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:dd6e21a54cf5761d82b7bd89609de888a05f38f9d115013b3a21fb05e166b8ae
+oid sha256:fbda16f22201e9e524a15af6202b88cb8086eedfb56cc7e0ad3b8e24c421e9f3
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:402dba4eec6d2b5a69b5e7c9a13cdbd57deeef3843f569223bc487f8fb8a125c
+oid sha256:4f6d99675e2f18144fed5994353ee7aedc1a51d76b5a13718330dcf9f25e7c47
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe5c89596f1d642180b865bea93be8c5dc02b146ba4a0debde4fa06d472fe06c
+oid sha256:74d669ad75c1aa74f54a0d08937a66d672c71f35137702d08f8af20c6a3c18fd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea56aee972bc1d0c8d42941343f85212051e2955991fcfd7ed6c5d198fd31cd
+oid sha256:a8eef7d5ef6f3f9f8d0479c95e3fb80b3423cd9fc87070cc203a3eaf08cbc21e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6304542941ffb39f27e62787c3f05424fe743cf336d3165cbd01c12e65b928c9
+oid sha256:84c733275063d53eb13c0eeca6f2aceb836f0813c55cf191ab1aa0f7331bc7ba
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:465ac45cb7ece6734890c72ecc3b35bb5d2252b7ddb3833e153a3fc04b5a9fe8
+oid sha256:fe1218ef1e7b0ec11629a039718758b8bd32d018addd16c14c6cee4a591307e2
 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": 0.44446834921836853,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3629764065335753,
+  "best_metric": 0.42325812578201294,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7259528130671506,
   "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": 16.642,
       "eval_steps_per_second": 4.327,
       "step": 25
+    },
+    {
+      "epoch": 0.37749546279491836,
+      "grad_norm": 1.2319997549057007,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 6.0149,
+      "step": 26
+    },
+    {
+      "epoch": 0.39201451905626133,
+      "grad_norm": 1.5031059980392456,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 6.6979,
+      "step": 27
+    },
+    {
+      "epoch": 0.40653357531760437,
+      "grad_norm": 1.725165843963623,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 6.7276,
+      "step": 28
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 1.559391736984253,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 6.9098,
+      "step": 29
+    },
+    {
+      "epoch": 0.4355716878402904,
+      "grad_norm": 1.6204358339309692,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 7.266,
+      "step": 30
+    },
+    {
+      "epoch": 0.4500907441016334,
+      "grad_norm": 1.7478471994400024,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 7.3426,
+      "step": 31
+    },
+    {
+      "epoch": 0.4646098003629764,
+      "grad_norm": 1.859602451324463,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 7.0126,
+      "step": 32
+    },
+    {
+      "epoch": 0.4791288566243194,
+      "grad_norm": 1.9271974563598633,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 7.0889,
+      "step": 33
+    },
+    {
+      "epoch": 0.49364791288566245,
+      "grad_norm": 2.088104009628296,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 6.8118,
+      "step": 34
+    },
+    {
+      "epoch": 0.5081669691470054,
+      "grad_norm": 2.275719404220581,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 7.0964,
+      "step": 35
+    },
+    {
+      "epoch": 0.5226860254083484,
+      "grad_norm": 2.5453503131866455,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 6.7696,
+      "step": 36
+    },
+    {
+      "epoch": 0.5372050816696915,
+      "grad_norm": 3.2486155033111572,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 6.8947,
+      "step": 37
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 3.0056145191192627,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 5.952,
+      "step": 38
+    },
+    {
+      "epoch": 0.5662431941923775,
+      "grad_norm": 1.3381630182266235,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 6.1744,
+      "step": 39
+    },
+    {
+      "epoch": 0.5807622504537205,
+      "grad_norm": 1.6222202777862549,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 6.6613,
+      "step": 40
+    },
+    {
+      "epoch": 0.5952813067150635,
+      "grad_norm": 1.715443730354309,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 6.4672,
+      "step": 41
+    },
+    {
+      "epoch": 0.6098003629764065,
+      "grad_norm": 1.7360793352127075,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 7.3668,
+      "step": 42
+    },
+    {
+      "epoch": 0.6243194192377496,
+      "grad_norm": 1.8243736028671265,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 6.5175,
+      "step": 43
+    },
+    {
+      "epoch": 0.6388384754990926,
+      "grad_norm": 1.931254506111145,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 6.7514,
+      "step": 44
+    },
+    {
+      "epoch": 0.6533575317604355,
+      "grad_norm": 2.2752747535705566,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 7.2249,
+      "step": 45
+    },
+    {
+      "epoch": 0.6678765880217786,
+      "grad_norm": 2.2827963829040527,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 7.4122,
+      "step": 46
+    },
+    {
+      "epoch": 0.6823956442831216,
+      "grad_norm": 2.2568490505218506,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.6329,
+      "step": 47
+    },
+    {
+      "epoch": 0.6969147005444646,
+      "grad_norm": 2.7081212997436523,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 6.6874,
+      "step": 48
+    },
+    {
+      "epoch": 0.7114337568058077,
+      "grad_norm": 2.533864974975586,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 6.7553,
+      "step": 49
+    },
+    {
+      "epoch": 0.7259528130671506,
+      "grad_norm": 3.477332353591919,
+      "learning_rate": 1e-05,
+      "loss": 7.084,
+      "step": 50
+    },
+    {
+      "epoch": 0.7259528130671506,
+      "eval_loss": 0.42325812578201294,
+      "eval_runtime": 3.0213,
+      "eval_samples_per_second": 16.549,
+      "eval_steps_per_second": 4.303,
+      "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": 2.649274029482967e+17,
+  "total_flos": 5.2936176405210726e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null