Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7125b65ef48a113b0dda86fcc714c295eaab11560106b539d1fb99c96c5a9b16
+oid sha256:e9210b70ab3c5e821ee3690c3964b87382ad85c08a84d302b09ce0445d07c135
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80c8613365f94704952972dc55e822e3f2f3e5f3b2f3434d661faed806006469
+oid sha256:175c2a7047ff5f4a3912b6ca6dd33546600c4d786ef0c203f7866934594e86e0
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f1d58240da413c0f02475505dcde188316027f9522cc7a66e82e7e040311fdb
+oid sha256:fbffa8b4034c334ef590bf262740ba8a38c85eae9b4d696609d078cdd27590e8
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f5b5a6ab011881aac264a9470f5e6ae69fd5308c5b423aeaab06fa2a804aa22
+oid sha256:6d84e5e88b02564e6fcff92b327f6a428b1d2521a725af9917885be98cb16f6a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca7a0a1d1339c03f15f61126da7162170c8151469addffb88fa95a69db3b18df
+oid sha256:187b75866019afe026d710fcccc6513e4c93daccc4515dfb7d4b64af42d51daf
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56e2eb998e3511987450b04c2821134362db5fea68a690ed6c4540da8553ff2d
+oid sha256:df73f21a3c64830a8e3b79f22bdc53b3503242cc10094ae9928f22ba123bf0ea
 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": 1.056871771812439,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9900990099009901,
+  "best_metric": 1.038770079612732,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.9801980198019802,
   "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": 33.485,
       "eval_steps_per_second": 4.333,
       "step": 25
+    },
+    {
+      "epoch": 1.0297029702970297,
+      "grad_norm": 0.3931041955947876,
+      "learning_rate": 5e-05,
+      "loss": 1.868,
+      "step": 26
+    },
+    {
+      "epoch": 1.0693069306930694,
+      "grad_norm": 0.17448069155216217,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.0283,
+      "step": 27
+    },
+    {
+      "epoch": 1.108910891089109,
+      "grad_norm": 0.16501682996749878,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.0282,
+      "step": 28
+    },
+    {
+      "epoch": 1.1485148514851484,
+      "grad_norm": 0.17824433743953705,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.0359,
+      "step": 29
+    },
+    {
+      "epoch": 1.188118811881188,
+      "grad_norm": 0.1824713945388794,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.1047,
+      "step": 30
+    },
+    {
+      "epoch": 1.2277227722772277,
+      "grad_norm": 0.1907730996608734,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.0385,
+      "step": 31
+    },
+    {
+      "epoch": 1.2673267326732673,
+      "grad_norm": 0.1827002614736557,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.0663,
+      "step": 32
+    },
+    {
+      "epoch": 1.306930693069307,
+      "grad_norm": 0.1699700951576233,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0677,
+      "step": 33
+    },
+    {
+      "epoch": 1.3465346534653464,
+      "grad_norm": 0.17300648987293243,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0733,
+      "step": 34
+    },
+    {
+      "epoch": 1.386138613861386,
+      "grad_norm": 0.19404511153697968,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0159,
+      "step": 35
+    },
+    {
+      "epoch": 1.4257425742574257,
+      "grad_norm": 0.1753624975681305,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0104,
+      "step": 36
+    },
+    {
+      "epoch": 1.4653465346534653,
+      "grad_norm": 0.18822410702705383,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0536,
+      "step": 37
+    },
+    {
+      "epoch": 1.504950495049505,
+      "grad_norm": 0.18399225175380707,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.0075,
+      "step": 38
+    },
+    {
+      "epoch": 1.5445544554455446,
+      "grad_norm": 0.1993323415517807,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0593,
+      "step": 39
+    },
+    {
+      "epoch": 1.5841584158415842,
+      "grad_norm": 0.2035914957523346,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.0215,
+      "step": 40
+    },
+    {
+      "epoch": 1.6237623762376239,
+      "grad_norm": 0.1820361465215683,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.0208,
+      "step": 41
+    },
+    {
+      "epoch": 1.6633663366336635,
+      "grad_norm": 0.18179836869239807,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.0272,
+      "step": 42
+    },
+    {
+      "epoch": 1.702970297029703,
+      "grad_norm": 0.1808120161294937,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0514,
+      "step": 43
+    },
+    {
+      "epoch": 1.7425742574257426,
+      "grad_norm": 0.2117820531129837,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0239,
+      "step": 44
+    },
+    {
+      "epoch": 1.7821782178217822,
+      "grad_norm": 0.18280823528766632,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1092,
+      "step": 45
+    },
+    {
+      "epoch": 1.8217821782178216,
+      "grad_norm": 0.1770055592060089,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0272,
+      "step": 46
+    },
+    {
+      "epoch": 1.8613861386138613,
+      "grad_norm": 0.18721257150173187,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.0148,
+      "step": 47
+    },
+    {
+      "epoch": 1.900990099009901,
+      "grad_norm": 0.1646788865327835,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0005,
+      "step": 48
+    },
+    {
+      "epoch": 1.9405940594059405,
+      "grad_norm": 0.20507276058197021,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9963,
+      "step": 49
+    },
+    {
+      "epoch": 1.9801980198019802,
+      "grad_norm": 0.1950192004442215,
+      "learning_rate": 0.0,
+      "loss": 1.1338,
+      "step": 50
+    },
+    {
+      "epoch": 1.9801980198019802,
+      "eval_loss": 1.038770079612732,
+      "eval_runtime": 5.0815,
+      "eval_samples_per_second": 33.455,
+      "eval_steps_per_second": 4.329,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null