Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2259d59255d1fdc1675c0b0524d722cd97fc01ba7beab4c7c6d543525a0cb704
+oid sha256:1d6239c7e17da49c894b6f2677ee4ab56f59482de745f43820e0c683a1e16fb9
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c047fddd711af36e1b3aa40f7b4ed12c55fd55e49eeaddc0302fbf033428b3cf
+oid sha256:73887fccc0e79f65dbc64a0060a90d28f27fdff3c36d6833e25595fdc9b6e1f9
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fbe7b0e2c56dd6a53333476c13f95c955977e2b58c3d045ab5a67beefef3a75
+oid sha256:dc5e23a004b9780c6ae9fa9f4fbdcb5420e59fbb989bbee335e6208e9cac1d22
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b60df96473e6ef83c0bd6e16377bfd2fdfeb6e5df729f23b06aaef5aec0c355
+oid sha256:055f375cd18ca5ae032eea15fdb1794195933f706d8341b766779e9bc44c6dc8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d10c01c66b001fcc8d24d40c093888a7ea2dcb0a20768149a5f765080a15d2fe
+oid sha256:4c4a857d6368ea00314aff3a472dff2412db2f8a467f06d999f0fcf84e4bafdd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ec39118955f17c904b7c8e051801b926b756ca7f61042cce5e5a8c5942d61d
+oid sha256:02942c51dd86f72a9ed350b3926c55e9c9d59d1fa861ba343d8b37eabab10a65
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df0d85110df25b13ee5d42e45cc81a4d1d50e1fb0599366d48777f04979e6c88
+oid sha256:e13907c7b4b4002600f5c88eb70a7e187a99ef52464c3c8ca52c5bbdcac0bd3d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.907273530960083,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.2066365007541477,
+  "best_metric": 0.8835566639900208,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.4132730015082955,
   "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": 15.455,
       "eval_steps_per_second": 4.018,
       "step": 25
+    },
+    {
+      "epoch": 1.2549019607843137,
+      "grad_norm": 0.5164334177970886,
+      "learning_rate": 6.978440718598757e-05,
+      "loss": 0.9255,
+      "step": 26
+    },
+    {
+      "epoch": 1.3031674208144797,
+      "grad_norm": 0.3558405339717865,
+      "learning_rate": 6.757685356832243e-05,
+      "loss": 0.9118,
+      "step": 27
+    },
+    {
+      "epoch": 1.3514328808446456,
+      "grad_norm": 0.3763732314109802,
+      "learning_rate": 6.533594839593081e-05,
+      "loss": 0.9167,
+      "step": 28
+    },
+    {
+      "epoch": 1.3996983408748114,
+      "grad_norm": 0.41895684599876404,
+      "learning_rate": 6.306763414648311e-05,
+      "loss": 0.8792,
+      "step": 29
+    },
+    {
+      "epoch": 1.4479638009049773,
+      "grad_norm": 0.4729040861129761,
+      "learning_rate": 6.07779259815948e-05,
+      "loss": 0.8689,
+      "step": 30
+    },
+    {
+      "epoch": 1.4962292609351433,
+      "grad_norm": 0.4113113284111023,
+      "learning_rate": 5.84728957956991e-05,
+      "loss": 0.8323,
+      "step": 31
+    },
+    {
+      "epoch": 1.544494720965309,
+      "grad_norm": 0.38738012313842773,
+      "learning_rate": 5.61586561144745e-05,
+      "loss": 0.9668,
+      "step": 32
+    },
+    {
+      "epoch": 1.5927601809954752,
+      "grad_norm": 0.4025406241416931,
+      "learning_rate": 5.384134388552552e-05,
+      "loss": 0.9097,
+      "step": 33
+    },
+    {
+      "epoch": 1.641025641025641,
+      "grad_norm": 0.4479067027568817,
