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:f604a8d312db59e3b60a02df55915e156b38fa939b3bdeb7a89aa1792c9e325c
+oid sha256:0144a0e5c407ba102b8dec6ac6d1bece2c28f6b4f910a19d32faa5956ec07d8e
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49d31a835814d0bd239eb8b76ec37f45f02c9071dc603b18098becf061b44a9f
+oid sha256:bfa689825989e4ebb4a7f73c8900727593458c1b611684f889fa41e32f21e05b
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19cb948e42e8a99bc852ee73c5abe9011bb9fc840425b115b8a4f1e7cb63686e
+oid sha256:c16ab50bb69688fe669861e9c629fe4a00786cf09d1d1e1da308d4c6bfe81900
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab137aaf91d93ca4521657682b761e290843761e28f62663c5e2ab0ae99927c6
+oid sha256:1268d38c969c2f25abd221bdef07e59188f853709ddc5def837f5be91ee9e6fd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb2dc4b20a3d39d19b12055e9c6ef6fcd5798647f4fe000235ad408cee180d9f
+oid sha256:b8ad86ad52fb0f0456d404e1239eaca34d5da066451e61468bb1c44c6dc4d3bd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e46163959db035cd01026d4d110ee6a58553569e08505276c7ecb019fa06e43
+oid sha256:1f79ea98ce875bf220f6834776ff5ae1f0cbf8195d054b94bbeabb2633af8c84
 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": 0.751792848110199,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06482982171799027,
+  "best_metric": 0.7129375338554382,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12965964343598055,
   "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": 16.729,
       "eval_steps_per_second": 4.349,
       "step": 25
+    },
+    {
+      "epoch": 0.06742301458670989,
+      "grad_norm": 1.1765886545181274,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.5108,
+      "step": 26
+    },
+    {
+      "epoch": 0.0700162074554295,
+      "grad_norm": 1.3730372190475464,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.427,
+      "step": 27
+    },
+    {
+      "epoch": 0.07260940032414911,
+      "grad_norm": 1.078452706336975,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.4443,
+      "step": 28
+    },
+    {
+      "epoch": 0.07520259319286872,
+      "grad_norm": 1.0745612382888794,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.8648,
+      "step": 29
+    },
+    {
+      "epoch": 0.07779578606158834,
+      "grad_norm": 1.2040302753448486,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.7814,
+      "step": 30
+    },
+    {
+      "epoch": 0.08038897893030794,
+      "grad_norm": 1.2691534757614136,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.2031,
+      "step": 31
+    },
+    {
+      "epoch": 0.08298217179902755,
+      "grad_norm": 1.609654426574707,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.1928,
+      "step": 32
+    },
+    {
+      "epoch": 0.08557536466774716,
+      "grad_norm": 1.7437150478363037,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.2497,
+      "step": 33
+    },
+    {
+      "epoch": 0.08816855753646677,
+      "grad_norm": 2.2530760765075684,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 9.4398,
+      "step": 34
+    },
+    {
+      "epoch": 0.09076175040518639,
+      "grad_norm": 4.513284206390381,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 9.8228,
+      "step": 35
+    },
+    {
+      "epoch": 0.09335494327390599,
+      "grad_norm": 5.1368536949157715,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 8.9785,
+      "step": 36
+    },
+    {
+      "epoch": 0.09594813614262561,
+      "grad_norm": 8.476035118103027,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3183,
+      "step": 37
+    },
+    {
+      "epoch": 0.09854132901134521,
+      "grad_norm": 11.310976028442383,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 12.9887,
+      "step": 38
+    },
+    {
+      "epoch": 0.10113452188006483,
+      "grad_norm": 1.1918339729309082,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.2354,
+      "step": 39
+    },
+    {
+      "epoch": 0.10372771474878444,
+      "grad_norm": 1.146219253540039,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.5345,
+      "step": 40
+    },
+    {
+      "epoch": 0.10632090761750405,
+      "grad_norm": 1.2467947006225586,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.6546,
+      "step": 41
+    },
+    {
+      "epoch": 0.10891410048622366,
+      "grad_norm": 1.2855454683303833,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.1265,
+      "step": 42
+    },
+    {
+      "epoch": 0.11150729335494328,
+      "grad_norm": 1.4412370920181274,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.0749,
+      "step": 43
+    },
+    {
+      "epoch": 0.11410048622366288,
+      "grad_norm": 1.6290322542190552,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.445,
+      "step": 44
+    },
+    {
+      "epoch": 0.1166936790923825,
+      "grad_norm": 1.820227026939392,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.4432,
+      "step": 45
+    },
+    {
+      "epoch": 0.1192868719611021,
+      "grad_norm": 2.2414534091949463,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 9.1642,
+      "step": 46
+    },
+    {
+      "epoch": 0.12188006482982172,
+      "grad_norm": 2.7672858238220215,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 9.3451,
+      "step": 47
+    },
+    {
+      "epoch": 0.12447325769854133,
+      "grad_norm": 3.4407408237457275,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 8.1439,
+      "step": 48
+    },
+    {
+      "epoch": 0.12706645056726093,
+      "grad_norm": 5.926863193511963,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3794,
+      "step": 49
+    },
+    {
+      "epoch": 0.12965964343598055,
+      "grad_norm": 10.669682502746582,
+      "learning_rate": 1e-05,
+      "loss": 11.1949,
+      "step": 50
+    },
+    {
+      "epoch": 0.12965964343598055,
+      "eval_loss": 0.7129375338554382,
+      "eval_runtime": 2.9843,
+      "eval_samples_per_second": 16.754,
+      "eval_steps_per_second": 4.356,
+      "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": 2.6345086191140864e+17,
+  "total_flos": 5.2706607182014054e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null