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:c382c0a3ce06e31b598d51e3f99bf813e24421f7c746bf7d05ee7453a58a0704
+oid sha256:a23c2faf050de80566ee094191658798b6bc90fbd26ce8cb3bec71dbebaa1c33
 size 844180648

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d592116ce62394c1f9b4305c1e0a400069bf5014822ddb44e4e777331248987
+oid sha256:1765074ab17785670b02a808863cc52c7256604ef35a4b1eca75b5f78013da76
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a86642feed49cf3105708c2d8cf554ce131e6b736eef05ddcd0d888019fc44a2
+oid sha256:7e827cce42e4df0e5f5941b229379c601561c611e19822fe5ee78d7a8d14bf9f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3621b58599df895517fadc9183fd6d26ab459046ec42e094a50ca0318f2f9650
+oid sha256:a02e3bfe7a84636e4c48f713e0b7ef1086124ad8d26e7bf8d7e28d1017c1f1d7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c67d8b59beeab44173f5569c386f73a53546895c2c13d9ed72d0caf1114bf4f
+oid sha256:1d9ed084ea8fbba944bfa6ac3313c8b81ddfe684d026e2223de8bf8dd8459f7e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a560bbdf7e47e25c9fcb266e05e7af6ad2f0b584ff75f4bf894282a030f95155
+oid sha256:56066f34c3251c1649482d09299be1970a68b8eaf0098a957d96a6dcc4c86ca2
 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": 0.151916965842247,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7889546351084813,
+  "best_metric": 0.12244860827922821,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.583826429980276,
   "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": 33.256,
       "eval_steps_per_second": 4.196,
       "step": 25
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 0.8126038908958435,
+      "learning_rate": 5e-05,
+      "loss": 0.1312,
+      "step": 26
+    },
+    {
+      "epoch": 0.8520710059171598,
+      "grad_norm": 0.6253982186317444,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.1348,
+      "step": 27
+    },
+    {
+      "epoch": 0.883629191321499,
+      "grad_norm": 1.232421636581421,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1731,
+      "step": 28
+    },
+    {
+      "epoch": 0.9151873767258383,
+      "grad_norm": 0.987608015537262,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1496,
+      "step": 29
+    },
+    {
+      "epoch": 0.9467455621301775,
+      "grad_norm": 1.2392596006393433,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1914,
+      "step": 30
+    },
+    {
+      "epoch": 0.9783037475345168,
+      "grad_norm": 1.2467976808547974,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1803,
+      "step": 31
+    },
+    {
+      "epoch": 1.0157790927021697,
+      "grad_norm": 2.3105454444885254,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.3194,
+      "step": 32
+    },
+    {
+      "epoch": 1.047337278106509,
+      "grad_norm": 0.9531238079071045,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1222,
+      "step": 33
+    },
+    {
+      "epoch": 1.078895463510848,
+      "grad_norm": 0.6901391744613647,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1073,
+      "step": 34
+    },
+    {
+      "epoch": 1.1104536489151873,
+      "grad_norm": 0.9436102509498596,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1575,
+      "step": 35
+    },
+    {
+      "epoch": 1.1420118343195267,
+      "grad_norm": 0.5259002447128296,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1389,
+      "step": 36
+    },
+    {
+      "epoch": 1.1735700197238659,
+      "grad_norm": 1.070943832397461,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0978,
+      "step": 37
+    },
+    {
+      "epoch": 1.205128205128205,
+      "grad_norm": 0.8379481434822083,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1064,
+      "step": 38
+    },
+    {
+      "epoch": 1.2366863905325443,
+      "grad_norm": 1.5261775255203247,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1332,
+      "step": 39
+    },
+    {
+      "epoch": 1.2682445759368837,
+      "grad_norm": 0.8805305361747742,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1793,
+      "step": 40
+    },
+    {
+      "epoch": 1.2998027613412229,
+      "grad_norm": 0.817218542098999,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0882,
+      "step": 41
+    },
+    {
+      "epoch": 1.331360946745562,
+      "grad_norm": 1.1261450052261353,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1114,
+      "step": 42
+    },
+    {
+      "epoch": 1.3629191321499015,
+      "grad_norm": 0.5421696901321411,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1106,
+      "step": 43
+    },
+    {
+      "epoch": 1.3944773175542406,
+      "grad_norm": 0.5997141003608704,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1043,
+      "step": 44
+    },
+    {
+      "epoch": 1.4260355029585798,
+      "grad_norm": 0.49338746070861816,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1309,
+      "step": 45
+    },
+    {
+      "epoch": 1.4575936883629192,
+      "grad_norm": 1.676269292831421,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1786,
+      "step": 46
+    },
+    {
+      "epoch": 1.4891518737672584,
+      "grad_norm": 0.6245267987251282,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.16,
+      "step": 47
+    },
+    {
+      "epoch": 1.5207100591715976,
+      "grad_norm": 0.6899737119674683,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1271,
+      "step": 48
+    },
+    {
+      "epoch": 1.552268244575937,
+      "grad_norm": 0.48432624340057373,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0773,
+      "step": 49
+    },
+    {
+      "epoch": 1.583826429980276,
+      "grad_norm": 0.7284166812896729,
+      "learning_rate": 0.0,
+      "loss": 0.1275,
+      "step": 50
+    },
+    {
+      "epoch": 1.583826429980276,
+      "eval_loss": 0.12244860827922821,
+      "eval_runtime": 6.4356,
+      "eval_samples_per_second": 33.252,
+      "eval_steps_per_second": 4.195,
+      "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": 2.629553998528512e+17,
+  "total_flos": 5.259107997057024e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null