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:b61ee1612c9b6f6efa4654d8e3d6e9a4e97dcc59e99b21e71666a0fd8fafd987
+oid sha256:587cda74d1970751ac641e2e6b66c9c352ccb18b0e78d84c3e65b8bc6fc5d578
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff8c35df084fabb8fefa8e653efb33ce01c5d3ba2dadd426580080aa9836c297
+oid sha256:3adac95d9f1582068abc88dfc59f4d7ce8ae620f059e8b6db60b194d790ff53e
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ce144d7ca0c0c78992bc440c767b103f8c72432f7ed987aead370bee57c514b
+oid sha256:03ae47e7a6e8583cd4f3f0abad1435d87b6ec3501fb706d2deaaa6a563e20abd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb4f6fe846a233db45a7b9d6c7fe98ffb925a99e6894390b8fb6efafed6f261a
+oid sha256:2ee46149ce84ee98fa066bc36a738fa97ff949ea6577e25a88236299ed723432
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1f7c22c92b48635045ebed7e5cf387664036a6c7b93b6d3aa7028edf6eee1e2
+oid sha256:058dd72305e43fd2ba0af6dd98cae7b04b35a5db2258430fc16935de066297d5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10d8287770ba48e04afad289be500ca189a71a4cab25e01e5ac58e1a76d93d8c
+oid sha256:844d225e2fa71685fd969694a9ea94574a16c43d924aac32434715ae8c53d118
 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": 0.2315373420715332,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3401360544217687,
+  "best_metric": 0.22627143561840057,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6802721088435374,
   "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": 39.575,
       "eval_steps_per_second": 4.957,
       "step": 25
+    },
+    {
+      "epoch": 0.35374149659863946,
+      "grad_norm": 10.045724868774414,
+      "learning_rate": 5e-05,
+      "loss": 0.0646,
+      "step": 26
+    },
+    {
+      "epoch": 0.3673469387755102,
+      "grad_norm": 17.253311157226562,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.1257,
+      "step": 27
+    },
+    {
+      "epoch": 0.38095238095238093,
+      "grad_norm": 16.977933883666992,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1158,
+      "step": 28
+    },
+    {
+      "epoch": 0.3945578231292517,
+      "grad_norm": 8.944509506225586,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0538,
+      "step": 29
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 3.2423906326293945,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0169,
+      "step": 30
+    },
+    {
+      "epoch": 0.4217687074829932,
+      "grad_norm": 47.8316535949707,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5456,
+      "step": 31
+    },
+    {
+      "epoch": 0.43537414965986393,
+      "grad_norm": 66.37613677978516,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5475,
+      "step": 32
+    },
+    {
+      "epoch": 0.4489795918367347,
+      "grad_norm": 39.44430923461914,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.5115,
+      "step": 33
+    },
+    {
+      "epoch": 0.46258503401360546,
+      "grad_norm": 17.030851364135742,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.3512,
+      "step": 34
+    },
+    {
+      "epoch": 0.47619047619047616,
+      "grad_norm": 14.662363052368164,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.3138,
+      "step": 35
+    },
+    {
+      "epoch": 0.4897959183673469,
+      "grad_norm": 14.485307693481445,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.2473,
+      "step": 36
+    },
+    {
+      "epoch": 0.5034013605442177,
+      "grad_norm": 12.0574312210083,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2097,
+      "step": 37
+    },
+    {
+      "epoch": 0.5170068027210885,
+      "grad_norm": 1.3240798711776733,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0633,
+      "step": 38
+    },
+    {
+      "epoch": 0.5306122448979592,
+      "grad_norm": 0.8655800819396973,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.003,
+      "step": 39
+    },
+    {
+      "epoch": 0.54421768707483,
+      "grad_norm": 0.7527680993080139,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0025,
+      "step": 40
+    },
+    {
+      "epoch": 0.5578231292517006,
+      "grad_norm": 0.4660660922527313,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0016,
+      "step": 41
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.297651469707489,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0011,
+      "step": 42
+    },
+    {
+      "epoch": 0.5850340136054422,
+      "grad_norm": 6.011413097381592,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0826,
+      "step": 43
+    },
+    {
+      "epoch": 0.5986394557823129,
+      "grad_norm": 18.873197555541992,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2667,
+      "step": 44
+    },
+    {
+      "epoch": 0.6122448979591837,
+      "grad_norm": 16.203052520751953,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2395,
+      "step": 45
+    },
+    {
+      "epoch": 0.6258503401360545,
+      "grad_norm": 17.224546432495117,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2585,
+      "step": 46
+    },
+    {
+      "epoch": 0.6394557823129252,
+      "grad_norm": 16.941646575927734,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.2371,
+      "step": 47
+    },
+    {
+      "epoch": 0.6530612244897959,
+      "grad_norm": 12.933724403381348,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1872,
+      "step": 48
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 18.311908721923828,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2395,
+      "step": 49
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "grad_norm": 14.999979019165039,
+      "learning_rate": 0.0,
+      "loss": 0.2348,
+      "step": 50
+    },
+    {
+      "epoch": 0.6802721088435374,
+      "eval_loss": 0.22627143561840057,
+      "eval_runtime": 12.4896,
+      "eval_samples_per_second": 39.633,
+      "eval_steps_per_second": 4.964,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null