Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c982d63b6868db4f8cfafe528fb4f65c0495f0a3735ebad56df296783660f15
+oid sha256:d2fffcb75cb74601a4931184d5da428b7d2025c4c2a01d8b81a5bf737ca4d491
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71e15aebc09cd709bd52259025b21bc15a1d8530d8f38c7ea5bfc27ef2c4e189
+oid sha256:12c2b3fbf10fc42b1d9c79db81926dcfba941465058ea9b4ff96a00fd266ead8
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fad82aa37d9e62addd90862d4d667fbc637c5b842063c2e4a6bed60b5848e78a
+oid sha256:a1a71924d0a3b5575b44a5460f386f17085a1257d34a591e528c02db34871393
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d9f3c874999915a4867cc028f46a02d8ffd3700ea7b7425fd9275fecb7e4e8d
+oid sha256:761db5f842bc9a70662b5afea60259cc6c35494694fc65df3b9f306eea481048
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa5073e2b4e0ffced78da8b6ae604d083de9edbb6f2bcf1b93b4a3bb1531d51c
+oid sha256:94786fba638039a9104ffc0b41bc76af6a0d9b1e5ad7ef966a347460906f6d4a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af8f72489536ccc97ba3873783313d302d10245c13f322636919cf33ade887b1
+oid sha256:eb4ede145cacb3468faa557a44ad0eb4d93a041bb1b9552b91a434849e413777
 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": 1.8972411155700684,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.08543357539513029,
+  "best_metric": 1.8900460004806519,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.17086715079026057,
   "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": 18.129,
       "eval_steps_per_second": 2.271,
       "step": 25
+    },
+    {
+      "epoch": 0.0888509184109355,
+      "grad_norm": 0.10595165938138962,
+      "learning_rate": 5e-05,
+      "loss": 1.8922,
+      "step": 26
+    },
+    {
+      "epoch": 0.0922682614267407,
+      "grad_norm": 0.11757422983646393,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.8751,
+      "step": 27
+    },
+    {
+      "epoch": 0.09568560444254592,
+      "grad_norm": 0.1445239782333374,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.9001,
+      "step": 28
+    },
+    {
+      "epoch": 0.09910294745835113,
+      "grad_norm": 0.13264216482639313,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.908,
+      "step": 29
+    },
+    {
+      "epoch": 0.10252029047415634,
+      "grad_norm": 0.12971806526184082,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.9422,
+      "step": 30
+    },
+    {
+      "epoch": 0.10593763348996156,
+      "grad_norm": 0.12412116676568985,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.9381,
+      "step": 31
+    },
+    {
+      "epoch": 0.10935497650576677,
+      "grad_norm": 0.13017012178897858,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.8708,
+      "step": 32
+    },
+    {
+      "epoch": 0.11277231952157198,
+      "grad_norm": 0.12155024707317352,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.9103,
+      "step": 33
+    },
+    {
+      "epoch": 0.11618966253737718,
+      "grad_norm": 0.12652578949928284,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.9216,
+      "step": 34
+    },
+    {
+      "epoch": 0.1196070055531824,
+      "grad_norm": 0.13414131104946136,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8772,
+      "step": 35
+    },
+    {
+      "epoch": 0.12302434856898761,
+      "grad_norm": 0.16717028617858887,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.8883,
+      "step": 36
+    },
+    {
+      "epoch": 0.12644169158479282,
+      "grad_norm": 0.19632896780967712,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.877,
+      "step": 37
+    },
+    {
+      "epoch": 0.12985903460059803,
+      "grad_norm": 0.09393993020057678,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.7997,
+      "step": 38
+    },
+    {
+      "epoch": 0.13327637761640324,
+      "grad_norm": 0.0870269238948822,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.8741,
+      "step": 39
+    },
+    {
+      "epoch": 0.13669372063220847,
+      "grad_norm": 0.09241853654384613,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.8601,
+      "step": 40
+    },
+    {
+      "epoch": 0.14011106364801368,
+      "grad_norm": 0.09979937970638275,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.891,
+      "step": 41
+    },
+    {
+      "epoch": 0.14352840666381889,
+      "grad_norm": 0.10324066132307053,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.9562,
+      "step": 42
+    },
+    {
+      "epoch": 0.1469457496796241,
+      "grad_norm": 0.10628210008144379,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.9238,
+      "step": 43
+    },
+    {
+      "epoch": 0.1503630926954293,
+      "grad_norm": 0.1087057814002037,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8855,
+      "step": 44
+    },
+    {
+      "epoch": 0.1537804357112345,
+      "grad_norm": 0.11976548284292221,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.8984,
+      "step": 45
+    },
+    {
+      "epoch": 0.15719777872703972,
+      "grad_norm": 0.13553528487682343,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.9285,
+      "step": 46
+    },
+    {
+      "epoch": 0.16061512174284495,
+      "grad_norm": 0.13018624484539032,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.9068,
+      "step": 47
+    },
+    {
+      "epoch": 0.16403246475865016,
+      "grad_norm": 0.14239846169948578,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.9332,
+      "step": 48
+    },
+    {
+      "epoch": 0.16744980777445537,
+      "grad_norm": 0.1821918785572052,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.923,
+      "step": 49
+    },
+    {
+      "epoch": 0.17086715079026057,
+      "grad_norm": 0.28308120369911194,
+      "learning_rate": 0.0,
+      "loss": 1.8405,
+      "step": 50
+    },
+    {
+      "epoch": 0.17086715079026057,
+      "eval_loss": 1.8900460004806519,
+      "eval_runtime": 106.1673,
+      "eval_samples_per_second": 18.574,
+      "eval_steps_per_second": 2.327,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null