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:c3ecf472c6d2eca2ae5f471f317acc3ea576c9f93293f1366ec25f30d3e4ad8f
+oid sha256:25e529eb99362011e86ead18a8cea5b7a4a94a8e5a347a763513124e47ce8fce
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dffaacd52ec1a31d5a2191db84ca639b6616284f8e42ae062f41e58580bb6fb
+oid sha256:c3741563ff82d2140e90eb9acc986a1032685431315eea43edc706bc5eab9ac1
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8517bb3718b3c5d6eb7cdf19fc912d18539aaf35383b6c54a0300a5457ae684
+oid sha256:85aff80d52cae8f82bf3256034787e4ea7c415ef0c0c4e43e17acaa355f3235b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e785933f4bc9f2ce7f7c2c35182c37d0aad70d7ed0b5ce523455728e5b71c1e1
+oid sha256:d8f3b71e35e3e0edbacba2333ca81f1fa9bb66c896b696c0d6b3c99c7c459c61
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5e3b1240af1479c916b55b58ac93c33a3d468f0fa6bb8d312e384230067999e
+oid sha256:98c106fd72716e2dd04efdb677d80f6a3326f244da165cb476d62571af01ea9a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f17a4610061dcbfdf11f2a73f8f4464c7037c8b54f1bf752a92c31150b98cfe8
+oid sha256:13c56bdb8a214e00cc7c7e59947a7f106f335f97221801ba514f64805debf88c
 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": 4.626386642456055,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.034381983840467596,
+  "best_metric": 4.621637344360352,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.06876396768093519,
   "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": 17.114,
       "eval_steps_per_second": 4.45,
       "step": 25
+    },
+    {
+      "epoch": 0.0357572631940863,
+      "grad_norm": 17.571855545043945,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 71.1024,
+      "step": 26
+    },
+    {
+      "epoch": 0.037132542547705004,
+      "grad_norm": 44.00326156616211,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 72.3466,
+      "step": 27
+    },
+    {
+      "epoch": 0.03850782190132371,
+      "grad_norm": 70.81744384765625,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 74.5078,
+      "step": 28
+    },
+    {
+      "epoch": 0.03988310125494241,
+      "grad_norm": 51.877384185791016,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 74.2768,
+      "step": 29
+    },
+    {
+      "epoch": 0.041258380608561115,
+      "grad_norm": 19.11564064025879,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 74.1218,
+      "step": 30
+    },
+    {
+      "epoch": 0.04263365996217982,
+      "grad_norm": 27.261991500854492,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 75.4165,
+      "step": 31
+    },
+    {
+      "epoch": 0.04400893931579852,
+      "grad_norm": 48.26954650878906,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 74.5459,
+      "step": 32
+    },
+    {
+      "epoch": 0.04538421866941723,
+      "grad_norm": 38.06425476074219,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 76.8192,
+      "step": 33
+    },
+    {
+      "epoch": 0.04675949802303593,
+      "grad_norm": 18.26669692993164,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 76.9858,
+      "step": 34
+    },
+    {
+      "epoch": 0.048134777376654635,
+      "grad_norm": 10.748762130737305,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 77.5933,
+      "step": 35
+    },
+    {
+      "epoch": 0.04951005673027334,
+      "grad_norm": 30.8355655670166,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 78.0878,
+      "step": 36
+    },
+    {
+      "epoch": 0.05088533608389204,
+      "grad_norm": 31.517621994018555,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 78.3195,
+      "step": 37
+    },
+    {
+      "epoch": 0.052260615437510746,
+      "grad_norm": 5.85664176940918,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 76.3249,
+      "step": 38
+    },
+    {
+      "epoch": 0.05363589479112945,
+      "grad_norm": 24.378793716430664,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 71.3614,
+      "step": 39
+    },
+    {
+      "epoch": 0.055011174144748154,
+      "grad_norm": 30.349285125732422,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 73.0253,
+      "step": 40
+    },
+    {
+      "epoch": 0.05638645349836686,
+      "grad_norm": 23.223705291748047,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 73.2813,
+      "step": 41
+    },
+    {
+      "epoch": 0.05776173285198556,
+      "grad_norm": 5.5575785636901855,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 73.9555,
+      "step": 42
+    },
+    {
+      "epoch": 0.059137012205604265,
+      "grad_norm": 13.843238830566406,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 74.1518,
+      "step": 43
+    },
+    {
+      "epoch": 0.06051229155922297,
+      "grad_norm": 19.540786743164062,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 74.4265,
+      "step": 44
+    },
+    {
+      "epoch": 0.06188757091284167,
+      "grad_norm": 22.034353256225586,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 74.6505,
+      "step": 45
+    },
+    {
+      "epoch": 0.06326285026646038,
+      "grad_norm": 18.099666595458984,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 75.1105,
+      "step": 46
+    },
+    {
+      "epoch": 0.06463812962007907,
+      "grad_norm": 7.462347030639648,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 77.1888,
+      "step": 47
+    },
+    {
+      "epoch": 0.06601340897369778,
+      "grad_norm": 5.528837203979492,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 77.7504,
+      "step": 48
+    },
+    {
+      "epoch": 0.06738868832731648,
+      "grad_norm": 19.01416015625,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 79.3957,
+      "step": 49
+    },
+    {
+      "epoch": 0.06876396768093519,
+      "grad_norm": 10.58906078338623,
+      "learning_rate": 1e-05,
+      "loss": 81.2795,
+      "step": 50
+    },
+    {
+      "epoch": 0.06876396768093519,
+      "eval_loss": 4.621637344360352,
+      "eval_runtime": 2.9236,
+      "eval_samples_per_second": 17.102,
+      "eval_steps_per_second": 4.447,
+      "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": 2.629552387915776e+17,
+  "total_flos": 5.259104775831552e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null