Training in progress, step 60, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dc1ed4ea3f34346ba15f8517ff368ba55023ad108f2ac9b39b14eb2653313a6
+oid sha256:8eedc6dd7db3d4fe601dd08ca45ac38cf98205c00682b172f51a906272469b9b
 size 226530600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1e5d79e4453cc3e80269c8010a1abc457598236ded8b6be8ff0e260a9ea6e97
+oid sha256:fa9bc8e0466959fb11e7f667b0a5fbeb864c9c9759dff133253add32590bb768
 size 115354644

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b194549dfcee051dcedd67af19a994f820d4ff8b2d796675ddffac208747af9
+oid sha256:254a2a4ea6570bd3318bb6c1ef5e9e7c1059051b32ba65d029c4727562c7eff5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a181c7feb65c92abcde98ab3662a60bf35ac366535cfc39ab425ef46f9e2e420
+oid sha256:1f63d4e0c7d7131d14392422b1ec0a6ff0f019a0c34c3f7beaaab7f148f866f5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bef9cd2c1fc33c197ddcdc788a37b14767be75603d368c4ea1c3192c225f5de1
+oid sha256:dba7096e660ce5e1d419bfc8b12086656b3da6c0ba477416c0f41ef749ee3d1b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68392f15be4d17a431bcf6184c85a3ee3a00f247121eb3d42073743fe4ba8d85
+oid sha256:5360e85dee95126c3a19c457af52319bf0238949a1cbd96011f42dd7aa5d8e9b
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c00cfb89cc0c1f4b44c9e8425b979978438eec9732f0a17406794bebcb25105f
+oid sha256:d545e31b57b52425b429413aec8655fe1208c666ebd2494232a540cd8bb8c251
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.4963310956954956,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 2.5,
+  "epoch": 3.0,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 60,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,76 @@
       "eval_samples_per_second": 202.139,
       "eval_steps_per_second": 13.577,
       "step": 50
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.2134854942560196,
+      "learning_rate": 7.783603724899257e-06,
+      "loss": 1.5809,
+      "step": 51
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.3256972134113312,
+      "learning_rate": 6.184665997806832e-06,
+      "loss": 1.4927,
+      "step": 52
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.3365941047668457,
+      "learning_rate": 4.758647376699032e-06,
+      "loss": 1.4284,
+      "step": 53
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.44477665424346924,
+      "learning_rate": 3.511175705587433e-06,
+      "loss": 1.3492,
+      "step": 54
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.2506597936153412,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.6165,
+      "step": 55
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.244708850979805,
+      "learning_rate": 1.5708419435684462e-06,
+      "loss": 1.5343,
+      "step": 56
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.2866310477256775,
+      "learning_rate": 8.856374635655695e-07,
+      "loss": 1.4461,
+      "step": 57
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.3651483952999115,
+      "learning_rate": 3.9426493427611177e-07,
+      "loss": 1.3975,
+      "step": 58
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 0.6168851256370544,
+      "learning_rate": 9.866357858642205e-08,
+      "loss": 1.4627,
+      "step": 59
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.22436027228832245,
+      "learning_rate": 0.0,
+      "loss": 1.6042,
+      "step": 60
     }
   ],
   "logging_steps": 1,
@@ -396,12 +466,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6.289557892890624e+16,
+  "total_flos": 7.515146245531238e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null