Training in progress, step 42, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea9f52cdecd5cdec9236efd8c7d5b9578e1f65b1621568cb1fec84682edc326
+oid sha256:84e1d8298db103c4263d41316999f626839adcea5d9f3cb61a8696fc5cfb8ef6
 size 389352298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d0dfdb84d8a900bb3eab2154b1f816910f09683cba4a5579b74bc37486bc7ec
+oid sha256:f5e1ee7bb80d13c7a6e39adacfadef48466759fb6292dcd02a8127af8563f373
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f80336a680673462238074a39fde3600f299b1a0ff07ca48fde26c383870ca08
+oid sha256:0180bbdae61375fbee54086be71c552bc622c0746225b3f4c558e1a5c42f20b5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad29f6a363d76fbfb3bf8227af8a1c2e7ac6cec67e0a1008233b0b83a1ad6ff
+oid sha256:46b5b4551584ca3ed02b847caa69c393f79103bc9e9025a13ebe4aae0f85e447
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1da2e8b58360abee8f9c75df592d334808b9803321f624c45a68e813a11b74c9
+oid sha256:c04fc5db7515c41ef1e9a1f9a3ed99e89a1ff87564ab885a4472e5ef72de00f4
 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": 28.113,
       "eval_steps_per_second": 7.309,
       "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": 1.127497768894464e+17,
+  "total_flos": 1.8941962517426995e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null