Training in progress, step 34, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85929c36d92d03f80167dd948253afea333de639b460592e797dfdd855ed5bc8
+oid sha256:bc9d850ea609216414612201c953048f6ccab0badb16fea9b8c93a39e3e6b00c
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e519d09c1517d643cd2ff8c0d44c15424e584451d72c7ee8e9d6284ea86f4940
+oid sha256:b3aabe0efc8fd3badef31a1805a143fd216a6558fc194ce2c86f1dacf973b18f
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f34728008c0cefcc500d3fffd3a67133de449dc943b88c6904bcfb126989ec7c
+oid sha256:1d8697b7551bf856a5235c618877d3f08e51bce117ee47d6167672006e195573
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8f669e3695c9dac9a3b6145c02a94d68976ffc49e59ce4702934a12372f0b02
+oid sha256:0b69b7af91cde0bda6b7460800b310fad956fbf111ccaf4508783178ada08c9b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc7ebba033607df4b2e7dae48cf3857238f09dd660eb0e95f585d541b5754c1
+oid sha256:96f93176472e0e74a81927968bc9740d1070fb3e56ee4eb37e50e997c7855738
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14860beba07708afd314aad109e30dd0abc3663a0e91bd94e02f33a6971da01e
+oid sha256:f69ae2acdc2430611e767f34a98667ac8877bf260d2c481eb0768cd6a8298368
 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": 0.8870174884796143,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.2598870056497176,
+  "epoch": 3.073446327683616,
   "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": 12.361,
       "eval_steps_per_second": 3.214,
       "step": 25
+    },
+    {
+      "epoch": 2.3502824858757063,
+      "grad_norm": 5.005720138549805,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.8566,
+      "step": 26
+    },
+    {
+      "epoch": 2.440677966101695,
+      "grad_norm": 2.771768808364868,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 0.8103,
+      "step": 27
+    },
+    {
+      "epoch": 2.5310734463276834,
+      "grad_norm": 4.710256099700928,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.8872,
+      "step": 28
+    },
+    {
+      "epoch": 2.621468926553672,
+      "grad_norm": 1.0690233707427979,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 0.7851,
+      "step": 29
+    },
+    {
+      "epoch": 2.711864406779661,
+      "grad_norm": 0.7217433452606201,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.7766,
+      "step": 30
+    },
+    {
+      "epoch": 2.8022598870056497,
+      "grad_norm": 4.904714584350586,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 0.9447,
+      "step": 31
+    },
+    {
+      "epoch": 2.8926553672316384,
+      "grad_norm": 0.3844352066516876,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.7963,
+      "step": 32
+    },
+    {
+      "epoch": 2.983050847457627,
+      "grad_norm": 1.9771721363067627,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 0.8196,
+      "step": 33
+    },
+    {
+      "epoch": 3.073446327683616,
+      "grad_norm": 2.5300893783569336,
+      "learning_rate": 1e-05,
+      "loss": 1.5906,
+      "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": 3.087239672233984e+17,
+  "total_flos": 4.198645954238218e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null