Training in progress, step 35, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79cc6a18876559809e4a724347b95a86bda27f1f865497c98e331ca191c5396e
+oid sha256:0db147ebb62417f81519e92d1b096573887b29755593ccce42d03cfada4e8191
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc258936e5ed6574cd7a789672d7acbbfdd3deea00a8ce16c126006b1600bb3f
+oid sha256:e1494c90d577ac674719fcc3483fd15c82e59f5d9b9290d2b5c0144f79a43fe1
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f7e416783ded80e754d433ee54d8ada7de014aade71da08382234de5539d9b5
+oid sha256:983ffc8d80e0f89eb6c032f40fbde1c4ea7470dcda8f2d1ff67029065309fbf4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f95ca7e75522f7ca7ffa31c80e048b0980d775d98cbd9c8bf1f97643a423c957
+oid sha256:1cef4a0f369ece5771a253d7d41b5911f46a68f493521964477ab6fe637f1da3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3048cb4a0da77acd359ab208c5b6249130428d9a657329f6bd012934712558a
+oid sha256:883566e95d53136cb99377aab4cac05d583a73b85430a197a9f587f439a55635
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cb81ea9f530fec5dd45037e557013ae6c30b722e432cc6cd443d9400270cadb
+oid sha256:c8036c139d9fdac2a864f5c9e2869f51f3bd93e9bd3b5deded9265e6135dedf1
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42c052e81d046347be3074b07671b8743acfee2fa86afcaf4cf737a53f8e085c
+oid sha256:400690333b498d3c3ea4cd1446f834c1cb37202647b1e68e58a488ea7599ce2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.7776047587394714,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4652014652014653,
+  "epoch": 2.051282051282051,
   "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": 19.549,
       "eval_steps_per_second": 1.275,
       "step": 25
+    },
+    {
+      "epoch": 1.5238095238095237,
+      "grad_norm": 0.7313464879989624,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.7806,
+      "step": 26
+    },
+    {
+      "epoch": 1.5824175824175826,
+      "grad_norm": 0.6874339580535889,
+      "learning_rate": 1.3813298094746491e-05,
+      "loss": 0.744,
+      "step": 27
+    },
+    {
+      "epoch": 1.641025641025641,
+      "grad_norm": 0.6659790277481079,
+      "learning_rate": 1.0697345262860636e-05,
+      "loss": 0.8011,
+      "step": 28
+    },
+    {
+      "epoch": 1.6996336996336996,
+      "grad_norm": 0.8043178915977478,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.8361,
+      "step": 29
+    },
+    {
+      "epoch": 1.7582417582417582,
+      "grad_norm": 0.5227417349815369,
+      "learning_rate": 5.558227567253832e-06,
+      "loss": 0.7979,
+      "step": 30
+    },
+    {
+      "epoch": 1.8168498168498168,
+      "grad_norm": 0.5979397892951965,
+      "learning_rate": 3.581603349196372e-06,
+      "loss": 0.7131,
+      "step": 31
+    },
+    {
+      "epoch": 1.8754578754578755,
+      "grad_norm": 0.43952739238739014,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.7307,
+      "step": 32
+    },
+    {
+      "epoch": 1.934065934065934,
+      "grad_norm": 0.8428590297698975,
+      "learning_rate": 9.035651368646648e-07,
+      "loss": 0.7661,
+      "step": 33
+    },
+    {
+      "epoch": 1.9926739926739927,
+      "grad_norm": 0.6554544568061829,
+      "learning_rate": 2.2640387134577058e-07,
+      "loss": 0.8265,
+      "step": 34
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 2.641814708709717,
+      "learning_rate": 0.0,
+      "loss": 1.6606,
+      "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": 6.631381723512832e+17,
+  "total_flos": 9.283934412917965e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null