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:c5314520f034fbc78a358bbab9a2efd226a6808497514d56664fa37a62b16bf2
+oid sha256:7dd0efb7e67b8cf4c1905bd44cc75d3ea916275cd7ecbdc5fdcf3a7f607cd706
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02160cdd678e84da797f1a06a9ae0f85f01c071af290236bfddfeb507039c919
+oid sha256:917670973951c7435e685cd2f8bbb27e2ce4b7799f084df7a947dddcc935f191
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ed07a0b32316281f5d5c970534ef28deafd8e75547f1f97b9e734de0fa65c4d
+oid sha256:d7d7c219cd6da259a158a16a058c420afb7f833e190b5b4bde6a4db17143f708
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9514fe20e801c3866271ef41663177fc88cd9948ed25b5968f9f6ac3a06d79a
+oid sha256:12f8ca7121446549f7b97764e16dbe0e1bb82857a5639715e3ce11a7d19fdcdd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e190259d5c3f10195eead7d636e35977ceea7ee16cc24c6e8bb2e7322130e082
+oid sha256:8539a35a9c3b4e73ab5cf11a619bd434a74e2713fc2673607caf8a4aa555ce11
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc6c36619a01103a328c98fb7e165b550c5925ea5178dabc2e076909a7b434c0
+oid sha256:6c74144317e2e8016a1b16dadaa78c56bdbaa9a7103f554e0ce200162ce34158
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6654880046844482,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.45300113250283125,
+  "best_metric": 1.581311821937561,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.9060022650056625,
   "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": 67.891,
       "eval_steps_per_second": 8.578,
       "step": 25
+    },
+    {
+      "epoch": 0.4711211778029445,
+      "grad_norm": 2.542720079421997,
+      "learning_rate": 5e-05,
+      "loss": 1.7668,
+      "step": 26
+    },
+    {
+      "epoch": 0.48924122310305773,
+      "grad_norm": 2.1035008430480957,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.6622,
+      "step": 27
+    },
+    {
+      "epoch": 0.507361268403171,
+      "grad_norm": 1.6165552139282227,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6098,
+      "step": 28
+    },
+    {
+      "epoch": 0.5254813137032842,
+      "grad_norm": 1.1599594354629517,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.7074,
+      "step": 29
+    },
+    {
+      "epoch": 0.5436013590033975,
+      "grad_norm": 1.094414234161377,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.5716,
+      "step": 30
+    },
+    {
+      "epoch": 0.5617214043035108,
+      "grad_norm": 1.1352035999298096,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.6661,
+      "step": 31
+    },
+    {
+      "epoch": 0.579841449603624,
+      "grad_norm": 1.135955810546875,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.6262,
+      "step": 32
+    },
+    {
+      "epoch": 0.5979614949037373,
+      "grad_norm": 1.227918028831482,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.6239,
+      "step": 33
+    },
+    {
+      "epoch": 0.6160815402038505,
+      "grad_norm": 1.2326364517211914,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.5764,
+      "step": 34
+    },
+    {
+      "epoch": 0.6342015855039638,
+      "grad_norm": 1.126684308052063,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.5883,
+      "step": 35
+    },
+    {
+      "epoch": 0.652321630804077,
+      "grad_norm": 1.3494774103164673,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.5888,
+      "step": 36
+    },
+    {
+      "epoch": 0.6704416761041903,
+      "grad_norm": 1.6403988599777222,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.4864,
+      "step": 37
+    },
+    {
+      "epoch": 0.6885617214043035,
+      "grad_norm": 1.1846927404403687,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6079,
+      "step": 38
+    },
+    {
+      "epoch": 0.7066817667044167,
+      "grad_norm": 0.950275182723999,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.6306,
+      "step": 39
+    },
+    {
+      "epoch": 0.72480181200453,
+      "grad_norm": 1.0314114093780518,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.6489,
+      "step": 40
+    },
+    {
+      "epoch": 0.7429218573046432,
+      "grad_norm": 1.047741174697876,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.5711,
+      "step": 41
+    },
+    {
+      "epoch": 0.7610419026047565,
+      "grad_norm": 0.9879609942436218,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.5778,
+      "step": 42
+    },
+    {
+      "epoch": 0.7791619479048698,
+      "grad_norm": 1.109057068824768,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.6443,
+      "step": 43
+    },
+    {
+      "epoch": 0.797281993204983,
+      "grad_norm": 1.013243317604065,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6006,
+      "step": 44
+    },
+    {
+      "epoch": 0.8154020385050963,
+      "grad_norm": 0.9669159650802612,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.5514,
+      "step": 45
+    },
+    {
+      "epoch": 0.8335220838052095,
+      "grad_norm": 1.0670894384384155,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.5702,
+      "step": 46
+    },
+    {
+      "epoch": 0.8516421291053228,
+      "grad_norm": 1.054745078086853,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.5336,
+      "step": 47
+    },
+    {
+      "epoch": 0.869762174405436,
+      "grad_norm": 1.253612995147705,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.6048,
+      "step": 48
+    },
+    {
+      "epoch": 0.8878822197055493,
+      "grad_norm": 1.2807451486587524,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.5269,
+      "step": 49
+    },
+    {
+      "epoch": 0.9060022650056625,
+      "grad_norm": 2.344367504119873,
+      "learning_rate": 0.0,
+      "loss": 1.64,
+      "step": 50
+    },
+    {
+      "epoch": 0.9060022650056625,
+      "eval_loss": 1.581311821937561,
+      "eval_runtime": 5.5382,
+      "eval_samples_per_second": 67.17,
+      "eval_steps_per_second": 8.486,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null