6454,
+      "step": 50
+    },
+    {
+      "epoch": 0.04609888210210902,
+      "eval_loss": 0.983562707901001,
+      "eval_runtime": 3.0034,
+      "eval_samples_per_second": 16.648,
+      "eval_steps_per_second": 4.328,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null