Training in progress, step 42, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ad3c7e422d2d12dec91cd763f82f50aab7564f38808a53d7e5029f441430c2ff
+oid sha256:ee681a6c63170a1729535f7435d382f4b35bb04957c886fc5e33c2d192395f99
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71e60b8a7111540fec8cfab121219a9364ec73c9794b616f8c92061128896b16
+oid sha256:6049c34f71317ec21f0dd322c3c3993ed311bb9ddafd66c9020082203753e7ee
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67227764c34c2f8846e24f53bdc41220bd46b7e0b05d49dac495931e1742f3f3
+oid sha256:9ddb2895a5d75299b2dbb8ce90af94d0650a8047d1bbdd21b71ddd51d7f59157
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36a41f1ec3d924bf5a99bc2f2cfd4d7e9db3bd9fc6a6bbc3d19cd22a7ebd8cad
+oid sha256:1d5530b5fac3e8f667c3f6fe77cfd6e09ccb7849fbfceb67bb8922e48e25edbd
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80f1280e4612c02f5480c3161106b62799fc515d10f6927ebf2e47d7c280fa42
+oid sha256:3764fa9af290045fd1f748be52e12f41605ff83c5c5440b61444f2a0f322a51a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f5af44da266da277e7531f687942d737458dea336c0a84bf03af6d775c87ac
+oid sha256:dde78f0152770b6d9ff9d100a4e49fd7ae2ec975980251062a46af49a9f251c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7857142857142856,
+  "epoch": 3.0,
   "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": 23.836,
       "eval_steps_per_second": 6.197,
       "step": 25
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": NaN,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.9285714285714286,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": NaN,
+      "learning_rate": 3.45704275117204e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.0714285714285716,
+      "grad_norm": NaN,
+      "learning_rate": 3.1487564587782306e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": NaN,
+      "learning_rate": 2.854966364683872e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.2142857142857144,
+      "grad_norm": NaN,
+      "learning_rate": 2.577483782514174e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.2857142857142856,
+      "grad_norm": NaN,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.357142857142857,
+      "grad_norm": NaN,
+      "learning_rate": 2.0781731547998614e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": NaN,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": NaN,
+      "learning_rate": 1.6631192604065855e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.571428571428571,
+      "grad_norm": NaN,
+      "learning_rate": 1.490470641152345e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.642857142857143,
+      "grad_norm": NaN,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": NaN,
+      "learning_rate": 1.2202456766718093e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.7857142857142856,
+      "grad_norm": NaN,
+      "learning_rate": 1.1243353582104556e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": NaN,
+      "learning_rate": 1.0554024673218807e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.928571428571429,
+      "grad_norm": NaN,
+      "learning_rate": 1.0138719982009242e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "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": 1,
   "trial_name": null,
   "trial_params": null