Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c553c821de6ba092f56f56009d780f419c7376303c7c7cc5d478caa10cd90af
+oid sha256:ca5c36893aa099c8cc957b58daf4a6c03d96cb635cfb681ae37b0433e3df9f8a
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d69215ae4c593d4f27aafc58cb090d2df7e6fa9185b818e438a127c717fa0911
+oid sha256:97e0d6f49069332e28ab7c96c79f82cf868023e160b407ffcb5884d1235cb175
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87a239a650621eea6047d5f1df1da829df6d05784765713834ce00ffa745f811
+oid sha256:2b5a87fc80ae366620e6e42965ed27e51aa26b6f70839a3225a3d354e734b449
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f87dd1cb96420df4269b40078ff1e04650698b609322540d2cfe8f3157ff40a
+oid sha256:34b853a6c44af7b8070b8232348756bab83bc04bbf3acdcb64fbb4a999097fc1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7472dfa43449500c6cc6962d407e0b40c5c1ca13fd520df9d7996e6831525ca8
+oid sha256:b327b145217001a1c6409259d40e5349097624a2efc89ec126670164714aa09e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af04c126da6cc121d926cffbc6e3948afe643aff23c80ddec07593a653fcbcce
+oid sha256:18736e8975ae7cf3ce7ed6cc65082fd76c4c104e54a3fb3fd3a8eb717855f64f
 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": 6.916877269744873,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012340346763744061,
+  "best_metric": 6.908915996551514,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.024680693527488123,
   "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": 674.775,
       "eval_steps_per_second": 175.441,
       "step": 25
+    },
+    {
+      "epoch": 0.012833960634293824,
+      "grad_norm": 0.13884158432483673,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 6.9225,
+      "step": 26
+    },
+    {
+      "epoch": 0.013327574504843585,
+      "grad_norm": 0.1499403864145279,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 6.9219,
+      "step": 27
+    },
+    {
+      "epoch": 0.013821188375393348,
+      "grad_norm": 0.1470962017774582,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 6.9218,
+      "step": 28
+    },
+    {
+      "epoch": 0.014314802245943111,
+      "grad_norm": 0.15731434524059296,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 6.9193,
+      "step": 29
+    },
+    {
+      "epoch": 0.014808416116492874,
+      "grad_norm": 0.14495715498924255,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.9224,
+      "step": 30
+    },
+    {
+      "epoch": 0.015302029987042635,
+      "grad_norm": 0.15400440990924835,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 6.9177,
+      "step": 31
+    },
+    {
+      "epoch": 0.015795643857592398,
+      "grad_norm": 0.15128593146800995,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 6.9184,
+      "step": 32
+    },
+    {
+      "epoch": 0.01628925772814216,
+      "grad_norm": 0.14144425094127655,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 6.9201,
+      "step": 33
+    },
+    {
+      "epoch": 0.016782871598691924,
+      "grad_norm": 0.1577358841896057,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 6.9144,
+      "step": 34
+    },
+    {
+      "epoch": 0.017276485469241685,
+      "grad_norm": 0.14602337777614594,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 6.9174,
+      "step": 35
+    },
+    {
+      "epoch": 0.01777009933979145,
+      "grad_norm": 0.16055308282375336,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 6.9148,
+      "step": 36
+    },
+    {
+      "epoch": 0.01826371321034121,
+      "grad_norm": 0.1566527783870697,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 6.9134,
+      "step": 37
+    },
+    {
+      "epoch": 0.01875732708089097,
+      "grad_norm": 0.150618776679039,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 6.9186,
+      "step": 38
+    },
+    {
+      "epoch": 0.019250940951440736,
+      "grad_norm": 0.1551329344511032,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 6.9181,
+      "step": 39
+    },
+    {
+      "epoch": 0.019744554821990497,
+      "grad_norm": 0.15703345835208893,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 6.9167,
+      "step": 40
+    },
+    {
+      "epoch": 0.020238168692540262,
+      "grad_norm": 0.1670963615179062,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 6.9153,
+      "step": 41
+    },
+    {
+      "epoch": 0.020731782563090023,
+      "grad_norm": 0.15504442155361176,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 6.9155,
+      "step": 42
+    },
+    {
+      "epoch": 0.021225396433639784,
+      "grad_norm": 0.1557377576828003,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 6.9165,
+      "step": 43
+    },
+    {
+      "epoch": 0.02171901030418955,
+      "grad_norm": 0.15476340055465698,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 6.9163,
+      "step": 44
+    },
+    {
+      "epoch": 0.02221262417473931,
+      "grad_norm": 0.16276222467422485,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 6.9113,
+      "step": 45
+    },
+    {
+      "epoch": 0.02270623804528907,
+      "grad_norm": 0.15289202332496643,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 6.9168,
+      "step": 46
+    },
+    {
+      "epoch": 0.023199851915838836,
+      "grad_norm": 0.1528581827878952,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.9146,
+      "step": 47
+    },
+    {
+      "epoch": 0.023693465786388597,
+      "grad_norm": 0.15851595997810364,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 6.9168,
+      "step": 48
+    },
+    {
+      "epoch": 0.02418707965693836,
+      "grad_norm": 0.16302946209907532,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 6.9156,
+      "step": 49
+    },
+    {
+      "epoch": 0.024680693527488123,
+      "grad_norm": 0.16977712512016296,
+      "learning_rate": 1e-05,
+      "loss": 6.9121,
+      "step": 50
+    },
+    {
+      "epoch": 0.024680693527488123,
+      "eval_loss": 6.908915996551514,
+      "eval_runtime": 0.0709,
+      "eval_samples_per_second": 705.333,
+      "eval_steps_per_second": 183.387,
+      "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": 2852978688000.0,
+  "total_flos": 5705957376000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null