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:e6f585080c644e2d447309966cd152ce3902d84d6a938f74d005009c8a474c06
+oid sha256:2c475331c296bd8db8754a1be8abdf3256e1246a4f2566917c4826317ee41693
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:343781cc3981bfe6df337d53426f0dcb5f6da65f1dc4c33182f478ef8e12364b
+oid sha256:e962e810796d18f64ab711f8f0c77e44679046f74197fc87f5eb9c6b3908f4a8
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71c3c3b8bd0da82b232ce82be72956e1deb3ddf247d35299f65b66cea9fa0110
+oid sha256:fd49d58210ff6e6e2c00136960839e4f9098ee161f487dd8ba548a70d10beacf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3659987768fc07b6ebc0c283d298d5744ba3af219ef5eece6652e7bb59c63992
+oid sha256:0d68e8888a7f7341f64c866c7f03d6cbb8d039e8a7fb4cd853f72eb3d003218e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2058a757384542e003689c3bee9d0a9832b501265083d855fcb758e59d07409
+oid sha256:1ce4e959bacbc58998061eee04390b28ec30621f1946f4b0ded9d121d17aa554
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e46a8ff3ad40bff281e3ebcdec735e8cef0494e482d41aceba12934967dc6172
+oid sha256:9eb9a81ca24b930c4157a9e680f02a5b5f630c84756f9d2d44eb402b6f98cfe6
 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": 1.1578917503356934,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.04749465685110425,
+  "best_metric": 1.1079792976379395,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0949893137022085,
   "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": 65.174,
       "eval_steps_per_second": 16.945,
       "step": 25
+    },
+    {
+      "epoch": 0.04939444312514842,
+      "grad_norm": 0.7630718350410461,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.6176,
+      "step": 26
+    },
+    {
+      "epoch": 0.05129422939919259,
+      "grad_norm": 1.0892037153244019,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.7635,
+      "step": 27
+    },
+    {
+      "epoch": 0.05319401567323676,
+      "grad_norm": 1.6025984287261963,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.708,
+      "step": 28
+    },
+    {
+      "epoch": 0.05509380194728093,
+      "grad_norm": 2.619377851486206,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.4022,
+      "step": 29
+    },
+    {
+      "epoch": 0.0569935882213251,
+      "grad_norm": 2.9281277656555176,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.2255,
+      "step": 30
+    },
+    {
+      "epoch": 0.05889337449536927,
+      "grad_norm": 2.5044264793395996,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.0397,
+      "step": 31
+    },
+    {
+      "epoch": 0.06079316076941344,
+      "grad_norm": 2.153557538986206,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.0303,
+      "step": 32
+    },
+    {
+      "epoch": 0.06269294704345761,
+      "grad_norm": 1.567138671875,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.9041,
+      "step": 33
+    },
+    {
+      "epoch": 0.06459273331750177,
+      "grad_norm": 1.282874345779419,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.8644,
+      "step": 34
+    },
+    {
+      "epoch": 0.06649251959154595,
+      "grad_norm": 1.0088517665863037,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.8199,
+      "step": 35
+    },
+    {
+      "epoch": 0.06839230586559013,
+      "grad_norm": 1.2049599885940552,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.8802,
+      "step": 36
+    },
+    {
+      "epoch": 0.07029209213963429,
+      "grad_norm": 1.835536003112793,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.7676,
+      "step": 37
+    },
+    {
+      "epoch": 0.07219187841367847,
+      "grad_norm": 0.6069178581237793,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.5519,
+      "step": 38
+    },
+    {
+      "epoch": 0.07409166468772263,
+      "grad_norm": 0.5351535081863403,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.7305,
+      "step": 39
+    },
+    {
+      "epoch": 0.07599145096176681,
+      "grad_norm": 0.7276419401168823,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.691,
+      "step": 40
+    },
+    {
+      "epoch": 0.07789123723581097,
+      "grad_norm": 0.9947127103805542,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.4187,
+      "step": 41
+    },
+    {
+      "epoch": 0.07979102350985515,
+      "grad_norm": 0.9087701439857483,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.1257,
+      "step": 42
+    },
+    {
+      "epoch": 0.08169080978389931,
+      "grad_norm": 0.8760981559753418,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.0551,
+      "step": 43
+    },
+    {
+      "epoch": 0.08359059605794349,
+      "grad_norm": 0.9599126577377319,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.871,
+      "step": 44
+    },
+    {
+      "epoch": 0.08549038233198765,
+      "grad_norm": 0.9589977264404297,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.8555,
+      "step": 45
+    },
+    {
+      "epoch": 0.08739016860603183,
+      "grad_norm": 1.009002447128296,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.8261,
+      "step": 46
+    },
+    {
+      "epoch": 0.08928995488007599,
+      "grad_norm": 1.101606845855713,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.7646,
+      "step": 47
+    },
+    {
+      "epoch": 0.09118974115412017,
+      "grad_norm": 1.3389166593551636,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.769,
+      "step": 48
+    },
+    {
+      "epoch": 0.09308952742816433,
+      "grad_norm": 1.942348837852478,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.7798,
+      "step": 49
+    },
+    {
+      "epoch": 0.0949893137022085,
+      "grad_norm": 2.624502420425415,
+      "learning_rate": 1e-05,
+      "loss": 0.7879,
+      "step": 50
+    },
+    {
+      "epoch": 0.0949893137022085,
+      "eval_loss": 1.1079792976379395,
+      "eval_runtime": 0.7484,
+      "eval_samples_per_second": 66.81,
+      "eval_steps_per_second": 17.371,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null