Training in progress, step 42, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a243e25868588098dfc5ac6739275cff9305a8f5d4580a18cb935e4a5992e16
+oid sha256:3847314accc72c286cb19a3eca09f4dbaf69efb71adeb6af8149e84b246487f1
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a5c0fc699e4a84bd20a5db050d3325c15510d8a0646518521770398f23b2bb1
+oid sha256:3d5be98d590bedd9351ec4a9989c1d7aac041502f07306260f53f977afd74319
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a828325a58bc744cb4d0ecef7c7b4b8aa50cd4bef0cdbc0cdac1f9dae32740d
+oid sha256:431e12a58eecd2d80288da8d83a472c9ee04db458a132adeac2166abfdbc4131
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02c79849e7e7ccefcc8213faac7e2b0c494ccf961e07e9f4289e8702b994c706
+oid sha256:89ac79122c8b378dfe324e1490f9b21075e03d5d33dd08a0b69aeee6bca67625
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:377fdbdd15df914f1dcdc6c32f078e4226c7905ab6027e54c22ed62d69579d1b
+oid sha256:ec0f77948c84045643e678a7b5e8fe1f16a3220beff76d97c16c27a3bb355967
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:270f031239c90143a69a5e3103494133e68e56d7495d4d43bd4cf80bb106050c
+oid sha256:1d29324a0d5877763002861a44f469da99d01dae7b8684c45bb1b74d6def2b49
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.8251121076233185,
+  "epoch": 3.10762331838565,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 42,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,125 @@
       "eval_samples_per_second": 91.478,
       "eval_steps_per_second": 11.678,
       "step": 25
+    },
+    {
+      "epoch": 1.8968609865470851,
+      "grad_norm": NaN,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.9686098654708521,
+      "grad_norm": NaN,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.071748878923767,
+      "grad_norm": NaN,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.1434977578475336,
+      "grad_norm": NaN,
+      "learning_rate": 2.3875071764202563e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.2152466367713006,
+      "grad_norm": NaN,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.286995515695067,
+      "grad_norm": NaN,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.3587443946188342,
+      "grad_norm": NaN,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.430493273542601,
+      "grad_norm": NaN,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.502242152466368,
+      "grad_norm": NaN,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.5739910313901344,
+      "grad_norm": NaN,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.6457399103139014,
+      "grad_norm": NaN,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.717488789237668,
+      "grad_norm": NaN,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.789237668161435,
+      "grad_norm": NaN,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.8609865470852016,
+      "grad_norm": NaN,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.9327354260089686,
+      "grad_norm": NaN,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 3.0358744394618835,
+      "grad_norm": NaN,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 3.10762331838565,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 42
     }
   ],
   "logging_steps": 1,
@@ -221,12 +340,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.29768176943104e+16,
+  "total_flos": 8.900105372644147e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null