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:a9507d21f27a8c4a3aef398eb488079a9cefef75fdd141555be58a3a7aa1238d
+oid sha256:06380742f95ab95a536574b786a37af27393c8a92bc03130f7aab51df40bbf35
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cb4cc13243387b280c71105c3a2113ec6ec11abee59e544ef891a297ee6b860
+oid sha256:dc4567ed838e7c6bfa0000da0a7b72ddabcbc3870aaf4f248a3f55a140f3cff2
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0acd4a18361ac6fa952a0a51dcd189d313faea339180df23b08591d117d463fe
+oid sha256:a682a96e194c1933623a7c6b736034bbadc0cb0bfcbb5ab5bb90310c82e93757
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2815a761751709f236d2a9a6742ad8c0ad56b5002e1ae38a0eea6a2a39504b85
+oid sha256:50e871229fc9648a0760a14fda05520e336a35fd43fb5ec6fb45101dd8c0fe37
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4876a69df208714817aed65e66017f3a224c3c314d3478a9bffd962d8ba5984d
+oid sha256:82a0ef19a8e54646460ffa67d92504ce5903e467b11d517e4d63634946762154
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb9fc235ba5054a1f93388ab65b640ad04e79a668531b539061708cda5dcaf83
+oid sha256:42bad85c358d1f5ede0684bacb03bdaa47c12c34f751cf7ba57c298daf9b6348
 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": 10.368396759033203,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012248522521970787,
+  "best_metric": 10.3651704788208,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.024497045043941575,
   "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": 439.785,
       "eval_steps_per_second": 54.977,
       "step": 25
+    },
+    {
+      "epoch": 0.012738463422849618,
+      "grad_norm": 0.12131338566541672,
+      "learning_rate": 5e-05,
+      "loss": 10.3703,
+      "step": 26
+    },
+    {
+      "epoch": 0.01322840432372845,
+      "grad_norm": 0.10950379073619843,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 10.3681,
+      "step": 27
+    },
+    {
+      "epoch": 0.013718345224607282,
+      "grad_norm": 0.1175779178738594,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 10.3684,
+      "step": 28
+    },
+    {
+      "epoch": 0.014208286125486113,
+      "grad_norm": 0.11989858746528625,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 10.3675,
+      "step": 29
+    },
+    {
+      "epoch": 0.014698227026364944,
+      "grad_norm": 0.11529122292995453,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 10.3677,
+      "step": 30
+    },
+    {
+      "epoch": 0.015188167927243775,
+      "grad_norm": 0.1135224774479866,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 10.3665,
+      "step": 31
+    },
+    {
+      "epoch": 0.01567810882812261,
+      "grad_norm": 0.1238592267036438,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 10.365,
+      "step": 32
+    },
+    {
+      "epoch": 0.01616804972900144,
+      "grad_norm": 0.13364364206790924,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 10.3664,
+      "step": 33
+    },
+    {
+      "epoch": 0.01665799062988027,
+      "grad_norm": 0.13014760613441467,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 10.3635,
+      "step": 34
+    },
+    {
+      "epoch": 0.0171479315307591,
+      "grad_norm": 0.13167224824428558,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 10.3663,
+      "step": 35
+    },
+    {
+      "epoch": 0.017637872431637933,
+      "grad_norm": 0.14532671868801117,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 10.3636,
+      "step": 36
+    },
+    {
+      "epoch": 0.018127813332516764,
+      "grad_norm": 0.14160360395908356,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 10.3645,
+      "step": 37
+    },
+    {
+      "epoch": 0.018617754233395598,
+      "grad_norm": 0.1375637799501419,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.3681,
+      "step": 38
+    },
+    {
+      "epoch": 0.01910769513427443,
+      "grad_norm": 0.12385618686676025,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 10.3669,
+      "step": 39
+    },
+    {
+      "epoch": 0.01959763603515326,
+      "grad_norm": 0.13332408666610718,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 10.3649,
+      "step": 40
+    },
+    {
+      "epoch": 0.02008757693603209,
+      "grad_norm": 0.13181282579898834,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 10.3666,
+      "step": 41
+    },
+    {
+      "epoch": 0.020577517836910923,
+      "grad_norm": 0.13302215933799744,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 10.3654,
+      "step": 42
+    },
+    {
+      "epoch": 0.021067458737789754,
+      "grad_norm": 0.1286499947309494,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 10.3634,
+      "step": 43
+    },
+    {
+      "epoch": 0.021557399638668585,
+      "grad_norm": 0.14264312386512756,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.3635,
+      "step": 44
+    },
+    {
+      "epoch": 0.022047340539547416,
+      "grad_norm": 0.14282181859016418,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 10.3655,
+      "step": 45
+    },
+    {
+      "epoch": 0.02253728144042625,
+      "grad_norm": 0.1369328647851944,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 10.3652,
+      "step": 46
+    },
+    {
+      "epoch": 0.02302722234130508,
+      "grad_norm": 0.1347339153289795,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 10.3637,
+      "step": 47
+    },
+    {
+      "epoch": 0.023517163242183912,
+      "grad_norm": 0.13543902337551117,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 10.3645,
+      "step": 48
+    },
+    {
+      "epoch": 0.024007104143062744,
+      "grad_norm": 0.15400274097919464,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 10.3637,
+      "step": 49
+    },
+    {
+      "epoch": 0.024497045043941575,
+      "grad_norm": 0.16417399048805237,
+      "learning_rate": 0.0,
+      "loss": 10.3647,
+      "step": 50
+    },
+    {
+      "epoch": 0.024497045043941575,
+      "eval_loss": 10.3651704788208,
+      "eval_runtime": 30.4468,
+      "eval_samples_per_second": 451.64,
+      "eval_steps_per_second": 56.459,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null