Training in progress, step 38, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55abf38da8560f502c7bfac468e3f5fd4734b6c15cfdd892fbf44e9f3d923f6d
+oid sha256:343218ed29268c03f1d1b92d8742d5ba4b9156672ec977e8f678d010622b4b7f
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb1fffd2886366d0f76f43c50746a2f2b49ba14198be08283facc93e12d8ecd8
+oid sha256:f21c21a6e64e9c95ef9d5f0c0d5224a2a1590fd0b24dd2de6c0db1c1db7e8a36
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:abb72c4c9f710d54d49fbbda13bd772fb4957f131cfa293fa0da5a18e4750975
+oid sha256:9644c862e904507065ededeb43d0bd7b253f7d68dbeeedba7e6116b6fc07be78
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d19a2e1832d537a8b8ecdff84af73235257f14b7f87d51937319ee9dcfb1018
+oid sha256:7cdfb2330847c8dc612b390971bde341682fec90dd46e14b0012e3b555a759a4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7761778d1a3ef62b2004bdd3df273514e3fd82412a22c21dee5de7cacfdaf9a
+oid sha256:16b5ad5e6e3ea0c387effffe337d57bec254db0243bf38b58a18bf1f2369f3ab
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a406d8192093f13a52f96414d92a2d6aeae9670af79ab805820a4fb9796883e
+oid sha256:740147718cad9cd26564841000686d2c7f17398d700c9c79cce591a1ce909303
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.9801980198019802,
+  "epoch": 3.00990099009901,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 38,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,97 @@
       "eval_samples_per_second": 87.138,
       "eval_steps_per_second": 22.656,
       "step": 25
+    },
+    {
+      "epoch": 2.0594059405940595,
+      "grad_norm": NaN,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.1386138613861387,
+      "grad_norm": NaN,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.217821782178218,
+      "grad_norm": NaN,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.297029702970297,
+      "grad_norm": NaN,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.376237623762376,
+      "grad_norm": NaN,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.4554455445544554,
+      "grad_norm": NaN,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.5346534653465347,
+      "grad_norm": NaN,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.613861386138614,
+      "grad_norm": NaN,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.693069306930693,
+      "grad_norm": NaN,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.772277227722772,
+      "grad_norm": NaN,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.8514851485148514,
+      "grad_norm": NaN,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.9306930693069306,
+      "grad_norm": NaN,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 3.00990099009901,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 38
     }
   ],
   "logging_steps": 1,
@@ -221,12 +312,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.47650456322048e+16,
+  "total_flos": 2.2442869360951296e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null