Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dd9f0143e041e217d3de19dba3ec4df644013efe1d423c4564d68efae717795
+oid sha256:b58ba0d42417d683a5b58063179409e58f2b22db354cff7c7a94f1318df95752
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c4aca230a16e3bf838b742d32616d47042de9b426775ff90f6d499b9e788185
+oid sha256:325704323cfbd5cdb4227274a55bdb00fc735dbcab6a046bf2f6760cd19f5724
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:130503a66240a2d7cb3bcd0daaf2e4fa7b7d0529cf847ef4f9b181134323c53a
+oid sha256:037f8c14c9f8c104e8dbd049222d7fe9955ded701bfa9584c086e7d7a4e2cd44
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:635cd719d7e7123bf4f3eb3f32bce3971553c1871e1ad81c5c66e53c90774ba9
+oid sha256:ffab1a60657d484ee96b63d10408341e8559a386df71a2ed972a852b84b4e1d3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d48793fc9ed9ca0bbe20da2f5351c6aca4c3bfb5e775dd20db7ab1f872067aa0
+oid sha256:aa0737b3dbae9d0aa80d851d48be84e2a12c718f249931e763f1869d9c5277ff
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f9dc4050f1963b17e81ed7a9cab065449bd043651c886ec94527fcebf530d10
+oid sha256:2f85c6afad9d0459b4e6532f7b69d246b2b394c367bd5deecd8e63f06930db7a
 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": 1.3017019033432007,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05901445854234287,
+  "best_metric": 1.2696001529693604,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11802891708468574,
   "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": 14.989,
       "eval_steps_per_second": 1.875,
       "step": 25
+    },
+    {
+      "epoch": 0.06137503688403659,
+      "grad_norm": 0.6911665797233582,
+      "learning_rate": 5e-05,
+      "loss": 1.7851,
+      "step": 26
+    },
+    {
+      "epoch": 0.0637356152257303,
+      "grad_norm": 0.6142681241035461,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5944,
+      "step": 27
+    },
+    {
+      "epoch": 0.06609619356742402,
+      "grad_norm": 0.5505021810531616,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.4149,
+      "step": 28
+    },
+    {
+      "epoch": 0.06845677190911774,
+      "grad_norm": 0.4889450669288635,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4167,
+      "step": 29
+    },
+    {
+      "epoch": 0.07081735025081144,
+      "grad_norm": 0.41566815972328186,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.3479,
+      "step": 30
+    },
+    {
+      "epoch": 0.07317792859250516,
+      "grad_norm": 0.43414074182510376,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2498,
+      "step": 31
+    },
+    {
+      "epoch": 0.07553850693419888,
+      "grad_norm": 0.3600168824195862,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2066,
+      "step": 32
+    },
+    {
+      "epoch": 0.0778990852758926,
+      "grad_norm": 0.4459245204925537,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1753,
+      "step": 33
+    },
+    {
+      "epoch": 0.08025966361758631,
+      "grad_norm": 0.4490649998188019,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1367,
+      "step": 34
+    },
+    {
+      "epoch": 0.08262024195928003,
+      "grad_norm": 0.44567686319351196,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0871,
+      "step": 35
+    },
+    {
+      "epoch": 0.08498082030097374,
+      "grad_norm": 0.47326353192329407,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0577,
+      "step": 36
+    },
+    {
+      "epoch": 0.08734139864266745,
+      "grad_norm": 0.5644652247428894,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9545,
+      "step": 37
+    },
+    {
+      "epoch": 0.08970197698436116,
+      "grad_norm": 0.35153478384017944,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5445,
+      "step": 38
+    },
+    {
+      "epoch": 0.09206255532605488,
+      "grad_norm": 0.36541318893432617,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5593,
+      "step": 39
+    },
+    {
+      "epoch": 0.0944231336677486,
+      "grad_norm": 0.387804239988327,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.4624,
+      "step": 40
+    },
+    {
+      "epoch": 0.09678371200944232,
+      "grad_norm": 0.35317885875701904,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.4352,
+      "step": 41
+    },
+    {
+      "epoch": 0.09914429035113603,
+      "grad_norm": 0.33535659313201904,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3673,
+      "step": 42
+    },
+    {
+      "epoch": 0.10150486869282975,
+      "grad_norm": 0.31882593035697937,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.316,
+      "step": 43
+    },
+    {
+      "epoch": 0.10386544703452345,
+      "grad_norm": 0.32166722416877747,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2454,
+      "step": 44
+    },
+    {
+      "epoch": 0.10622602537621717,
+      "grad_norm": 0.36580532789230347,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1923,
+      "step": 45
+    },
+    {
+      "epoch": 0.10858660371791089,
+      "grad_norm": 0.369552880525589,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1445,
+      "step": 46
+    },
+    {
+      "epoch": 0.1109471820596046,
+      "grad_norm": 0.3656086325645447,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0958,
+      "step": 47
+    },
+    {
+      "epoch": 0.11330776040129832,
+      "grad_norm": 0.39978259801864624,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0955,
+      "step": 48
+    },
+    {
+      "epoch": 0.11566833874299204,
+      "grad_norm": 0.4766823947429657,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9948,
+      "step": 49
+    },
+    {
+      "epoch": 0.11802891708468574,
+      "grad_norm": 0.6909182667732239,
+      "learning_rate": 0.0,
+      "loss": 0.909,
+      "step": 50
+    },
+    {
+      "epoch": 0.11802891708468574,
+      "eval_loss": 1.2696001529693604,
+      "eval_runtime": 191.0143,
+      "eval_samples_per_second": 14.941,
+      "eval_steps_per_second": 1.869,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null