Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4994183306984912e8366a60c13fb3d7dfef5795f5ba6ba22ae142218e986194
+oid sha256:870d3a9cc274c3be986175e5de965d116a820e57d346e015fcc3aa75c468b9e0
 size 2436967616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed9293522cdf5fe1c63254d9f1c4009656b4ed67c3145959e8cf3b8cb79302b2
+oid sha256:c954ca4e366e3e82eb4776b45598add1af29e39523b05e82ad3155eb0e603f92
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:280b3e6cb09232c5239a067332af69d19517af70519c6b9c4909b36cb49379a8
+oid sha256:82701af47aee262ed2de158601900d0fb32c3907f9ce5c99bd179091b4d1fc62
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15eb1b3f11e3f90b9a24d2310e3e16fddc042471df751ef308f61d988a9a0fa7
+oid sha256:ca8bf645ce6a95c97a3f89254193dc7bf1940f1525a365e879da119b46278092
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69266c0513bff85135bb17b1231273390ca5f750fa3d13599d95044e7a20cc95
+oid sha256:7173c84e432f1f327e91e1c1c746da9eb0c802512b249878ab51703e23203def
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d3cfaafa3a4bf5df9c1eeb20e1bea1b7542889376cb72239836c668c351455f
+oid sha256:afab7caa3d9479a1ad7e6a0a95b1b57f49f4490949c3c3285bcf7517b454e7e6
 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": 3.4176676273345947,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0319310289774088,
+  "best_metric": 2.955871820449829,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0638620579548176,
   "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": 21.382,
       "eval_steps_per_second": 5.559,
       "step": 25
+    },
+    {
+      "epoch": 0.033208270136505146,
+      "grad_norm": 2.9280927181243896,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.5654,
+      "step": 26
+    },
+    {
+      "epoch": 0.0344855112956015,
+      "grad_norm": 2.801668882369995,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.7446,
+      "step": 27
+    },
+    {
+      "epoch": 0.03576275245469785,
+      "grad_norm": 3.4079697132110596,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.2324,
+      "step": 28
+    },
+    {
+      "epoch": 0.0370399936137942,
+      "grad_norm": 4.457375526428223,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.2512,
+      "step": 29
+    },
+    {
+      "epoch": 0.038317234772890556,
+      "grad_norm": 12.326119422912598,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.4725,
+      "step": 30
+    },
+    {
+      "epoch": 0.03959447593198691,
+      "grad_norm": 6.261662006378174,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.2874,
+      "step": 31
+    },
+    {
+      "epoch": 0.04087171709108326,
+      "grad_norm": 4.075770854949951,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.3201,
+      "step": 32
+    },
+    {
+      "epoch": 0.04214895825017961,
+      "grad_norm": 2.7039589881896973,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.6826,
+      "step": 33
+    },
+    {
+      "epoch": 0.043426199409275966,
+      "grad_norm": 2.4863486289978027,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.7119,
+      "step": 34
+    },
+    {
+      "epoch": 0.04470344056837232,
+      "grad_norm": 3.140991687774658,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.5157,
+      "step": 35
+    },
+    {
+      "epoch": 0.04598068172746867,
+      "grad_norm": 3.5709006786346436,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.8917,
+      "step": 36
+    },
+    {
+      "epoch": 0.04725792288656502,
+      "grad_norm": 4.075592994689941,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.3369,
+      "step": 37
+    },
+    {
+      "epoch": 0.04853516404566137,
+      "grad_norm": 3.7284469604492188,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.5284,
+      "step": 38
+    },
+    {
+      "epoch": 0.04981240520475772,
+      "grad_norm": 3.799734354019165,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.1592,
+      "step": 39
+    },
+    {
+      "epoch": 0.051089646363854074,
+      "grad_norm": 3.1631314754486084,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.7785,
+      "step": 40
+    },
+    {
+      "epoch": 0.05236688752295043,
+      "grad_norm": 3.053359031677246,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.9911,
+      "step": 41
+    },
+    {
+      "epoch": 0.05364412868204678,
+      "grad_norm": 3.8054542541503906,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.8448,
+      "step": 42
+    },
+    {
+      "epoch": 0.05492136984114313,
+      "grad_norm": 2.217982530593872,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.7711,
+      "step": 43
+    },
+    {
+      "epoch": 0.056198611000239485,
+      "grad_norm": 2.570152521133423,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.3292,
+      "step": 44
+    },
+    {
+      "epoch": 0.05747585215933584,
+      "grad_norm": 2.582834482192993,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.452,
+      "step": 45
+    },
+    {
+      "epoch": 0.05875309331843219,
+      "grad_norm": 4.0312957763671875,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.5707,
+      "step": 46
+    },
+    {
+      "epoch": 0.060030334477528535,
+      "grad_norm": 2.474395513534546,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.4277,
+      "step": 47
+    },
+    {
+      "epoch": 0.06130757563662489,
+      "grad_norm": 2.419994592666626,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.6311,
+      "step": 48
+    },
+    {
+      "epoch": 0.06258481679572124,
+      "grad_norm": 4.7385430335998535,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.4403,
+      "step": 49
+    },
+    {
+      "epoch": 0.0638620579548176,
+      "grad_norm": 4.351629257202148,
+      "learning_rate": 1e-05,
+      "loss": 3.6853,
+      "step": 50
+    },
+    {
+      "epoch": 0.0638620579548176,
+      "eval_loss": 2.955871820449829,
+      "eval_runtime": 2.355,
+      "eval_samples_per_second": 21.232,
+      "eval_steps_per_second": 5.52,
+      "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": 2.984043419271168e+17,
+  "total_flos": 5.968086838542336e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null