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:eab3dd3d0d49c48b5143631060d479cca403b0354293d788157d238003bd88f3
+oid sha256:dfb446b314177422e6b273f0dc6ef48a35a91a96bfc1c2dc1e9c435432eded07
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d672cc0945a1901fe39aaa003d8c40d739b94c5ec96697dbf811c4c372f4b80
+oid sha256:a9cd80e8200c2a8651ca79b1ab7102f98b868a146a17c5143e5aa66909f4b74f
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ce5e81c1a8d1089a37f548b1536bfa212991040f28d75a5fad2d4eb55c28a1e
+oid sha256:12c0d8d348ae3d7e79ed9409a4b517164f0bc67cbc031c1f8b28a7ed115d84fe
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7152150b60a0d298e3aee8226acdd044cb2743ca75b3e9abd93d3f144ac98606
+oid sha256:da521312d9d055cc4aee8f0a5c6b7372776c37f7b484dc217221b1e8d9138a73
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:136f72441c8588b721dbb95744ac33c7bb3d3613b27f826dcf963bde86f3c9f1
+oid sha256:d1dc83b09ba1513fd65e0a1edacd3de7427a574fe0901a1e8d08c91b0efff5e2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6bcf069c8d6b6322350230afa4b5d7685f414cf5ef3b4314ce108187fd74ed1
+oid sha256:75e2f5a76efa626e2a5ea714ac2192b27d85b5672efff83f16f6d6ece8bb8b9b
 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": 0.7558804750442505,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0167897918065816,
+  "best_metric": 0.7356575727462769,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0335795836131632,
   "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": 35.281,
       "eval_steps_per_second": 4.41,
       "step": 25
+    },
+    {
+      "epoch": 0.017461383478844864,
+      "grad_norm": 0.3415839970111847,
+      "learning_rate": 5e-05,
+      "loss": 1.3886,
+      "step": 26
+    },
+    {
+      "epoch": 0.018132975151108125,
+      "grad_norm": 0.36007195711135864,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.3492,
+      "step": 27
+    },
+    {
+      "epoch": 0.01880456682337139,
+      "grad_norm": 0.3535638451576233,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.2543,
+      "step": 28
+    },
+    {
+      "epoch": 0.019476158495634655,
+      "grad_norm": 0.3168131709098816,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.3221,
+      "step": 29
+    },
+    {
+      "epoch": 0.020147750167897917,
+      "grad_norm": 0.2952622175216675,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2661,
+      "step": 30
+    },
+    {
+      "epoch": 0.020819341840161182,
+      "grad_norm": 0.27426886558532715,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1886,
+      "step": 31
+    },
+    {
+      "epoch": 0.021490933512424447,
+      "grad_norm": 0.30082210898399353,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2767,
+      "step": 32
+    },
+    {
+      "epoch": 0.02216252518468771,
+      "grad_norm": 0.304557204246521,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4439,
+      "step": 33
+    },
+    {
+      "epoch": 0.022834116856950974,
+      "grad_norm": 0.20018385350704193,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1384,
+      "step": 34
+    },
+    {
+      "epoch": 0.02350570852921424,
+      "grad_norm": 0.1809197962284088,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1245,
+      "step": 35
+    },
+    {
+      "epoch": 0.0241773002014775,
+      "grad_norm": 0.14720425009727478,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.113,
+      "step": 36
+    },
+    {
+      "epoch": 0.024848891873740765,
+      "grad_norm": 0.21793410181999207,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1166,
+      "step": 37
+    },
+    {
+      "epoch": 0.02552048354600403,
+      "grad_norm": 0.29882678389549255,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1536,
+      "step": 38
+    },
+    {
+      "epoch": 0.026192075218267292,
+      "grad_norm": 0.26655298471450806,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.292,
+      "step": 39
+    },
+    {
+      "epoch": 0.026863666890530557,
+      "grad_norm": 0.2551353871822357,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.289,
+      "step": 40
+    },
+    {
+      "epoch": 0.027535258562793822,
+      "grad_norm": 0.28045758605003357,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2735,
+      "step": 41
+    },
+    {
+      "epoch": 0.028206850235057087,
+      "grad_norm": 0.26998549699783325,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.2411,
+      "step": 42
+    },
+    {
+      "epoch": 0.02887844190732035,
+      "grad_norm": 0.27158471941947937,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2325,
+      "step": 43
+    },
+    {
+      "epoch": 0.029550033579583614,
+      "grad_norm": 0.26602280139923096,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2189,
+      "step": 44
+    },
+    {
+      "epoch": 0.03022162525184688,
+      "grad_norm": 0.3358999192714691,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8734,
+      "step": 45
+    },
+    {
+      "epoch": 0.03089321692411014,
+      "grad_norm": 0.18822167813777924,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1388,
+      "step": 46
+    },
+    {
+      "epoch": 0.0315648085963734,
+      "grad_norm": 0.1590106040239334,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.1096,
+      "step": 47
+    },
+    {
+      "epoch": 0.03223640026863667,
+      "grad_norm": 0.12474197149276733,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1196,
+      "step": 48
+    },
+    {
+      "epoch": 0.03290799194089993,
+      "grad_norm": 0.16445966064929962,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1025,
+      "step": 49
+    },
+    {
+      "epoch": 0.0335795836131632,
+      "grad_norm": 0.26562613248825073,
+      "learning_rate": 0.0,
+      "loss": 0.0996,
+      "step": 50
+    },
+    {
+      "epoch": 0.0335795836131632,
+      "eval_loss": 0.7356575727462769,
+      "eval_runtime": 284.4429,
+      "eval_samples_per_second": 35.269,
+      "eval_steps_per_second": 4.409,
+      "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": 2.629552387915776e+17,
+  "total_flos": 5.259104775831552e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null