Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:949c09f5188b509237e1877c0cba4f025fbcac2e9a70071ee2f773a7df7faa6f
+oid sha256:a01505cc3d5ce15a9318998843c27e8357aceed52393fcf206a8899bc9b47abb
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7ef981b82a4ea3666eb19a6e6806d9ce2e88f2aa6f042ad4046ac40a010972b
+oid sha256:24884ed1366ba955b4c676d32e0a59d8e0982b8fce77bea346de4979acccce2e
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e78d514889da57390aef8d46386bba19c5ceea1c6d9dfb203af675ecb2818c
+oid sha256:76e2ee9f61df1e22ddd68cbe8c8c9b5843bbf8e80228aac06c1f7bd5662300ed
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc4db2cba29c9d02b14f131f3458cf8a98f6b85856c4556b52403bf9c45fbc07
+oid sha256:8c69358b98666ee4dbb45643a1e835927e239a7584fb2be0d99b0b0011024d20
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f6271c3bc66c6025f7112e222cb09949729db1029e4a3eb334211fd70f6736a
+oid sha256:11116c062c92b847a4cd4662b26591f061aebc3978167ab1558b3c96938fb3d3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93ff1fae3e3d3cb4f4c8a32f98913f6936b1bc4b1424c120d1f7c63313662a9d
+oid sha256:1fc8edd827d5bd89341db14fd538084c40576ef1427e73891092cf13fb3b421e
 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": 1.4483610391616821,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.625,
+  "best_metric": 1.3389908075332642,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.25,
   "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": 19.226,
       "eval_steps_per_second": 2.421,
       "step": 25
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 7.969269275665283,
+      "learning_rate": 5e-05,
+      "loss": 1.8311,
+      "step": 26
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 1.6885390281677246,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.4602,
+      "step": 27
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.9986926913261414,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3842,
+      "step": 28
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 1.213174819946289,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.1437,
+      "step": 29
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.6171689629554749,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1844,
+      "step": 30
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.6505604982376099,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2404,
+      "step": 31
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.6912071704864502,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.4684,
+      "step": 32
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.49850189685821533,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1891,
+      "step": 33
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.5205236077308655,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2419,
+      "step": 34
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 1.081421136856079,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8376,
+      "step": 35
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.883995532989502,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.5465,
+      "step": 36
+    },
+    {
+      "epoch": 0.925,
+      "grad_norm": 0.7116379141807556,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.382,
+      "step": 37
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.7163117527961731,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2866,
+      "step": 38
+    },
+    {
+      "epoch": 0.975,
+      "grad_norm": 0.9886005520820618,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.1005,
+      "step": 39
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.4299323260784149,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.3191,
+      "step": 40
+    },
+    {
+      "epoch": 1.025,
+      "grad_norm": 0.6381961703300476,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2092,
+      "step": 41
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.5745808482170105,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.2759,
+      "step": 42
+    },
+    {
+      "epoch": 1.075,
+      "grad_norm": 0.5236896872520447,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2957,
+      "step": 43
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.559079647064209,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.1753,
+      "step": 44
+    },
+    {
+      "epoch": 1.125,
+      "grad_norm": 0.6100291013717651,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.4734,
+      "step": 45
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.8117789030075073,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.6454,
+      "step": 46
+    },
+    {
+      "epoch": 1.175,
+      "grad_norm": 0.694729208946228,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.411,
+      "step": 47
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.6393530368804932,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.263,
+      "step": 48
+    },
+    {
+      "epoch": 1.225,
+      "grad_norm": 0.8060018420219421,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.2268,
+      "step": 49
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.4653865694999695,
+      "learning_rate": 0.0,
+      "loss": 1.1996,
+      "step": 50
+    },
+    {
+      "epoch": 1.25,
+      "eval_loss": 1.3389908075332642,
+      "eval_runtime": 13.5873,
+      "eval_samples_per_second": 19.872,
+      "eval_steps_per_second": 2.502,
+      "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