+      "learning_rate": 5.152710420430091e-05,
+      "loss": 0.9427,
+      "step": 34
+    },
+    {
+      "epoch": 1.689291101055807,
+      "grad_norm": 0.44481536746025085,
+      "learning_rate": 4.9222074018405206e-05,
+      "loss": 0.8624,
+      "step": 35
+    },
+    {
+      "epoch": 1.737556561085973,
+      "grad_norm": 0.46713030338287354,
+      "learning_rate": 4.693236585351691e-05,
+      "loss": 0.8882,
+      "step": 36
+    },
+    {
+      "epoch": 1.7858220211161386,
+      "grad_norm": 0.3744671642780304,
+      "learning_rate": 4.4664051604069214e-05,
+      "loss": 0.9416,
+      "step": 37
+    },
+    {
+      "epoch": 1.8340874811463048,
+      "grad_norm": 0.44846299290657043,
+      "learning_rate": 4.2423146431677585e-05,
+      "loss": 1.0138,
+      "step": 38
+    },
+    {
+      "epoch": 1.8823529411764706,
+      "grad_norm": 0.4410933256149292,
+      "learning_rate": 4.021559281401244e-05,
+      "loss": 0.8851,
+      "step": 39
+    },
+    {
+      "epoch": 1.9306184012066365,
+      "grad_norm": 0.47139236330986023,
+      "learning_rate": 3.804724478641667e-05,
+      "loss": 0.8259,
+      "step": 40
+    },
+    {
+      "epoch": 1.9788838612368025,
+      "grad_norm": 0.5577002167701721,
+      "learning_rate": 3.592385241805628e-05,
+      "loss": 1.0754,
+      "step": 41
+    },
+    {
+      "epoch": 2.0271493212669682,
+      "grad_norm": 0.4690263569355011,
+      "learning_rate": 3.385104656377062e-05,
+      "loss": 0.9935,
+      "step": 42
+    },
+    {
+      "epoch": 2.0754147812971344,
+      "grad_norm": 0.38023629784584045,
+      "learning_rate": 3.183432393205763e-05,
+      "loss": 0.8952,
+      "step": 43
+    },
+    {
+      "epoch": 2.1236802413273,
+      "grad_norm": 0.41368529200553894,
+      "learning_rate": 2.9879032508791093e-05,
+      "loss": 0.9206,
+      "step": 44
+    },
+    {
+      "epoch": 2.171945701357466,
+      "grad_norm": 0.4637509882450104,
+      "learning_rate": 2.799035737532344e-05,
+      "loss": 0.826,
+      "step": 45
+    },
+    {
+      "epoch": 2.220211161387632,
+      "grad_norm": 0.510759711265564,
+      "learning_rate": 2.6173306958582123e-05,
+      "loss": 0.8312,
+      "step": 46
+    },
+    {
+      "epoch": 2.268476621417798,
+      "grad_norm": 0.4286244511604309,
+      "learning_rate": 2.443269974962181e-05,
+      "loss": 0.7866,
+      "step": 47
+    },
+    {
+      "epoch": 2.3167420814479636,
+      "grad_norm": 0.37086257338523865,
+      "learning_rate": 2.277315152585231e-05,
+      "loss": 0.7716,
+      "step": 48
+    },
+    {
+      "epoch": 2.3650075414781297,
+      "grad_norm": 0.415539026260376,
+      "learning_rate": 2.1199063110826618e-05,
+      "loss": 0.7904,
+      "step": 49
+    },
+    {
+      "epoch": 2.4132730015082955,
+      "grad_norm": 0.47227543592453003,
+      "learning_rate": 1.9714608704048037e-05,
+      "loss": 0.7771,
+      "step": 50
+    },
+    {
+      "epoch": 2.4132730015082955,
+      "eval_loss": 0.8835566639900208,
+      "eval_runtime": 3.2406,
+      "eval_samples_per_second": 15.429,
+      "eval_steps_per_second": 4.012,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null