Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd86f1e4fc94ab77988b8ce005aada1e9dfa144e08b9bfff2513f757dd3f9ed
+oid sha256:8aad3581afae582e654416cdf003a9e32ee7738950198523070cfa5645ec79b2
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78fad4819807d8f14f882e015885de4d0e7efbaec0819cdaa4fe4fbe938998e8
+oid sha256:ebf1a35bd3343e200844e0f13de3b6048f343550e0f89f80341e671aa8601470
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d87ae7f4e86269a327aa577a5da9f55c89219de13adb3ad0337b113f196cf65b
+oid sha256:3aad882531c3ac30efbd7e842ca19eeba897913705570fb32d76a9a4a8fec29c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e48dcfec9cc888294eb94ce7a43ac2a00dc8332e48c1031ef4a79b24721914
+oid sha256:1662496cd6ffaec72b4b8cef804faa1e67929afbe7b15711562fc3f949cb2a00
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e076405531e4766774de78a81a4bd25dfa35538cf05d7be6dad0f681917be016
+oid sha256:5ca4d575edd0326db6b3f538ee0ad65fcc25278e2a5c18bb0db7090e8c053883
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:025cfdde0aee96677fc133df5b7c430dff741c42bdc2d6410a2a115eb2c67fba
+oid sha256:ac46fff64956cb6d71a047476e3cf9662861b1cc8c2a4691c4a06c70501eb8b6
 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": 0.0325031504034996,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.41109969167523125,
+  "best_metric": 0.029691379517316818,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.8221993833504625,
   "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": 107.262,
       "eval_steps_per_second": 13.604,
       "step": 25
+    },
+    {
+      "epoch": 0.42754367934224047,
+      "grad_norm": 0.4967133402824402,
+      "learning_rate": 5e-05,
+      "loss": 0.0747,
+      "step": 26
+    },
+    {
+      "epoch": 0.44398766700924974,
+      "grad_norm": 0.6573581099510193,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.051,
+      "step": 27
+    },
+    {
+      "epoch": 0.460431654676259,
+      "grad_norm": 0.7091865539550781,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0283,
+      "step": 28
+    },
+    {
+      "epoch": 0.47687564234326824,
+      "grad_norm": 0.353059321641922,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0551,
+      "step": 29
+    },
+    {
+      "epoch": 0.4933196300102775,
+      "grad_norm": 0.40428224205970764,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0467,
+      "step": 30
+    },
+    {
+      "epoch": 0.5097636176772867,
+      "grad_norm": 0.38357752561569214,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0407,
+      "step": 31
+    },
+    {
+      "epoch": 0.526207605344296,
+      "grad_norm": 0.4076400697231293,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0214,
+      "step": 32
+    },
+    {
+      "epoch": 0.5426515930113053,
+      "grad_norm": 0.5312539935112,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0276,
+      "step": 33
+    },
+    {
+      "epoch": 0.5590955806783144,
+      "grad_norm": 0.24239972233772278,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0114,
+      "step": 34
+    },
+    {
+      "epoch": 0.5755395683453237,
+      "grad_norm": 0.21986766159534454,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0108,
+      "step": 35
+    },
+    {
+      "epoch": 0.591983556012333,
+      "grad_norm": 0.43781280517578125,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0552,
+      "step": 36
+    },
+    {
+      "epoch": 0.6084275436793423,
+      "grad_norm": 0.503707766532898,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.045,
+      "step": 37
+    },
+    {
+      "epoch": 0.6248715313463515,
+      "grad_norm": 0.5236077308654785,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.027,
+      "step": 38
+    },
+    {
+      "epoch": 0.6413155190133607,
+      "grad_norm": 0.5696163773536682,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0188,
+      "step": 39
+    },
+    {
+      "epoch": 0.65775950668037,
+      "grad_norm": 0.5354735851287842,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0348,
+      "step": 40
+    },
+    {
+      "epoch": 0.6742034943473793,
+      "grad_norm": 0.5729418396949768,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0507,
+      "step": 41
+    },
+    {
+      "epoch": 0.6906474820143885,
+      "grad_norm": 0.29594871401786804,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0176,
+      "step": 42
+    },
+    {
+      "epoch": 0.7070914696813977,
+      "grad_norm": 0.2777194678783417,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0149,
+      "step": 43
+    },
+    {
+      "epoch": 0.723535457348407,
+      "grad_norm": 0.5910176634788513,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0334,
+      "step": 44
+    },
+    {
+      "epoch": 0.7399794450154162,
+      "grad_norm": 0.47184309363365173,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0284,
+      "step": 45
+    },
+    {
+      "epoch": 0.7564234326824255,
+      "grad_norm": 0.36582136154174805,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0392,
+      "step": 46
+    },
+    {
+      "epoch": 0.7728674203494348,
+      "grad_norm": 0.3152853548526764,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0294,
+      "step": 47
+    },
+    {
+      "epoch": 0.789311408016444,
+      "grad_norm": 0.25798124074935913,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.017,
+      "step": 48
+    },
+    {
+      "epoch": 0.8057553956834532,
+      "grad_norm": 0.1165856271982193,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0048,
+      "step": 49
+    },
+    {
+      "epoch": 0.8221993833504625,
+      "grad_norm": 0.3071959614753723,
+      "learning_rate": 0.0,
+      "loss": 0.0306,
+      "step": 50
+    },
+    {
+      "epoch": 0.8221993833504625,
+      "eval_loss": 0.029691379517316818,
+      "eval_runtime": 3.8208,
+      "eval_samples_per_second": 107.309,
+      "eval_steps_per_second": 13.61,
+      "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": 4.169686388310016e+16,
+  "total_flos": 8.336768348717056e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null