Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87f3eb91fcf01c18e042f8b79a8f9d9e495ddc64bf519224d0b3e217bee51bf7
+oid sha256:7e7267bc84a4469c0b9333a7cdc9e2c9fbcaacce313f39529a05163fec42fe8f
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2a33d42bbc1e3a0ab72f152d4480094bb5dc2d383955f2af43f84065d017f1a
+oid sha256:cceb0cb1d008062b4b8ba06a9a63d6eaedff7cb8dcbe80843aadd1268a1900b4
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8235692eca218a99363e9cf0875eab1f1233673c53beb72af754474a6a2a8e63
+oid sha256:a37221e38224a438c7db13429642ba640876c935336c9276e55bcc764de40544
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d8f7e4aeaafdd9a36eb4fe1e75155c79d7832621b7e592f0d9d0963b1e6350a
+oid sha256:a29b159be9ccbdb1f70b6f27bbe59c1f034c46def26cc460853f7aad0e58b855
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b5a21af16ee766785675a0c9b5da33184a75c1ab88d06b86a098eced4225bf0
+oid sha256:3682300f808555107115b9c113de1cce7394d1494615ac596117e2576a00bd90
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c5d285df93ad6accb4ead70b1fc3780fdbec4fc0733b599094194bd86c99d72
+oid sha256:3da257874618b1eb1cc2d9b4fb9c05077b5c6a30c86e2f54927a07498636b12e
 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": 3.4724762439727783,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.015196413646379454,
+  "best_metric": 3.4378933906555176,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.030392827292758908,
   "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": 27.227,
       "eval_steps_per_second": 7.079,
       "step": 25
+    },
+    {
+      "epoch": 0.015804270192234633,
+      "grad_norm": 0.6599547266960144,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.4072,
+      "step": 26
+    },
+    {
+      "epoch": 0.01641212673808981,
+      "grad_norm": 0.7060936689376831,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 3.385,
+      "step": 27
+    },
+    {
+      "epoch": 0.017019983283944988,
+      "grad_norm": 0.8498525619506836,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.4661,
+      "step": 28
+    },
+    {
+      "epoch": 0.01762783982980017,
+      "grad_norm": 0.8462444543838501,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.4616,
+      "step": 29
+    },
+    {
+      "epoch": 0.018235696375655346,
+      "grad_norm": 0.708667516708374,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.4996,
+      "step": 30
+    },
+    {
+      "epoch": 0.018843552921510524,
+      "grad_norm": 0.7013354301452637,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.5255,
+      "step": 31
+    },
+    {
+      "epoch": 0.0194514094673657,
+      "grad_norm": 0.7256174683570862,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.6334,
+      "step": 32
+    },
+    {
+      "epoch": 0.02005926601322088,
+      "grad_norm": 0.7189586162567139,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.5756,
+      "step": 33
+    },
+    {
+      "epoch": 0.02066712255907606,
+      "grad_norm": 0.9632193446159363,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.662,
+      "step": 34
+    },
+    {
+      "epoch": 0.021274979104931237,
+      "grad_norm": 1.1224030256271362,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.6491,
+      "step": 35
+    },
+    {
+      "epoch": 0.021882835650786414,
+      "grad_norm": 1.4623186588287354,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.8356,
+      "step": 36
+    },
+    {
+      "epoch": 0.02249069219664159,
+      "grad_norm": 2.6539292335510254,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.9538,
+      "step": 37
+    },
+    {
+      "epoch": 0.023098548742496772,
+      "grad_norm": 0.6411238312721252,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.4825,
+      "step": 38
+    },
+    {
+      "epoch": 0.02370640528835195,
+      "grad_norm": 0.7229188680648804,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.4894,
+      "step": 39
+    },
+    {
+      "epoch": 0.024314261834207127,
+      "grad_norm": 0.7024473547935486,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.3929,
+      "step": 40
+    },
+    {
+      "epoch": 0.024922118380062305,
+      "grad_norm": 0.6970648765563965,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.3762,
+      "step": 41
+    },
+    {
+      "epoch": 0.025529974925917482,
+      "grad_norm": 0.6724116802215576,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.4809,
+      "step": 42
+    },
+    {
+      "epoch": 0.026137831471772663,
+      "grad_norm": 0.6194472312927246,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.4265,
+      "step": 43
+    },
+    {
+      "epoch": 0.02674568801762784,
+      "grad_norm": 0.6786876916885376,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.6158,
+      "step": 44
+    },
+    {
+      "epoch": 0.027353544563483018,
+      "grad_norm": 0.794440507888794,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.6502,
+      "step": 45
+    },
+    {
+      "epoch": 0.027961401109338195,
+      "grad_norm": 0.752371072769165,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.6907,
+      "step": 46
+    },
+    {
+      "epoch": 0.028569257655193376,
+      "grad_norm": 0.8845945000648499,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.5251,
+      "step": 47
+    },
+    {
+      "epoch": 0.029177114201048553,
+      "grad_norm": 1.2242646217346191,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.6133,
+      "step": 48
+    },
+    {
+      "epoch": 0.02978497074690373,
+      "grad_norm": 1.964848279953003,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.8659,
+      "step": 49
+    },
+    {
+      "epoch": 0.030392827292758908,
+      "grad_norm": 3.6303746700286865,
+      "learning_rate": 1e-05,
+      "loss": 3.7604,
+      "step": 50
+    },
+    {
+      "epoch": 0.030392827292758908,
+      "eval_loss": 3.4378933906555176,
+      "eval_runtime": 1.8363,
+      "eval_samples_per_second": 27.229,
+      "eval_steps_per_second": 7.079,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null