Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e9dd9be59d412e7f7d52818fbe9d15c1c25c49c12f03c25f43870531281e80f
+oid sha256:df227fa3d52d440c66aa267a144d5a3a69f47ca067549f19228dfb8e8b902a8b
 size 161533192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4171178a8d8e6a60474238c0c2255410e42ffad2d2a0e828e869fd273987cf2
+oid sha256:e54808edb394d0ed7c90566a1184e3da1c80f78de19a50a75dcc9ca2918b0dfd
 size 323290986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:008b6a389a038ecdb7471742378ed56da6268026f09f4e3d7ea3fc3fc6bc3f86
+oid sha256:5a54490b99370abe9f22c9edac5af10e233f012e495822a9566654c348c60f1f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa8c935d1f5ee2de90c29a5fabd7736ef8695aaeb2c52ea8c5bcc4a573fee422
+oid sha256:0a11ccd9312462cb64879b643b059b1d229b4127435d2851fea488751cfb3d1b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f6a1c16a35ed2b20e687e9c436429260a4ee2611da193418796ebec259463ae
+oid sha256:bdd4258911000ed83d26af1b45689b3f72be7dc7a604a48cb873e7f68c4b48f9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd2ee8cc5604082b35eab5d7049b34f58c5fa6360cec760da1df9cc1bd1493d1
+oid sha256:61300c222fa644e07f64110f4902b8aaae738d7065740bccb2b9ff2737096606
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.006916701328009367,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0042124773579342014,
+  "best_metric": 0.0040573906153440475,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.008424954715868403,
   "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": 18.368,
       "eval_steps_per_second": 2.297,
       "step": 25
+    },
+    {
+      "epoch": 0.0043809764522515695,
+      "grad_norm": 0.19603978097438812,
+      "learning_rate": 0.0001,
+      "loss": 0.0213,
+      "step": 26
+    },
+    {
+      "epoch": 0.0045494755465689376,
+      "grad_norm": 0.5282886028289795,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 0.0656,
+      "step": 27
+    },
+    {
+      "epoch": 0.004717974640886306,
+      "grad_norm": 0.0671163946390152,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 0.0094,
+      "step": 28
+    },
+    {
+      "epoch": 0.004886473735203674,
+      "grad_norm": 0.05665583908557892,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 0.0151,
+      "step": 29
+    },
+    {
+      "epoch": 0.005054972829521042,
+      "grad_norm": 0.07490652799606323,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 0.0009,
+      "step": 30
+    },
+    {
+      "epoch": 0.00522347192383841,
+      "grad_norm": 0.037155721336603165,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 0.0024,
+      "step": 31
+    },
+    {
+      "epoch": 0.005391971018155778,
+      "grad_norm": 0.05099332705140114,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 0.0078,
+      "step": 32
+    },
+    {
+      "epoch": 0.005560470112473145,
+      "grad_norm": 0.17277608811855316,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 0.0109,
+      "step": 33
+    },
+    {
+      "epoch": 0.005728969206790513,
+      "grad_norm": 0.04528217762708664,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 0.0052,
+      "step": 34
+    },
+    {
+      "epoch": 0.005897468301107881,
+      "grad_norm": 0.008220179006457329,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0004,
+      "step": 35
+    },
+    {
+      "epoch": 0.006065967395425249,
+      "grad_norm": 0.012407345697283745,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 0.0006,
+      "step": 36
+    },
+    {
+      "epoch": 0.006234466489742617,
+      "grad_norm": 0.017425227910280228,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 0.0024,
+      "step": 37
+    },
+    {
+      "epoch": 0.006402965584059985,
+      "grad_norm": 0.22802281379699707,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 0.0073,
+      "step": 38
+    },
+    {
+      "epoch": 0.006571464678377353,
+      "grad_norm": 0.0339801162481308,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 0.0057,
+      "step": 39
+    },
+    {
+      "epoch": 0.006739963772694721,
+      "grad_norm": 0.020060187205672264,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 0.0019,
+      "step": 40
+    },
+    {
+      "epoch": 0.0069084628670120895,
+      "grad_norm": 0.03689638152718544,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 0.0009,
+      "step": 41
+    },
+    {
+      "epoch": 0.0070769619613294575,
+      "grad_norm": 0.05137154832482338,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 0.0044,
+      "step": 42
+    },
+    {
+      "epoch": 0.007245461055646826,
+      "grad_norm": 0.11253440380096436,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 0.0022,
+      "step": 43
+    },
+    {
+      "epoch": 0.007413960149964194,
+      "grad_norm": 0.009691456332802773,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0005,
+      "step": 44
+    },
+    {
+      "epoch": 0.007582459244281562,
+      "grad_norm": 0.09334763884544373,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 0.0031,
+      "step": 45
+    },
+    {
+      "epoch": 0.00775095833859893,
+      "grad_norm": 0.025010887533426285,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 0.0011,
+      "step": 46
+    },
+    {
+      "epoch": 0.007919457432916298,
+      "grad_norm": 0.06059917062520981,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 0.0068,
+      "step": 47
+    },
+    {
+      "epoch": 0.008087956527233667,
+      "grad_norm": 0.0202567707747221,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 0.0009,
+      "step": 48
+    },
+    {
+      "epoch": 0.008256455621551034,
+      "grad_norm": 0.020429080352187157,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 0.003,
+      "step": 49
+    },
+    {
+      "epoch": 0.008424954715868403,
+      "grad_norm": 0.06769539415836334,
+      "learning_rate": 0.0,
+      "loss": 0.0056,
+      "step": 50
+    },
+    {
+      "epoch": 0.008424954715868403,
+      "eval_loss": 0.0040573906153440475,
+      "eval_runtime": 544.1235,
+      "eval_samples_per_second": 18.369,
+      "eval_steps_per_second": 2.297,
+      "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": 1.398077353099264e+17,
+  "total_flos": 2.796154706198528e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null