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:def1296cfc365d8bd737c99871b53837e32f4367c0d2b6f3b32659b057c4222f
+oid sha256:c0f413280ffd0a90f89a3c869220162d5a94f0393a980c1ebef64a232daf8127
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:179ac297a6121b3342486801f863df7f4abd3b252978147ed50171b05eb15e35
+oid sha256:c79dfbc60b4e6a74cfcd9c389d6cad25941a8395ac7e096f2ae3b586de9fbf46
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20bb54e6c596c1a4a4c413f122f8897f1e7103523228713bae9cd27bdd24b4a4
+oid sha256:2eb8636eadde64c83f1b1677655650437ec9c1774f12de95c6d4d453964bcb54
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8f7234cd96fd39575c5451c28cbd437369aa19acfd20be0405114b8bda65690
+oid sha256:707f1e33b7875cef1fa507ff0f20624267ea04b155208289547e2b7df42b8892
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb8acc56b9129ceeb4d5b4f26a81bc00ff31f2b31fdbd0e9e174a80d10a49b49
+oid sha256:aedc2bfb4e77788856da9f2e286a59fa3dafa98122fdd413558bc58c7ff18aa2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:560bcab24a568bb62257eef1a1aa2c8fc996ed57482881572c1e3f66990a24b7
+oid sha256:2774c24426d90b59cecf18c4c1533c6618f03ef3fa15c668b2f3d57d4aeb9585
 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": 1.85048246383667,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09259259259259259,
+  "best_metric": 1.8121827840805054,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.18518518518518517,
   "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": 42.02,
       "eval_steps_per_second": 10.925,
       "step": 25
+    },
+    {
+      "epoch": 0.0962962962962963,
+      "grad_norm": 1.1121193170547485,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.1252,
+      "step": 26
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.8684629797935486,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.1406,
+      "step": 27
+    },
+    {
+      "epoch": 0.1037037037037037,
+      "grad_norm": 0.9157536625862122,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.1774,
+      "step": 28
+    },
+    {
+      "epoch": 0.10740740740740741,
+      "grad_norm": 0.8227851390838623,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.0968,
+      "step": 29
+    },
+    {
+      "epoch": 0.1111111111111111,
+      "grad_norm": 0.78924959897995,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.9995,
+      "step": 30
+    },
+    {
+      "epoch": 0.11481481481481481,
+      "grad_norm": 0.7110780477523804,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.1279,
+      "step": 31
+    },
+    {
+      "epoch": 0.11851851851851852,
+      "grad_norm": 0.9979654550552368,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.9278,
+      "step": 32
+    },
+    {
+      "epoch": 0.12222222222222222,
+      "grad_norm": 0.8598797917366028,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.8535,
+      "step": 33
+    },
+    {
+      "epoch": 0.1259259259259259,
+      "grad_norm": 0.7902474999427795,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.9307,
+      "step": 34
+    },
+    {
+      "epoch": 0.12962962962962962,
+      "grad_norm": 0.7645499110221863,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.881,
+      "step": 35
+    },
+    {
+      "epoch": 0.13333333333333333,
+      "grad_norm": 0.719105064868927,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.8728,
+      "step": 36
+    },
+    {
+      "epoch": 0.13703703703703704,
+      "grad_norm": 0.8383614420890808,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.8178,
+      "step": 37
+    },
+    {
+      "epoch": 0.14074074074074075,
+      "grad_norm": 0.8378170132637024,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.0145,
+      "step": 38
+    },
+    {
+      "epoch": 0.14444444444444443,
+      "grad_norm": 0.7174258232116699,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.0416,
+      "step": 39
+    },
+    {
+      "epoch": 0.14814814814814814,
+      "grad_norm": 0.7204661965370178,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.0629,
+      "step": 40
+    },
+    {
+      "epoch": 0.15185185185185185,
+      "grad_norm": 0.8379583358764648,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.2456,
+      "step": 41
+    },
+    {
+      "epoch": 0.15555555555555556,
+      "grad_norm": 0.7334498763084412,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.0159,
+      "step": 42
+    },
+    {
+      "epoch": 0.15925925925925927,
+      "grad_norm": 0.6511536240577698,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.8639,
+      "step": 43
+    },
+    {
+      "epoch": 0.16296296296296298,
+      "grad_norm": 0.7303625345230103,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.0572,
+      "step": 44
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 0.8422804474830627,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.1421,
+      "step": 45
+    },
+    {
+      "epoch": 0.17037037037037037,
+      "grad_norm": 0.7520930171012878,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.0257,
+      "step": 46
+    },
+    {
+      "epoch": 0.17407407407407408,
+      "grad_norm": 0.6944776177406311,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.9534,
+      "step": 47
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.6583529710769653,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.8021,
+      "step": 48
+    },
+    {
+      "epoch": 0.1814814814814815,
+      "grad_norm": 0.7733290791511536,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.9247,
+      "step": 49
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "grad_norm": 0.8443518280982971,
+      "learning_rate": 1e-05,
+      "loss": 1.7639,
+      "step": 50
+    },
+    {
+      "epoch": 0.18518518518518517,
+      "eval_loss": 1.8121827840805054,
+      "eval_runtime": 1.1902,
+      "eval_samples_per_second": 42.01,
+      "eval_steps_per_second": 10.923,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null