Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e29dc0d7e7dbbffb1de810fd4c7c644cc9098ae978057553f142947517a30e
+oid sha256:a007e65347a3904aa8e46c75e90efdff01b6ae35bef8ed00f25f18cfce781931
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:35fa1932e7837e7d4af81100a2ba55fb8eabb44b9d1575868ea2801272fb3a03
+oid sha256:d2e085ad8648412cd3be680f35aa6e2f2a13c72d8d3f624a18271e36a1160bbf
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a394e2019c603fbb66374daac3d18e3f21403ad57941d827035b0eb77f5040b
+oid sha256:c386edb3455509fb6612a645820007dbe4b8dc753ddbc714353798058af567e3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0192df02f9f52297beac3508bd6c454c7914acff4a94f5a1c2487eb7030aff19
+oid sha256:82f4520b625fbd8e02df07d900ccedefa50e67ca129dc01b9f9ece2db6691936
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f3a8e2d2a3e11d0562ae4aac9e192aaf4b20f4e53e805ece55bae50a2390462
+oid sha256:4c58f2b9f9575f256a534d2aff055de3d5fadc2afe82bdf0ba1003e12a9eafb4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa033fae943977a09ce59b3984040889cea7b43398571e40ce3eaa61a7ec97bc
+oid sha256:a785646994d94264cad1aa6947996b33d7b84bfa9d1d6fc71ed42ac7cea30ba5
 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": 0.7068415284156799,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05355469272995046,
+  "best_metric": 0.69820237159729,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.10710938545990092,
   "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": 9.984,
       "eval_steps_per_second": 2.596,
       "step": 25
+    },
+    {
+      "epoch": 0.05569688043914848,
+      "grad_norm": 8.646862983703613,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 23.0047,
+      "step": 26
+    },
+    {
+      "epoch": 0.0578390681483465,
+      "grad_norm": 2.957317352294922,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 22.7869,
+      "step": 27
+    },
+    {
+      "epoch": 0.05998125585754452,
+      "grad_norm": 2.7320399284362793,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 22.442,
+      "step": 28
+    },
+    {
+      "epoch": 0.062123443566742535,
+      "grad_norm": 2.0762381553649902,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 22.4845,
+      "step": 29
+    },
+    {
+      "epoch": 0.06426563127594055,
+      "grad_norm": 1.6332262754440308,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 22.4456,
+      "step": 30
+    },
+    {
+      "epoch": 0.06640781898513858,
+      "grad_norm": 2.0493698120117188,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 22.4885,
+      "step": 31
+    },
+    {
+      "epoch": 0.06855000669433658,
+      "grad_norm": 1.6183415651321411,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 22.4925,
+      "step": 32
+    },
+    {
+      "epoch": 0.07069219440353461,
+      "grad_norm": 1.547934651374817,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 22.4405,
+      "step": 33
+    },
+    {
+      "epoch": 0.07283438211273263,
+      "grad_norm": 2.028595447540283,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 22.5106,
+      "step": 34
+    },
+    {
+      "epoch": 0.07497656982193064,
+      "grad_norm": 5.2422285079956055,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 22.4615,
+      "step": 35
+    },
+    {
+      "epoch": 0.07711875753112866,
+      "grad_norm": 1.9077330827713013,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 22.4419,
+      "step": 36
+    },
+    {
+      "epoch": 0.07926094524032669,
+      "grad_norm": 1.5004316568374634,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 22.4519,
+      "step": 37
+    },
+    {
+      "epoch": 0.0814031329495247,
+      "grad_norm": 1.5373482704162598,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 22.4174,
+      "step": 38
+    },
+    {
+      "epoch": 0.08354532065872272,
+      "grad_norm": 6.600869178771973,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 22.5424,
+      "step": 39
+    },
+    {
+      "epoch": 0.08568750836792074,
+      "grad_norm": 1.9094051122665405,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 22.425,
+      "step": 40
+    },
+    {
+      "epoch": 0.08782969607711875,
+      "grad_norm": 1.1293197870254517,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 22.3906,
+      "step": 41
+    },
+    {
+      "epoch": 0.08997188378631678,
+      "grad_norm": 1.5770303010940552,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 22.4555,
+      "step": 42
+    },
+    {
+      "epoch": 0.09211407149551479,
+      "grad_norm": 1.7812321186065674,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 22.465,
+      "step": 43
+    },
+    {
+      "epoch": 0.09425625920471281,
+      "grad_norm": 1.4559767246246338,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 22.4248,
+      "step": 44
+    },
+    {
+      "epoch": 0.09639844691391083,
+      "grad_norm": 1.6689614057540894,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 22.4673,
+      "step": 45
+    },
+    {
+      "epoch": 0.09854063462310884,
+      "grad_norm": 1.4703079462051392,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 22.4004,
+      "step": 46
+    },
+    {
+      "epoch": 0.10068282233230687,
+      "grad_norm": 1.3788950443267822,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 22.4353,
+      "step": 47
+    },
+    {
+      "epoch": 0.10282501004150489,
+      "grad_norm": 1.4672656059265137,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 22.4183,
+      "step": 48
+    },
+    {
+      "epoch": 0.1049671977507029,
+      "grad_norm": 1.815381407737732,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 22.4214,
+      "step": 49
+    },
+    {
+      "epoch": 0.10710938545990092,
+      "grad_norm": 0.9922463893890381,
+      "learning_rate": 1e-05,
+      "loss": 22.4399,
+      "step": 50
+    },
+    {
+      "epoch": 0.10710938545990092,
+      "eval_loss": 0.69820237159729,
+      "eval_runtime": 5.0539,
+      "eval_samples_per_second": 9.893,
+      "eval_steps_per_second": 2.572,
+      "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": 3.039627994810286e+17,
+  "total_flos": 6.059534154779853e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null