Training in progress, step 35, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5a2fcbd27b645c2e6e67b5e4c6b3623a09ff1412b2a9f04322710b6f3cd024f
+oid sha256:fe9b3c91781fb64a2a070d458f515d3474e7c0924b65e3bee5a042eae7efd121
 size 389352298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71040a26e535da4ccc4e4fa30ae0587d32bd2f489d90ca65a35db93ae79d1f3e
+oid sha256:1f215bdf14ef4bdfc3a87bb581d362c4ebcdc7c3fd1b8a3f2e5eba4fc946d295
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7b2da7a65cadcc88f94c27e5b14090b0260065a8199c95a58b4a2e75bbc8e4b
+oid sha256:b9071ea54b8a193cc44b9da4ab7387aea17ff7048416999ad59f97aef835643f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9caa4a0fc4a94a5fb02e422d7b1641bfbb41a4d56632309edf6363225486579
+oid sha256:d7104555415fc0c13079c9fe4f9cef2a653643f7710c5c483cc3f20790b7bf9c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ef1b3558ac2ed13dd9ae78da88a28f0df4794c8539b24b10d4db48594385d51
+oid sha256:ab47b877f4cb3365ae6a850d9dd0a2faa3c8553a020633b832ffd6a73ea6afd1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c09031e244e5c89e52b3c3bb662b54db8a85996e54bd9c77222030648f1c7db3
+oid sha256:93ce236cdfc3570e60fc168a599f38d18a8345a454926b769bf6e4e2c224361f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.1739130434782608,
+  "epoch": 3.0434782608695654,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 35,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,76 @@
       "eval_samples_per_second": 48.246,
       "eval_steps_per_second": 12.544,
       "step": 25
+    },
+    {
+      "epoch": 2.260869565217391,
+      "grad_norm": NaN,
+      "learning_rate": 2.5531266972462177e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.3478260869565215,
+      "grad_norm": NaN,
+      "learning_rate": 2.2431968285271844e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.4347826086956523,
+      "grad_norm": NaN,
+      "learning_rate": 1.9627610736574575e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.5217391304347827,
+      "grad_norm": NaN,
+      "learning_rate": 1.7143591022596845e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.608695652173913,
+      "grad_norm": NaN,
+      "learning_rate": 1.5002404810528451e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.6956521739130435,
+      "grad_norm": NaN,
+      "learning_rate": 1.3223443014276737e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.782608695652174,
+      "grad_norm": NaN,
+      "learning_rate": 1.1822816187347623e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.869565217391304,
+      "grad_norm": NaN,
+      "learning_rate": 1.08132086231782e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.9565217391304346,
+      "grad_norm": NaN,
+      "learning_rate": 1.0203763484211195e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 3.0434782608695654,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 35
     }
   ],
   "logging_steps": 1,
@@ -221,12 +291,12 @@
         "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": 1.5784968764522496e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null