Training in progress, step 34, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba5b31852294f16cc452ebec610dc7cf066487a624e8e79249ccd302825369b4
+oid sha256:f04ef4511017ad729eb540c517cb5253fdf36214b26dab021a815c78cfdd9f21
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5747905eb9b3ffcffceee5d69bbc68f3c403d62248bfe0635377daf6e97d5c49
+oid sha256:1e1e3c24374308bc623e6638a0f796a710348f87a4b1611428debbd860d430b9
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a39b740605c9c32e5d9586e20ae4e39de2c50c6e17e19e6464eff30e3263a93
+oid sha256:333376be933d0caecd4e6449c2dc5b2ed0935ba795d28ce0d25b032b6a0db6a5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:33b0468f4b92d56c61da0bcfeb6299c470c5b6189cde04d0841ba6e8984afe6a
+oid sha256:a392ce66d547275b38cc2d38bf4bd7a5dcf480e6c51cbc4db93827cb84285e55
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5e3cea3e500b2d60e7489a8975ff8483ff7a23c835a1b09583d555d6399ffec
+oid sha256:815d0d269d0a0c543b30c8e4da40d705090114bdbf1015058fa509d207e04d0d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c220d2fbe9a2870f9ac93749b3d4b3852ce94b5983d948fa8de3d35e453f98ce
+oid sha256:7312f49c1e1b01f68cdaee175129535fda49cd22ed1f251a2745d2c8c42996be
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.209366391184573,
+  "epoch": 3.005509641873278,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 34,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,69 @@
       "eval_samples_per_second": 12.339,
       "eval_steps_per_second": 3.208,
       "step": 25
+    },
+    {
+      "epoch": 2.2975206611570247,
+      "grad_norm": NaN,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 2.3856749311294765,
+      "grad_norm": NaN,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 2.4738292011019283,
+      "grad_norm": NaN,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.56198347107438,
+      "grad_norm": NaN,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.650137741046832,
+      "grad_norm": NaN,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.7382920110192837,
+      "grad_norm": NaN,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.8264462809917354,
+      "grad_norm": NaN,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.9146005509641872,
+      "grad_norm": NaN,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 3.005509641873278,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 34
     }
   ],
   "logging_steps": 1,
@@ -221,12 +284,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.629552387915776e+17,
+  "total_flos": 3.5761912475654554e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null