Training in progress, step 49, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6dc3cab5602d16198888d33ca2c487e564fa653789e42538df82236fcfe81d4c
+oid sha256:78772dea953c4f078bb17a2b824027b32bc26ef8d303c0b1503783d97134fed0
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7e7b0a49962c1f8bf203390a2101df5eddb3bb4720dc7b65816d0525d8c8e96
+oid sha256:8f1ae15f901939f76d2b6ec05a9a56fc44941ce0b544fd32a23c63506a9dad7f
 size 259694

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3c08dd4f4d0f8bf70ba4916a22a48ca5cb6eff49f66864265bc65d1604ee991
+oid sha256:5d73ad644beff3ba03788e9d73274ebb887b8fd64e49d57363e61d5b9901354f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30ac867ff001608364612dd3b6b7c46ee7c3a7109ead81f0e242ded2685b53fe
+oid sha256:7de102f79d63951edf3a9bd9bfca97181efb3a75d66ca4c97d402f63d2e6afc0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eec57648b4610ba3a1626e237f0d57e4db004d1ae043c04f9b7d6915391be8e
+oid sha256:e4c073552e1051ed8d8f4171410cb2ab7d7d1575de3054dde1a53e25f6ec99c5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a98f0733cf4b7592c86131d89e2e8335cc2a21f37277f360545364ceb8906515
+oid sha256:0bf9b1879252a77834af53724708170cb677762ba2f7ddcb32f03a32b3f3744a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8339621e0254150598b8a53ec927095b94a662289d4252af9f13d6ac65a483e
+oid sha256:c3beede4336a46640c9aa1536e08db38f31dc18c73764913b78bf6e9f1d29144
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 11.073678970336914,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.556420233463035,
+  "epoch": 3.0505836575875485,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 49,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,174 @@
       "eval_samples_per_second": 390.526,
       "eval_steps_per_second": 101.537,
       "step": 25
+    },
+    {
+      "epoch": 1.6186770428015564,
+      "grad_norm": 6.747447490692139,
+      "learning_rate": 5.349632603465466e-05,
+      "loss": 354.3671,
+      "step": 26
+    },
+    {
+      "epoch": 1.6809338521400778,
+      "grad_norm": 6.908236980438232,
+      "learning_rate": 5.049569387691557e-05,
+      "loss": 354.321,
+      "step": 27
+    },
+    {
+      "epoch": 1.7431906614785992,
+      "grad_norm": 8.76644515991211,
+      "learning_rate": 4.751517904375915e-05,
+      "loss": 354.1532,
+      "step": 28
+    },
+    {
+      "epoch": 1.8054474708171206,
+      "grad_norm": 6.134677410125732,
+      "learning_rate": 4.456809323796123e-05,
+      "loss": 354.4615,
+      "step": 29
+    },
+    {
+      "epoch": 1.867704280155642,
+      "grad_norm": 6.538084506988525,
+      "learning_rate": 4.166759886014648e-05,
+      "loss": 354.2479,
+      "step": 30
+    },
+    {
+      "epoch": 1.9299610894941635,
+      "grad_norm": 6.925525188446045,
+      "learning_rate": 3.882665022231193e-05,
+      "loss": 354.2771,
+      "step": 31
+    },
+    {
+      "epoch": 1.9922178988326849,
+      "grad_norm": 8.646419525146484,
+      "learning_rate": 3.605793569072493e-05,
+      "loss": 354.1879,
+      "step": 32
+    },
+    {
+      "epoch": 2.054474708171206,
+      "grad_norm": 5.98707389831543,
+      "learning_rate": 3.337382101659923e-05,
+      "loss": 354.2527,
+      "step": 33
+    },
+    {
+      "epoch": 2.1167315175097277,
+      "grad_norm": 6.75242805480957,
+      "learning_rate": 3.078629410764824e-05,
+      "loss": 354.1018,
+      "step": 34
+    },
+    {
+      "epoch": 2.178988326848249,
+      "grad_norm": 7.0720367431640625,
+      "learning_rate": 2.830691148717902e-05,
+      "loss": 354.2889,
+      "step": 35
+    },
+    {
+      "epoch": 2.2412451361867705,
+      "grad_norm": 8.26923656463623,
+      "learning_rate": 2.5946746679853894e-05,
+      "loss": 354.068,
+      "step": 36
+    },
+    {
+      "epoch": 2.3035019455252916,
+      "grad_norm": 6.108309268951416,
+      "learning_rate": 2.3716340754641102e-05,
+      "loss": 354.3232,
+      "step": 37
+    },
+    {
+      "epoch": 2.3657587548638133,
+      "grad_norm": 6.104388236999512,
+      "learning_rate": 2.162565524584191e-05,
+      "loss": 354.2594,
+      "step": 38
+    },
+    {
+      "epoch": 2.4280155642023344,
+      "grad_norm": 6.536022663116455,
+      "learning_rate": 1.9684027662460257e-05,
+      "loss": 354.216,
+      "step": 39
+    },
+    {
+      "epoch": 2.490272373540856,
+      "grad_norm": 7.577517509460449,
+      "learning_rate": 1.79001297846208e-05,
+      "loss": 354.1721,
+      "step": 40
+    },
+    {
+      "epoch": 2.5525291828793772,
+      "grad_norm": 6.564501762390137,
+      "learning_rate": 1.628192893329374e-05,
+      "loss": 354.4042,
+      "step": 41
+    },
+    {
+      "epoch": 2.614785992217899,
+      "grad_norm": 6.541054725646973,
+      "learning_rate": 1.4836652386305349e-05,
+      "loss": 354.275,
+      "step": 42
+    },
+    {
+      "epoch": 2.6770428015564205,
+      "grad_norm": 6.654796600341797,
+      "learning_rate": 1.35707550995607e-05,
+      "loss": 354.1229,
+      "step": 43
+    },
+    {
+      "epoch": 2.7392996108949417,
+      "grad_norm": 8.07349967956543,
+      "learning_rate": 1.248989087764366e-05,
+      "loss": 354.0651,
+      "step": 44
+    },
+    {
+      "epoch": 2.801556420233463,
+      "grad_norm": 6.307331562042236,
+      "learning_rate": 1.1598887122553061e-05,
+      "loss": 354.4648,
+      "step": 45
+    },
+    {
+      "epoch": 2.8638132295719845,
+      "grad_norm": 6.029254913330078,
+      "learning_rate": 1.0901723273353597e-05,
+      "loss": 354.2171,
+      "step": 46
+    },
+    {
+      "epoch": 2.926070038910506,
+      "grad_norm": 6.842432022094727,
+      "learning_rate": 1.04015130330349e-05,
+      "loss": 354.2176,
+      "step": 47
+    },
+    {
+      "epoch": 2.9883268482490273,
+      "grad_norm": 7.468156814575195,
+      "learning_rate": 1.0100490461958109e-05,
+      "loss": 354.0009,
+      "step": 48
+    },
+    {
+      "epoch": 3.0505836575875485,
+      "grad_norm": 6.788173198699951,
+      "learning_rate": 1e-05,
+      "loss": 354.2026,
+      "step": 49
     }
   ],
   "logging_steps": 1,
@@ -221,12 +389,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2101346304000.0,
+  "total_flos": 4118638755840.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null