Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59536822162cfe641ce0d1182d6e0d8b8640b26c88906c0fa21c3bb9049e8ee5
+oid sha256:7ce030893098d1240ed7d4dff3e627aaddba82948fee8dfe831524fc5a660c67
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bde37760b3962f4b751b5a988b09c68524743da00191e993aeeaf744e1f7c648
+oid sha256:a9ebbc67cdb1d12bd24600e6b55de6651240da6fc6d881f87c828dd1b0078140
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc3b25964f7444e7a5cf208c11a554021117b61bc691b6e3f1774373f596074c
+oid sha256:59cb44e4072420837152db37cc1deb7f004d717da4ec44d95aeee42ac77b8477
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1e4da84041a7a7969ce0a19d01bf4413ece716c2ae8f890b30904f362d22948
+oid sha256:bf4a72d778cdc6bf8d009f5f719aa058e9bff07ce4209bb05c04edc06018c1a0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9155c73ccad965bd264fc74661bd05d42dd6109659bb2923bfa39f8c9b264f2
+oid sha256:07cb81682f344c99dba1327c5d3b81d4d08e9e320cea6b61d3ace5ce0dd6792f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6dd63e95fc017427a2b4bf75c3a61301ad572970189de6c06cb221b0f796ae
+oid sha256:6653c273417adb13163b2ede9a74cac39fd86410d23c392fa4b0590e5a4329f3
 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": 11.754063606262207,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.11031439602868175,
+  "best_metric": 11.751538276672363,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2206287920573635,
   "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": 437.174,
       "eval_steps_per_second": 113.665,
       "step": 25
+    },
+    {
+      "epoch": 0.11472697186982901,
+      "grad_norm": 0.08237963169813156,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 11.7582,
+      "step": 26
+    },
+    {
+      "epoch": 0.11913954771097628,
+      "grad_norm": 0.0781407356262207,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.7578,
+      "step": 27
+    },
+    {
+      "epoch": 0.12355212355212356,
+      "grad_norm": 0.08831605315208435,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 11.7569,
+      "step": 28
+    },
+    {
+      "epoch": 0.12796469939327082,
+      "grad_norm": 0.0830259621143341,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 11.7563,
+      "step": 29
+    },
+    {
+      "epoch": 0.13237727523441808,
+      "grad_norm": 0.08338623493909836,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 11.7598,
+      "step": 30
+    },
+    {
+      "epoch": 0.13678985107556535,
+      "grad_norm": 0.09287534654140472,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 11.7559,
+      "step": 31
+    },
+    {
+      "epoch": 0.14120242691671264,
+      "grad_norm": 0.08480775356292725,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 11.7557,
+      "step": 32
+    },
+    {
+      "epoch": 0.1456150027578599,
+      "grad_norm": 0.10712478309869766,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 11.7569,
+      "step": 33
+    },
+    {
+      "epoch": 0.15002757859900717,
+      "grad_norm": 0.1056855097413063,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 11.7546,
+      "step": 34
+    },
+    {
+      "epoch": 0.15444015444015444,
+      "grad_norm": 0.11568643897771835,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 11.7539,
+      "step": 35
+    },
+    {
+      "epoch": 0.1588527302813017,
+      "grad_norm": 0.12338628619909286,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 11.7537,
+      "step": 36
+    },
+    {
+      "epoch": 0.16326530612244897,
+      "grad_norm": 0.1299927532672882,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 11.7543,
+      "step": 37
+    },
+    {
+      "epoch": 0.16767788196359626,
+      "grad_norm": 0.09283430874347687,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 11.7571,
+      "step": 38
+    },
+    {
+      "epoch": 0.17209045780474352,
+      "grad_norm": 0.0892544612288475,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 11.7577,
+      "step": 39
+    },
+    {
+      "epoch": 0.1765030336458908,
+      "grad_norm": 0.08588219434022903,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 11.7591,
+      "step": 40
+    },
+    {
+      "epoch": 0.18091560948703805,
+      "grad_norm": 0.10914891213178635,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 11.7575,
+      "step": 41
+    },
+    {
+      "epoch": 0.18532818532818532,
+      "grad_norm": 0.10082217305898666,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 11.7547,
+      "step": 42
+    },
+    {
+      "epoch": 0.1897407611693326,
+      "grad_norm": 0.10159717500209808,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 11.7576,
+      "step": 43
+    },
+    {
+      "epoch": 0.19415333701047988,
+      "grad_norm": 0.10012318938970566,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 11.754,
+      "step": 44
+    },
+    {
+      "epoch": 0.19856591285162714,
+      "grad_norm": 0.11955250799655914,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 11.7546,
+      "step": 45
+    },
+    {
+      "epoch": 0.2029784886927744,
+      "grad_norm": 0.10700767487287521,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 11.7574,
+      "step": 46
+    },
+    {
+      "epoch": 0.20739106453392167,
+      "grad_norm": 0.10580254346132278,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 11.7561,
+      "step": 47
+    },
+    {
+      "epoch": 0.21180364037506894,
+      "grad_norm": 0.10959888994693756,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 11.7556,
+      "step": 48
+    },
+    {
+      "epoch": 0.21621621621621623,
+      "grad_norm": 0.12163785099983215,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 11.7515,
+      "step": 49
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "grad_norm": 0.1607298105955124,
+      "learning_rate": 1e-05,
+      "loss": 11.7545,
+      "step": 50
+    },
+    {
+      "epoch": 0.2206287920573635,
+      "eval_loss": 11.751538276672363,
+      "eval_runtime": 0.1129,
+      "eval_samples_per_second": 442.842,
+      "eval_steps_per_second": 115.139,
+      "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": 81943068672000.0,
+  "total_flos": 163886137344000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null