Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3062cfefba211466c5e2628b661386eca5b986211c1133d0b2d66c4039db9e1e
+oid sha256:8486e0f63a9b9e0f4e18268c30b5b7518393028f80efa4415a3aeb3f0ce30fb7
 size 2436967616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3460d1aba9e622d47646755b2f8a3ec5fae162f378cf0be12f83da2ecb961eaa
+oid sha256:8d8764d5189fc7e9f984ab60d4b0456b55f948ba4d5d9e1fb5f08fc00a6d0198
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a257fbe75de43d719a5d383f2170f688ba60c4c2144b2ed1ec4b621e2a86aa8f
+oid sha256:111222c603ccb065e59781f0bc3bf5fd9d9931f641e5e2091e164828be9a0956
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45c79f01d53ee026a0c7511f6c1df5f7b92faa8715a7a3d0423e155a6149c690
+oid sha256:6d896f07f2ef4ee37bbbb517c52d231ddbb61d57108129ebc92943b3584f6059
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e4f3d3c6cdbf7d13d6738ae9278c0d136831452458ebf1eeea8eeb7dfd76116
+oid sha256:fd706c23ae8c5ed5a6d5c21f0f7042ed04aa55f0e46c1c26a12dfbf32923e9d9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42971e1097e30ddacfd6c52ac19281378a8dcaab8e714918ef273df826c6b88d
+oid sha256:7ddf0517b48d98114b7d6d89b04972989a85bf1b5fe15a8729945edc91475268
 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": 2.087225914001465,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.007450454477723141,
+  "best_metric": 2.003491163253784,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.014900908955446282,
   "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": 21.358,
       "eval_steps_per_second": 5.553,
       "step": 25
+    },
+    {
+      "epoch": 0.007748472656832066,
+      "grad_norm": 0.47236016392707825,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.156,
+      "step": 26
+    },
+    {
+      "epoch": 0.008046490835940992,
+      "grad_norm": 0.5345865488052368,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.1204,
+      "step": 27
+    },
+    {
+      "epoch": 0.008344509015049918,
+      "grad_norm": 0.4965778887271881,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.0456,
+      "step": 28
+    },
+    {
+      "epoch": 0.008642527194158844,
+      "grad_norm": 0.45029252767562866,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.0003,
+      "step": 29
+    },
+    {
+      "epoch": 0.008940545373267769,
+      "grad_norm": 0.4446468949317932,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.0242,
+      "step": 30
+    },
+    {
+      "epoch": 0.009238563552376695,
+      "grad_norm": 0.48782452940940857,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.9474,
+      "step": 31
+    },
+    {
+      "epoch": 0.009536581731485621,
+      "grad_norm": 0.46959659457206726,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.9684,
+      "step": 32
+    },
+    {
+      "epoch": 0.009834599910594547,
+      "grad_norm": 0.4955771565437317,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.0053,
+      "step": 33
+    },
+    {
+      "epoch": 0.010132618089703472,
+      "grad_norm": 0.4691748023033142,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.9942,
+      "step": 34
+    },
+    {
+      "epoch": 0.010430636268812398,
+      "grad_norm": 0.5127565264701843,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.0143,
+      "step": 35
+    },
+    {
+      "epoch": 0.010728654447921324,
+      "grad_norm": 0.516806423664093,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.0691,
+      "step": 36
+    },
+    {
+      "epoch": 0.011026672627030248,
+      "grad_norm": 0.533613920211792,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.0478,
+      "step": 37
+    },
+    {
+      "epoch": 0.011324690806139175,
+      "grad_norm": 0.42579934000968933,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.0956,
+      "step": 38
+    },
+    {
+      "epoch": 0.0116227089852481,
+      "grad_norm": 0.4248853623867035,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.1222,
+      "step": 39
+    },
+    {
+      "epoch": 0.011920727164357025,
+      "grad_norm": 0.41036468744277954,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.0217,
+      "step": 40
+    },
+    {
+      "epoch": 0.012218745343465951,
+      "grad_norm": 0.42496877908706665,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.0106,
+      "step": 41
+    },
+    {
+      "epoch": 0.012516763522574878,
+      "grad_norm": 0.4574867784976959,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.9419,
+      "step": 42
+    },
+    {
+      "epoch": 0.012814781701683802,
+      "grad_norm": 0.4341859221458435,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.9376,
+      "step": 43
+    },
+    {
+      "epoch": 0.013112799880792728,
+      "grad_norm": 0.40266716480255127,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.0011,
+      "step": 44
+    },
+    {
+      "epoch": 0.013410818059901655,
+      "grad_norm": 0.4303281009197235,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.998,
+      "step": 45
+    },
+    {
+      "epoch": 0.013708836239010579,
+      "grad_norm": 0.4447619616985321,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.999,
+      "step": 46
+    },
+    {
+      "epoch": 0.014006854418119505,
+      "grad_norm": 0.4733419716358185,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.0109,
+      "step": 47
+    },
+    {
+      "epoch": 0.014304872597228431,
+      "grad_norm": 0.5527592301368713,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.956,
+      "step": 48
+    },
+    {
+      "epoch": 0.014602890776337356,
+      "grad_norm": 0.5123348832130432,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.9812,
+      "step": 49
+    },
+    {
+      "epoch": 0.014900908955446282,
+      "grad_norm": 0.5983260273933411,
+      "learning_rate": 1e-05,
+      "loss": 2.1283,
+      "step": 50
+    },
+    {
+      "epoch": 0.014900908955446282,
+      "eval_loss": 2.003491163253784,
+      "eval_runtime": 2.3523,
+      "eval_samples_per_second": 21.256,
+      "eval_steps_per_second": 5.527,
+      "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": 2.9859084443949466e+17,
+  "total_flos": 5.969951863666115e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null