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:bb56fd2112a6869e73514f4752ae9fb47c9a36cd9aec89ad0bf31dd46a0aa0e5
+oid sha256:ddd0f29413149336cd4917ac3ed474b538aa5eb1b9756ff390fe123daed9a293
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61703e857fd7711b0616c9cba4f439790e7f4982102a4c92c97282e88ad034a7
+oid sha256:a9354bf07bfa81aefd2c17a0aaa1f073b635b011268d75f5d30f32567a72ac16
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ade23b41bbd155310fd1b897b0716b9bf297375db9164f5a1de86bf845e448e
+oid sha256:466026b1d56db3aad559727172b0b7c416454c0ce61a8887f4cdab3ac1a8d42a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:017934e6fb9e4ae12d06d02e43c7379192fed2c847c4475ecfe9b645b9d4cd5b
+oid sha256:3bc682a7d00141b62262bf1bcc7ebbf86b1ce05a6d1cc658a33c4a811e314023
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f346947469840f0090c4d5ffcd8170f5c58fd1ddb282d70c16354cb209e0a59
+oid sha256:dd5599b6b5632839ea5b1a46bb5ba5a776be2da51ee2e99e59107666df644afe
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6125bd901fbdddfb043f2ad26702da6ada80f3d4ddca552c4c40fc4ca4f555e
+oid sha256:dc7535e10e53476bba009b2266e858a760980ba7a1f2381e59e3661073dbf777
 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": 0.5469670295715332,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7326007326007326,
+  "best_metric": 0.44779691100120544,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.4652014652014653,
   "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": 133.402,
       "eval_steps_per_second": 16.82,
       "step": 25
+    },
+    {
+      "epoch": 0.7619047619047619,
+      "grad_norm": 2.2465901374816895,
+      "learning_rate": 5e-05,
+      "loss": 0.7292,
+      "step": 26
+    },
+    {
+      "epoch": 0.7912087912087912,
+      "grad_norm": 2.726881742477417,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5378,
+      "step": 27
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 3.4950568675994873,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.5653,
+      "step": 28
+    },
+    {
+      "epoch": 0.8498168498168498,
+      "grad_norm": 4.879532814025879,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.5347,
+      "step": 29
+    },
+    {
+      "epoch": 0.8791208791208791,
+      "grad_norm": 3.8265433311462402,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.5369,
+      "step": 30
+    },
+    {
+      "epoch": 0.9084249084249084,
+      "grad_norm": 2.4588706493377686,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5768,
+      "step": 31
+    },
+    {
+      "epoch": 0.9377289377289377,
+      "grad_norm": 2.2632195949554443,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5339,
+      "step": 32
+    },
+    {
+      "epoch": 0.967032967032967,
+      "grad_norm": 1.8849637508392334,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5138,
+      "step": 33
+    },
+    {
+      "epoch": 0.9963369963369964,
+      "grad_norm": 1.885278344154358,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.6452,
+      "step": 34
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 8.720766067504883,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.9202,
+      "step": 35
+    },
+    {
+      "epoch": 1.054945054945055,
+      "grad_norm": 3.255974531173706,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4334,
+      "step": 36
+    },
+    {
+      "epoch": 1.0842490842490842,
+      "grad_norm": 2.663154363632202,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4535,
+      "step": 37
+    },
+    {
+      "epoch": 1.1135531135531136,
+      "grad_norm": 1.670108437538147,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.323,
+      "step": 38
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 1.3575395345687866,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3692,
+      "step": 39
+    },
+    {
+      "epoch": 1.1721611721611722,
+      "grad_norm": 1.4140348434448242,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4319,
+      "step": 40
+    },
+    {
+      "epoch": 1.2014652014652014,
+      "grad_norm": 1.2480062246322632,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4183,
+      "step": 41
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 1.2195627689361572,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4386,
+      "step": 42
+    },
+    {
+      "epoch": 1.26007326007326,
+      "grad_norm": 1.6348038911819458,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5866,
+      "step": 43
+    },
+    {
+      "epoch": 1.2893772893772895,
+      "grad_norm": 1.241610050201416,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3238,
+      "step": 44
+    },
+    {
+      "epoch": 1.3186813186813187,
+      "grad_norm": 1.3212645053863525,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.3719,
+      "step": 45
+    },
+    {
+      "epoch": 1.347985347985348,
+      "grad_norm": 1.4683098793029785,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.3706,
+      "step": 46
+    },
+    {
+      "epoch": 1.3772893772893773,
+      "grad_norm": 1.5584352016448975,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4469,
+      "step": 47
+    },
+    {
+      "epoch": 1.4065934065934065,
+      "grad_norm": 1.3631318807601929,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4557,
+      "step": 48
+    },
+    {
+      "epoch": 1.435897435897436,
+      "grad_norm": 1.372761845588684,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4394,
+      "step": 49
+    },
+    {
+      "epoch": 1.4652014652014653,
+      "grad_norm": 1.3545066118240356,
+      "learning_rate": 0.0,
+      "loss": 0.3641,
+      "step": 50
+    },
+    {
+      "epoch": 1.4652014652014653,
+      "eval_loss": 0.44779691100120544,
+      "eval_runtime": 1.7354,
+      "eval_samples_per_second": 132.533,
+      "eval_steps_per_second": 16.711,
+      "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": 1.4820414672863232e+16,
+  "total_flos": 2.9677741905281024e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null