Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1005b900b533584ab5744bf76da2904c35fa56076037d490c9a688d2b2c7bef1
+oid sha256:e4bd17dfab427d5c768b3eb967db1335fcae54ef9801ecf153aa4f2e1d0a76f8
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36ed320491a0588501b58139431d380432a9bfa83e15955271b5703b3724d471
+oid sha256:83c294913fe2f0ee7207d3d276f5a7c33ddb54844eb47aed8f230306ef9dbeb2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24366e1cc433abb45e3fd36e07f60a98d812a118c5584c0f42aaf1adf71b4d5d
+oid sha256:5105b5dd972cffa95838513dc133fff01678c7af85ff23a2ead1ed3a0529f0b3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24084076559973c1c5674fc9d601745bbc4e2ec5ea210c93140a09a5159f898b
+oid sha256:4f67f4028efc44831abd09933689cb49ca48f4491732a082c06209368c5f6198
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:087f38feb127b74fa5f2863a488f745cc8549a3bed013130253c2f6c8cc5e698
+oid sha256:8847af796359877d3edb5eaab41c6d9ef447ba2c0fc73726328ef677e238f14d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:623f9e02229f75fa8ad8aa8e1eaac115f7f1d9d0aaf38fe3a9d0e31ccce25e59
+oid sha256:6699b472638a8f31a11ca6f5b99da46ca204c5d0b66a5f98a434363ae58a4b5d
 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": 1.1730780601501465,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.03971405877680699,
+  "best_metric": 1.1204490661621094,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.07942811755361398,
   "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": 24.514,
       "eval_steps_per_second": 6.374,
       "step": 25
+    },
+    {
+      "epoch": 0.04130262112787927,
+      "grad_norm": 0.7173677086830139,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.1916,
+      "step": 26
+    },
+    {
+      "epoch": 0.04289118347895155,
+      "grad_norm": 0.76693195104599,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.2504,
+      "step": 27
+    },
+    {
+      "epoch": 0.04447974583002383,
+      "grad_norm": 0.6550216674804688,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.2569,
+      "step": 28
+    },
+    {
+      "epoch": 0.046068308181096106,
+      "grad_norm": 0.5112429857254028,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.2407,
+      "step": 29
+    },
+    {
+      "epoch": 0.04765687053216839,
+      "grad_norm": 0.36219966411590576,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1617,
+      "step": 30
+    },
+    {
+      "epoch": 0.04924543288324067,
+      "grad_norm": 0.3246273100376129,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.1618,
+      "step": 31
+    },
+    {
+      "epoch": 0.050833995234312944,
+      "grad_norm": 0.3080134391784668,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.2093,
+      "step": 32
+    },
+    {
+      "epoch": 0.05242255758538523,
+      "grad_norm": 0.36938804388046265,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.1696,
+      "step": 33
+    },
+    {
+      "epoch": 0.054011119936457505,
+      "grad_norm": 0.4594118893146515,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.1996,
+      "step": 34
+    },
+    {
+      "epoch": 0.05559968228752978,
+      "grad_norm": 0.6706517934799194,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.154,
+      "step": 35
+    },
+    {
+      "epoch": 0.057188244638602066,
+      "grad_norm": 0.7852743864059448,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.1745,
+      "step": 36
+    },
+    {
+      "epoch": 0.05877680698967434,
+      "grad_norm": 0.5067930817604065,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.9723,
+      "step": 37
+    },
+    {
+      "epoch": 0.06036536934074663,
+      "grad_norm": 0.3320077955722809,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.1624,
+      "step": 38
+    },
+    {
+      "epoch": 0.061953931691818905,
+      "grad_norm": 0.23800799250602722,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.1551,
+      "step": 39
+    },
+    {
+      "epoch": 0.06354249404289118,
+      "grad_norm": 0.2339501529932022,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.1591,
+      "step": 40
+    },
+    {
+      "epoch": 0.06513105639396347,
+      "grad_norm": 0.24399659037590027,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.1155,
+      "step": 41
+    },
+    {
+      "epoch": 0.06671961874503574,
+      "grad_norm": 0.24500925838947296,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.0994,
+      "step": 42
+    },
+    {
+      "epoch": 0.06830818109610802,
+      "grad_norm": 0.27097079157829285,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.2019,
+      "step": 43
+    },
+    {
+      "epoch": 0.0698967434471803,
+      "grad_norm": 0.26295530796051025,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.1541,
+      "step": 44
+    },
+    {
+      "epoch": 0.07148530579825259,
+      "grad_norm": 0.2993250787258148,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.1529,
+      "step": 45
+    },
+    {
+      "epoch": 0.07307386814932486,
+      "grad_norm": 0.32925310730934143,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.1371,
+      "step": 46
+    },
+    {
+      "epoch": 0.07466243050039714,
+      "grad_norm": 0.32412636280059814,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.1342,
+      "step": 47
+    },
+    {
+      "epoch": 0.07625099285146943,
+      "grad_norm": 0.45030054450035095,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.1043,
+      "step": 48
+    },
+    {
+      "epoch": 0.0778395552025417,
+      "grad_norm": 0.43968403339385986,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.066,
+      "step": 49
+    },
+    {
+      "epoch": 0.07942811755361398,
+      "grad_norm": 0.5369355082511902,
+      "learning_rate": 1e-05,
+      "loss": 0.9676,
+      "step": 50
+    },
+    {
+      "epoch": 0.07942811755361398,
+      "eval_loss": 1.1204490661621094,
+      "eval_runtime": 2.0299,
+      "eval_samples_per_second": 24.632,
+      "eval_steps_per_second": 6.404,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.971813667564421e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null