Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e685fd1abb704fd8eb507969ea2153bff1fcfa7bbe9bcdf93d28d38459be664
+oid sha256:dd3cc23ee16bbfd90651b0e0e9cc0fa6fb9fd7b8c4ba35d385cf9fab5abf6fc9
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a4eab81d047a3362d818efeee583280fcdaa5cbd523e3fd2a20330d5b1d6c85
+oid sha256:0ad56e5bbba1a8b0932f651e54941bbdb236bfcd613bd52f2da592e625fb02d4
 size 259694

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f55e6006041fb4816af533e474a688c49bc1c65f15a7f9b7902b1f08a9b8b014
+oid sha256:4d1bbcd82655c3c3cb37fabf82f54f6369105b3e8c895953128cf0852673409c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9a3ed7d778acfab8bda34c4c7353473bf0b409392f8abc233c4db141ac995bb
+oid sha256:80386af8aeec5e0a65b01d2e0b53f6cfa4a2b786821784872c115a03a5698886
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2305435af1859714a81f5450e6aa7c40f5951fd8d0bc2c52215d09c69ead730a
+oid sha256:772eab293367a4299972f9e1518fe97bb926ccd1200a084db9b69570bb1ca9cd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa83f619b8ea1db6c0c6663b3afa7bf063f705dbb4ff263734f70d0445fb0577
+oid sha256:45d7099f6af0a0ee7127638a22ea69f5dbb58bebbd15cb372ce346a6d3f5dcb5
 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": 10.940447807312012,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6359300476947536,
+  "best_metric": 10.90896224975586,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2734499205087442,
   "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": 342.688,
       "eval_steps_per_second": 43.968,
       "step": 25
+    },
+    {
+      "epoch": 0.6613672496025437,
+      "grad_norm": 13.278068542480469,
+      "learning_rate": 5e-05,
+      "loss": 175.0375,
+      "step": 26
+    },
+    {
+      "epoch": 0.6868044515103339,
+      "grad_norm": 12.864252090454102,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 174.925,
+      "step": 27
+    },
+    {
+      "epoch": 0.712241653418124,
+      "grad_norm": 13.144230842590332,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 174.7344,
+      "step": 28
+    },
+    {
+      "epoch": 0.7376788553259142,
+      "grad_norm": 13.34295654296875,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 174.6859,
+      "step": 29
+    },
+    {
+      "epoch": 0.7631160572337043,
+      "grad_norm": 12.916960716247559,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 174.8438,
+      "step": 30
+    },
+    {
+      "epoch": 0.7885532591414944,
+      "grad_norm": 13.577077865600586,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 174.6344,
+      "step": 31
+    },
+    {
+      "epoch": 0.8139904610492846,
+      "grad_norm": 12.431527137756348,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 174.5969,
+      "step": 32
+    },
+    {
+      "epoch": 0.8394276629570747,
+      "grad_norm": 12.354952812194824,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 174.7516,
+      "step": 33
+    },
+    {
+      "epoch": 0.8648648648648649,
+      "grad_norm": 12.568489074707031,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 174.8016,
+      "step": 34
+    },
+    {
+      "epoch": 0.890302066772655,
+      "grad_norm": 12.316400527954102,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 174.7937,
+      "step": 35
+    },
+    {
+      "epoch": 0.9157392686804452,
+      "grad_norm": 13.003135681152344,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 174.4141,
+      "step": 36
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 13.115909576416016,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 174.275,
+      "step": 37
+    },
+    {
+      "epoch": 0.9666136724960255,
+      "grad_norm": 12.456389427185059,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 174.6125,
+      "step": 38
+    },
+    {
+      "epoch": 0.9920508744038156,
+      "grad_norm": 12.58653736114502,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 174.5969,
+      "step": 39
+    },
+    {
+      "epoch": 1.0190779014308426,
+      "grad_norm": 12.444266319274902,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 174.6016,
+      "step": 40
+    },
+    {
+      "epoch": 1.0445151033386328,
+      "grad_norm": 12.287275314331055,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 174.7563,
+      "step": 41
+    },
+    {
+      "epoch": 1.0699523052464228,
+      "grad_norm": 12.920654296875,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 174.4234,
+      "step": 42
+    },
+    {
+      "epoch": 1.095389507154213,
+      "grad_norm": 12.601585388183594,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 174.4937,
+      "step": 43
+    },
+    {
+      "epoch": 1.1208267090620032,
+      "grad_norm": 12.357393264770508,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 174.6625,
+      "step": 44
+    },
+    {
+      "epoch": 1.1462639109697934,
+      "grad_norm": 12.532998085021973,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 174.5516,
+      "step": 45
+    },
+    {
+      "epoch": 1.1717011128775834,
+      "grad_norm": 12.560898780822754,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 174.425,
+      "step": 46
+    },
+    {
+      "epoch": 1.1971383147853736,
+      "grad_norm": 12.610762596130371,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 174.3813,
+      "step": 47
+    },
+    {
+      "epoch": 1.2225755166931638,
+      "grad_norm": 12.676226615905762,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 174.6047,
+      "step": 48
+    },
+    {
+      "epoch": 1.248012718600954,
+      "grad_norm": 13.310853958129883,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 174.2234,
+      "step": 49
+    },
+    {
+      "epoch": 1.2734499205087442,
+      "grad_norm": 12.485175132751465,
+      "learning_rate": 0.0,
+      "loss": 174.6688,
+      "step": 50
+    },
+    {
+      "epoch": 1.2734499205087442,
+      "eval_loss": 10.90896224975586,
+      "eval_runtime": 0.7939,
+      "eval_samples_per_second": 333.783,
+      "eval_steps_per_second": 42.825,
+      "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": 2101346304000.0,
+  "total_flos": 4202692608000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null