Training in progress, step 34, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2d66f455a952e4176f67d05e9c04675fc25aa83391a8f55aedf3b85c512d436
+oid sha256:c42c3c2a0c13a16005baf285dc8912d1a1e173086f4a129e56148a19067f02c3
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69f87be26e2e3eda0942e1c9d0c6a219fb0d8e0b24a5257d9703f2cb0da86021
+oid sha256:52baca46da63ab8d923767173662ad968098bca9c6095b7bd53de804023b83ea
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72713686055434aa580e04407b2af0c220263b2b6e945a661eed39a617383124
+oid sha256:0069bf334de6ead6a3628d22b2ac83680f342c63ae9d2f9519892fc6cb7342b4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94763f01747a9e805c5d5a661fb0449b24048697de45934fb5e1ff4678da1f71
+oid sha256:3da20df5877d051a6416d3a303ff38b8dd96c361ab0c6bd7ceb680dbfa447567
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0123f51a6ab1b5ab3e72ff93bb75fcf860b180de30fc3ad8ca06deaa3484852
+oid sha256:af92f7c0b468606cac8dde6cb9f4a2abeb325056793c54bf3238837549f5b55e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b12d241e8fb1b3e11e8c5cb02193273c2ee654cad9db25aa440994d84e6216c
+oid sha256:d1b434902ffa6e64a48fb35f89428cde0d06ff603d30772ad82d91be6047f9a2
 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": 2.4257006645202637,
   "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": 9.698,
       "eval_steps_per_second": 2.521,
       "step": 25
+    },
+    {
+      "epoch": 2.2975206611570247,
+      "grad_norm": 0.41272634267807007,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.5983,
+      "step": 26
+    },
+    {
+      "epoch": 2.3856749311294765,
+      "grad_norm": 0.36301037669181824,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 2.2062,
+      "step": 27
+    },
+    {
+      "epoch": 2.4738292011019283,
+      "grad_norm": 0.3128720819950104,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.4659,
+      "step": 28
+    },
+    {
+      "epoch": 2.56198347107438,
+      "grad_norm": 0.4098537266254425,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 2.8288,
+      "step": 29
+    },
+    {
+      "epoch": 2.650137741046832,
+      "grad_norm": 0.3570498824119568,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.247,
+      "step": 30
+    },
+    {
+      "epoch": 2.7382920110192837,
+      "grad_norm": 0.33370527625083923,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 1.6995,
+      "step": 31
+    },
+    {
+      "epoch": 2.8264462809917354,
+      "grad_norm": 0.3551836907863617,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.5734,
+      "step": 32
+    },
+    {
+      "epoch": 2.9146005509641872,
+      "grad_norm": 0.43611598014831543,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 2.4137,
+      "step": 33
+    },
+    {
+      "epoch": 3.005509641873278,
+      "grad_norm": 0.7053166627883911,
+      "learning_rate": 1e-05,
+      "loss": 3.3946,
+      "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": 3.315690861756416e+17,
+  "total_flos": 4.509339571988726e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null