Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:543ed420611bf3bbf49df1b32435c161bf127f1cc69400a8c5bd7a295e2a5da7
+oid sha256:a3badbccf24ba63aa666ef25b85c799e7c9388142542e134f99c18881b18b231
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ded96e668e7a2a7259eecc4112b48ed18b3d02648f853a942b3b2a4c8e60a181
+oid sha256:ef8816c4187ea3934d4e8a4159c234967741f56de57526779e6abf19e7de7c06
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3bb2a808089f7ae08f7d4ddda42b05f0169f1bd2eda7406a823292b6d78e4cd1
+oid sha256:f8c9763da1e3087ff7aa50e99b47af9f50569a2f01fa1d4d32102e1362500cca
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e77367dcec8f5c251115d2375ebaf3139963cabfd0b53d4af4ce515f8232849f
+oid sha256:e2911ed03ffdf701c23498a501e9b447d7448be16f4e88294babef2df490f803
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f852f68a2b42f052bdcf8bf638375e8e4fab5452bbf2329183dcb237751f7c8
+oid sha256:8469d24707e229ec76eb8a59e2bf5fcf10c26701a399ae795e7286dcaf15e6bd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5630ffc5e774c285dc141d97b2b9dfc6401916f4874d98254da5355df9629e0f
+oid sha256:5d46a6b10e6e73a377f5ab64b6531836c2c6d419c7b44a87fa243c6b04ccf445
 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": 2.450536012649536,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.28188865398167723,
+  "best_metric": 2.402477979660034,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5637773079633545,
   "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": 14.695,
       "eval_steps_per_second": 3.821,
       "step": 25
+    },
+    {
+      "epoch": 0.29316420014094435,
+      "grad_norm": 0.44498252868652344,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.1312,
+      "step": 26
+    },
+    {
+      "epoch": 0.3044397463002114,
+      "grad_norm": 0.5225245356559753,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.1957,
+      "step": 27
+    },
+    {
+      "epoch": 0.3157152924594785,
+      "grad_norm": 0.613101601600647,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.2669,
+      "step": 28
+    },
+    {
+      "epoch": 0.3269908386187456,
+      "grad_norm": 0.69422847032547,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.3354,
+      "step": 29
+    },
+    {
+      "epoch": 0.3382663847780127,
+      "grad_norm": 0.7282578349113464,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.4521,
+      "step": 30
+    },
+    {
+      "epoch": 0.34954193093727975,
+      "grad_norm": 0.758098840713501,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.4844,
+      "step": 31
+    },
+    {
+      "epoch": 0.3608174770965469,
+      "grad_norm": 0.7578940987586975,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.5849,
+      "step": 32
+    },
+    {
+      "epoch": 0.37209302325581395,
+      "grad_norm": 0.7460212707519531,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.5532,
+      "step": 33
+    },
+    {
+      "epoch": 0.383368569415081,
+      "grad_norm": 0.9101610779762268,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.7905,
+      "step": 34
+    },
+    {
+      "epoch": 0.39464411557434814,
+      "grad_norm": 0.9511696696281433,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.8009,
+      "step": 35
+    },
+    {
+      "epoch": 0.4059196617336152,
+      "grad_norm": 1.00968599319458,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.7485,
+      "step": 36
+    },
+    {
+      "epoch": 0.41719520789288234,
+      "grad_norm": 1.268140435218811,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.8114,
+      "step": 37
+    },
+    {
+      "epoch": 0.4284707540521494,
+      "grad_norm": 0.39350399374961853,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.9405,
+      "step": 38
+    },
+    {
+      "epoch": 0.4397463002114165,
+      "grad_norm": 0.3165318965911865,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.1426,
+      "step": 39
+    },
+    {
+      "epoch": 0.4510218463706836,
+      "grad_norm": 0.3479296863079071,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.2977,
+      "step": 40
+    },
+    {
+      "epoch": 0.46229739252995067,
+      "grad_norm": 0.41276392340660095,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.2873,
+      "step": 41
+    },
+    {
+      "epoch": 0.47357293868921774,
+      "grad_norm": 0.45391130447387695,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.2867,
+      "step": 42
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.4915991723537445,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.3572,
+      "step": 43
+    },
+    {
+      "epoch": 0.49612403100775193,
+      "grad_norm": 0.5937020778656006,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.5314,
+      "step": 44
+    },
+    {
+      "epoch": 0.507399577167019,
+      "grad_norm": 0.6090872883796692,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.5386,
+      "step": 45
+    },
+    {
+      "epoch": 0.5186751233262861,
+      "grad_norm": 0.6918545365333557,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.5389,
+      "step": 46
+    },
+    {
+      "epoch": 0.5299506694855532,
+      "grad_norm": 0.8110177516937256,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.6418,
+      "step": 47
+    },
+    {
+      "epoch": 0.5412262156448203,
+      "grad_norm": 0.9591464996337891,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.785,
+      "step": 48
+    },
+    {
+      "epoch": 0.5525017618040874,
+      "grad_norm": 1.1250903606414795,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.7281,
+      "step": 49
+    },
+    {
+      "epoch": 0.5637773079633545,
+      "grad_norm": 1.741119623184204,
+      "learning_rate": 1e-05,
+      "loss": 2.9174,
+      "step": 50
+    },
+    {
+      "epoch": 0.5637773079633545,
+      "eval_loss": 2.402477979660034,
+      "eval_runtime": 3.4073,
+      "eval_samples_per_second": 14.674,
+      "eval_steps_per_second": 3.815,
+      "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": 3.317763172739318e+17,
+  "total_flos": 6.633454034495734e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null