Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f64d5e4f9ca107b54b373da85d43604e6a88b67b0835d8b608532f1f0fdc580
+oid sha256:780df823635a4eef7733d4139cd5b64a0e4dd9760826a1b0b8f0a0bbb98fdac2
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19dcf50f4a002aaa61e148978fa364d966893aafd36feeedda47cc4f30ea7297
+oid sha256:5737cc6195a7dadd0be1148f8be08410416c3793dc7cbaead6b95fbcbc4d3f67
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5635024ad3fd5605ff66cbc2b710a32f42768040fdf2904e2e4d53f61116ef0
+oid sha256:2a8bfd5ebfe20d42cbdceaa3a74a2b2d234a1aad9ef18ffb9f3904afa7f5b79f
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be341029818f6de9a246e99376f151952ef574e5d6288db5a2e81204d51649de
+oid sha256:db45180d36355f4148ae43cbe7713d9c0c43cf3bdf1707b8e6457abfd573a55e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d4f99418c23b6e6ba60b9fa7ac40e24c4c0eac50fb623ddb636f983a8882dc2
+oid sha256:eb065b89c1772cbbbe10d2fb92a1d279633642bfdd31f69b94eb917c53aec646
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5ad4174958854b38f1ea45caf998c7a8deb59f8719595d5a7ec1308613a31da
+oid sha256:d1dfc8a3cbe907f4381d17b2a69933991bf9310d9fcb915fc0935d6ef3b03d6d
 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": 2.1019418239593506,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0756000756000756,
+  "best_metric": 2.0980021953582764,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1512001512001512,
   "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": 20.908,
       "eval_steps_per_second": 2.618,
       "step": 25
+    },
+    {
+      "epoch": 0.07862407862407862,
+      "grad_norm": 0.05332132428884506,
+      "learning_rate": 5e-05,
+      "loss": 2.0911,
+      "step": 26
+    },
+    {
+      "epoch": 0.08164808164808164,
+      "grad_norm": 0.05668758228421211,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 2.0646,
+      "step": 27
+    },
+    {
+      "epoch": 0.08467208467208467,
+      "grad_norm": 0.05856581777334213,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 2.0811,
+      "step": 28
+    },
+    {
+      "epoch": 0.0876960876960877,
+      "grad_norm": 0.06092054769396782,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 2.1128,
+      "step": 29
+    },
+    {
+      "epoch": 0.09072009072009073,
+      "grad_norm": 0.061290230602025986,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 2.0705,
+      "step": 30
+    },
+    {
+      "epoch": 0.09374409374409375,
+      "grad_norm": 0.05879451707005501,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.1229,
+      "step": 31
+    },
+    {
+      "epoch": 0.09676809676809676,
+      "grad_norm": 0.05842060595750809,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.148,
+      "step": 32
+    },
+    {
+      "epoch": 0.0997920997920998,
+      "grad_norm": 0.05611104518175125,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.1368,
+      "step": 33
+    },
+    {
+      "epoch": 0.10281610281610282,
+      "grad_norm": 0.05795889347791672,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.2185,
+      "step": 34
+    },
+    {
+      "epoch": 0.10584010584010584,
+      "grad_norm": 0.06058291345834732,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.071,
+      "step": 35
+    },
+    {
+      "epoch": 0.10886410886410887,
+      "grad_norm": 0.07205378264188766,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.0645,
+      "step": 36
+    },
+    {
+      "epoch": 0.11188811188811189,
+      "grad_norm": 0.07796823978424072,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.0426,
+      "step": 37
+    },
+    {
+      "epoch": 0.11491211491211491,
+      "grad_norm": 0.0645485669374466,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.066,
+      "step": 38
+    },
+    {
+      "epoch": 0.11793611793611794,
+      "grad_norm": 0.05329917371273041,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.1214,
+      "step": 39
+    },
+    {
+      "epoch": 0.12096012096012096,
+      "grad_norm": 0.05362192541360855,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0971,
+      "step": 40
+    },
+    {
+      "epoch": 0.12398412398412398,
+      "grad_norm": 0.05432514101266861,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 2.0811,
+      "step": 41
+    },
+    {
+      "epoch": 0.127008127008127,
+      "grad_norm": 0.05242035165429115,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.1001,
+      "step": 42
+    },
+    {
+      "epoch": 0.13003213003213004,
+      "grad_norm": 0.05346823111176491,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.0913,
+      "step": 43
+    },
+    {
+      "epoch": 0.13305613305613306,
+      "grad_norm": 0.05273548886179924,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0959,
+      "step": 44
+    },
+    {
+      "epoch": 0.13608013608013608,
+      "grad_norm": 0.05268967151641846,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.0965,
+      "step": 45
+    },
+    {
+      "epoch": 0.1391041391041391,
+      "grad_norm": 0.054601460695266724,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.1074,
+      "step": 46
+    },
+    {
+      "epoch": 0.14212814212814212,
+      "grad_norm": 0.05563381314277649,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.2237,
+      "step": 47
+    },
+    {
+      "epoch": 0.14515214515214514,
+      "grad_norm": 0.06596875190734863,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.1502,
+      "step": 48
+    },
+    {
+      "epoch": 0.1481761481761482,
+      "grad_norm": 0.07697181403636932,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.0869,
+      "step": 49
+    },
+    {
+      "epoch": 0.1512001512001512,
+      "grad_norm": 0.10499610006809235,
+      "learning_rate": 0.0,
+      "loss": 2.0315,
+      "step": 50
+    },
+    {
+      "epoch": 0.1512001512001512,
+      "eval_loss": 2.0980021953582764,
+      "eval_runtime": 106.6124,
+      "eval_samples_per_second": 20.898,
+      "eval_steps_per_second": 2.617,
+      "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": 9.0954574235435e+16,
+  "total_flos": 1.821740327942226e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null