Training in progress, step 42, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0445b133b7b6d94d2ff5066ac5931dac99f55605fadbf38ff69b2d5b14edd82
+oid sha256:e1de22e17f7e67e5df72b78e2bd8deeb0785349b70bddf6c3be42c36a5ed5d37
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd7db42e2583f09150fd074eddf69ec653cc2e21f27a0f147adc1f9bac6eb973
+oid sha256:50993900c031c98ad0d31cb97cacb6082310c2f5faccece67c1d5f1653702c6c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f53af7c162ab20ecde73e2c7a71f279183f01f3817090fec86e0130fc3c36b3b
+oid sha256:c0dc7b74864db77fed26e0877e36ba4ba07eeee46247be2aa5f4ea8c416b4056
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79301b518cd110c5963e63fe4aa1d2e20a8e1ca9fe36f9df3f1648359d947c5f
+oid sha256:854ff160db0bc05ab03e4a84c599e6fb49c8e9406f816367e43123453baf9e24
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:363c352cd7597154d6bf94a6eb823af53b58d416a6ddd0c7f7cdc8c43fd703fd
+oid sha256:41910b4715488a29de59c04faeea4a8e40cbc4fc55ef41abb899244ebb2c9566
 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": 1.8018018018018018,
+  "epoch": 3.027027027027027,
   "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": 49.543,
       "eval_steps_per_second": 12.881,
       "step": 25
+    },
+    {
+      "epoch": 1.8738738738738738,
+      "grad_norm": NaN,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.945945945945946,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.018018018018018,
+      "grad_norm": NaN,
+      "learning_rate": 3.45704275117204e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.09009009009009,
+      "grad_norm": NaN,
+      "learning_rate": 3.1487564587782306e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": NaN,
+      "learning_rate": 2.854966364683872e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.234234234234234,
+      "grad_norm": NaN,
+      "learning_rate": 2.577483782514174e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.3063063063063063,
+      "grad_norm": NaN,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.3783783783783785,
+      "grad_norm": NaN,
+      "learning_rate": 2.0781731547998614e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.4504504504504503,
+      "grad_norm": NaN,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.5225225225225225,
+      "grad_norm": NaN,
+      "learning_rate": 1.6631192604065855e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.5945945945945947,
+      "grad_norm": NaN,
+      "learning_rate": 1.490470641152345e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": NaN,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.7387387387387387,
+      "grad_norm": NaN,
+      "learning_rate": 1.2202456766718093e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.810810810810811,
+      "grad_norm": NaN,
+      "learning_rate": 1.1243353582104556e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.8828828828828827,
+      "grad_norm": NaN,
+      "learning_rate": 1.0554024673218807e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.954954954954955,
+      "grad_norm": NaN,
+      "learning_rate": 1.0138719982009242e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 3.027027027027027,
+      "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": 4.16708196040704e+16,
+  "total_flos": 7.000697693483827e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null