Training in progress, step 42, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0e90780e95f3566e2c326d23bfa66a422581afaa811b0f21d45ba9016e71f78
+oid sha256:af9ce5aa38b29b62f3c34d44f56dcea936c82cd18d46eecf9404b7557abfd0cc
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:304259f67cdea0f7dfe82d17fd6cb415c8fed084ad0f6755d24fbc33c636f051
+oid sha256:756d192e57815519c5ed3e204d067b1ca7e65cc9dee868fa1eefc269c3ec9b28
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17430f784bb69f42c7e56507ad7bd326b4fe1d0e770a29abdb453e1e81417073
+oid sha256:0154da413b4719b094cf336c1f8577a9eb74931a82e9f36cb428952d976fb143
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:565e16ecc176b06ed1e25c41b971a48ee962f35fb8769fd89c9b2c6e303ba47d
+oid sha256:4f9979ab11f5dd8e066fb7d600fa53d89e5ae7ff0899bdc28c259b6a87808b31
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:936d89bada3860a77be57456923a4f382d55999392133763b3cfdfb8f161205c
+oid sha256:44e84dd805afe4692ae2431dfc53dd326bca9f6aade370530337725da56ccf14
 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": 1.82648401826484,
+  "epoch": 3.0684931506849313,
   "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": 11.927,
       "eval_steps_per_second": 3.101,
       "step": 25
+    },
+    {
+      "epoch": 1.8995433789954337,
+      "grad_norm": NaN,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.9726027397260273,
+      "grad_norm": NaN,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.045662100456621,
+      "grad_norm": NaN,
+      "learning_rate": 3.45704275117204e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.1187214611872145,
+      "grad_norm": NaN,
+      "learning_rate": 3.1487564587782306e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.191780821917808,
+      "grad_norm": NaN,
+      "learning_rate": 2.854966364683872e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.2648401826484017,
+      "grad_norm": NaN,
+      "learning_rate": 2.577483782514174e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.3378995433789953,
+      "grad_norm": NaN,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.410958904109589,
+      "grad_norm": NaN,
+      "learning_rate": 2.0781731547998614e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.4840182648401825,
+      "grad_norm": NaN,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.557077625570776,
+      "grad_norm": NaN,
+      "learning_rate": 1.6631192604065855e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.6301369863013697,
+      "grad_norm": NaN,
+      "learning_rate": 1.490470641152345e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.7031963470319633,
+      "grad_norm": NaN,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.776255707762557,
+      "grad_norm": NaN,
+      "learning_rate": 1.2202456766718093e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.8493150684931505,
+      "grad_norm": NaN,
+      "learning_rate": 1.1243353582104556e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.922374429223744,
+      "grad_norm": NaN,
+      "learning_rate": 1.0554024673218807e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.9954337899543377,
+      "grad_norm": NaN,
+      "learning_rate": 1.0138719982009242e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 3.0684931506849313,
+      "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": 2.829010669142016e+17,
+  "total_flos": 4.752737924158587e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null