Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19a438028621c28799dfc5763be0f83cd1862ef9d0bfe3ef6564cddad2f06e01
+oid sha256:68662d923a35f5bd39ff151b6766f3a5e4433ebe631e341dbc92d71d85e7849d
 size 27153960

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cfe8f7c11180f66edff03ba14a2f474d910d374b89511ee86c665ddc6f57cdd
+oid sha256:0fb83d023cd63eab9fbed976bd9805c5f0d021f6f60c83317a305b17f37d6f9f
 size 54405050

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88121a8f2323707ff9cb977b8063eb3b3ab1256107c96f98551b97376a0ac92f
+oid sha256:53c951f9715126baf76ce2edad8e8d001217d1022539dfc32d55c99528ac1875
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:602b71f0bdd753776f1e94ab44ef93f98a4aca57d02a09d9dd930da766204ad9
+oid sha256:eb41327a930056c7451a3ff14723e6ad04af9e7c9b87d2a5ba504253c7f66c2d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d508f1b74c430365481dc35c2c88ef82804680a5200f4cb5045f8754f17ea5
+oid sha256:ebd44e60a26111c8ac62f713e769a4d1c58fcc480c6c24128061fb2023b31f9c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:028221c36d0d50d2c72b113ce2debe5a2568dc168c7e0de3e8eaa99cc49080c9
+oid sha256:ba4603212b851f9298b382df4fffd110cc9cdcf95bf5526c57dc479b9b5966b0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 4.168821811676025,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4598540145985401,
+  "best_metric": 4.039027214050293,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.9197080291970803,
   "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": 345.484,
       "eval_steps_per_second": 44.675,
       "step": 25
+    },
+    {
+      "epoch": 1.5182481751824817,
+      "grad_norm": 0.8879239559173584,
+      "learning_rate": 5e-05,
+      "loss": 3.6184,
+      "step": 26
+    },
+    {
+      "epoch": 1.5766423357664232,
+      "grad_norm": 0.7602900862693787,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 4.2293,
+      "step": 27
+    },
+    {
+      "epoch": 1.635036496350365,
+      "grad_norm": 0.7398382425308228,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 4.083,
+      "step": 28
+    },
+    {
+      "epoch": 1.6934306569343067,
+      "grad_norm": 0.7375873327255249,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 4.1524,
+      "step": 29
+    },
+    {
+      "epoch": 1.7518248175182483,
+      "grad_norm": 0.5078723430633545,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.9595,
+      "step": 30
+    },
+    {
+      "epoch": 1.8102189781021898,
+      "grad_norm": 0.9409177303314209,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 4.5501,
+      "step": 31
+    },
+    {
+      "epoch": 1.8686131386861313,
+      "grad_norm": 0.6193199157714844,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.9367,
+      "step": 32
+    },
+    {
+      "epoch": 1.9270072992700729,
+      "grad_norm": 0.6904658079147339,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 4.1563,
+      "step": 33
+    },
+    {
+      "epoch": 1.9854014598540146,
+      "grad_norm": 1.267682433128357,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.6498,
+      "step": 34
+    },
+    {
+      "epoch": 2.0437956204379564,
+      "grad_norm": 1.2440922260284424,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 6.9059,
+      "step": 35
+    },
+    {
+      "epoch": 2.102189781021898,
+      "grad_norm": 0.7068952322006226,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.7204,
+      "step": 36
+    },
+    {
+      "epoch": 2.1605839416058394,
+      "grad_norm": 0.7181689143180847,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 4.1171,
+      "step": 37
+    },
+    {
+      "epoch": 2.218978102189781,
+      "grad_norm": 1.070713758468628,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 4.3304,
+      "step": 38
+    },
+    {
+      "epoch": 2.2773722627737225,
+      "grad_norm": 0.5744719505310059,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.6591,
+      "step": 39
+    },
+    {
+      "epoch": 2.335766423357664,
+      "grad_norm": 0.6503571271896362,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.8797,
+      "step": 40
+    },
+    {
+      "epoch": 2.394160583941606,
+      "grad_norm": 0.7630330920219421,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.9595,
+      "step": 41
+    },
+    {
+      "epoch": 2.4525547445255476,
+      "grad_norm": 0.753737211227417,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 4.1945,
+      "step": 42
+    },
+    {
+      "epoch": 2.510948905109489,
+      "grad_norm": 0.6379414796829224,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.2557,
+      "step": 43
+    },
+    {
+      "epoch": 2.5693430656934306,
+      "grad_norm": 0.7391951084136963,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.2283,
+      "step": 44
+    },
+    {
+      "epoch": 2.627737226277372,
+      "grad_norm": 0.5288726687431335,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.8803,
+      "step": 45
+    },
+    {
+      "epoch": 2.686131386861314,
+      "grad_norm": 0.7749550938606262,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 4.0824,
+      "step": 46
+    },
+    {
+      "epoch": 2.7445255474452557,
+      "grad_norm": 0.4466674029827118,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.6886,
+      "step": 47
+    },
+    {
+      "epoch": 2.802919708029197,
+      "grad_norm": 1.1186093091964722,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 5.789,
+      "step": 48
+    },
+    {
+      "epoch": 2.8613138686131387,
+      "grad_norm": 0.5663947463035583,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.8237,
+      "step": 49
+    },
+    {
+      "epoch": 2.9197080291970803,
+      "grad_norm": 0.6125584244728088,
+      "learning_rate": 0.0,
+      "loss": 4.0685,
+      "step": 50
+    },
+    {
+      "epoch": 2.9197080291970803,
+      "eval_loss": 4.039027214050293,
+      "eval_runtime": 0.3355,
+      "eval_samples_per_second": 345.792,
+      "eval_steps_per_second": 44.715,
+      "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": 5686862177894400.0,
+  "total_flos": 1.13737243557888e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null