Training in progress, step 34, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02bfbc6cd92789a2f6a8b3fe886230a6835f454195410432fc46ab7380f01c99
+oid sha256:0e8ff8a3cca1669e0800678526d55e17ea190198caf853604770746d50e3c15c
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:959a53cbd58ca1728d2737845a1cf667a016131716223ef55d416c66c1cc20c9
+oid sha256:8ebe422dfb58a5314739201813f77cde9627cd9ee345fd37142995acb7352f3c
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45ecef59091e3b876f80bbbd4921eb82d6bdad7381dec09c7769f549c9e1dfc5
+oid sha256:30cbc145e7febf9b6bc713f5656c2a854549f4d0aaccb76429dffd756e280617
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f35ca1a6dd5ef924829bd687fb8b4d177ad0b25aca274698eb8e343aebb943c8
+oid sha256:669d64392262fbd560d1602459935c91d72bf7455e5769dae8a777306dd1ab57
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ba573cb08edde1f3e520b10ee624ae47565a85a0ece8f697a6fc1934a8dbc9f
+oid sha256:97cd049a21c8b813e0071639689c3c239fa59ac0faa693a9f89f78d1f26ff960
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dee3ced2eeea2f042e3f5bd4e5222a0cedaf6a40c2166fec4f1e21d207f3baf3
+oid sha256:1090e5cefdf373f41eb80263d26d0cc0fc124a998cc4474b185d2ed814c5b911
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9df2a04f62b67211447d8ed44cee6691ed618e4d6af94df3c64d249c82d80c3
+oid sha256:1fe247b8abd9f098bbbafb55011dbe010f2fe145118845b911d1500aa9422fe0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.449061393737793,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.2569832402234637,
+  "epoch": 3.0726256983240225,
   "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": 17.738,
       "eval_steps_per_second": 2.365,
       "step": 25
+    },
+    {
+      "epoch": 2.346368715083799,
+      "grad_norm": 0.3303333520889282,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.624,
+      "step": 26
+    },
+    {
+      "epoch": 2.435754189944134,
+      "grad_norm": 0.3606821298599243,
+      "learning_rate": 1.134947733186315e-05,
+      "loss": 2.1936,
+      "step": 27
+    },
+    {
+      "epoch": 2.5251396648044695,
+      "grad_norm": 0.28290900588035583,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.9875,
+      "step": 28
+    },
+    {
+      "epoch": 2.6145251396648046,
+      "grad_norm": 0.3111993074417114,
+      "learning_rate": 5.903936782582253e-06,
+      "loss": 2.3929,
+      "step": 29
+    },
+    {
+      "epoch": 2.7039106145251397,
+      "grad_norm": 0.3869682848453522,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.2854,
+      "step": 30
+    },
+    {
+      "epoch": 2.793296089385475,
+      "grad_norm": 0.27436700463294983,
+      "learning_rate": 2.152983213389559e-06,
+      "loss": 2.072,
+      "step": 31
+    },
+    {
+      "epoch": 2.88268156424581,
+      "grad_norm": 0.3000536859035492,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.3339,
+      "step": 32
+    },
+    {
+      "epoch": 2.972067039106145,
+      "grad_norm": 0.4352191388607025,
+      "learning_rate": 2.407636663901591e-07,
+      "loss": 2.3471,
+      "step": 33
+    },
+    {
+      "epoch": 3.0726256983240225,
+      "grad_norm": 1.0655169486999512,
+      "learning_rate": 0.0,
+      "loss": 4.1814,
+      "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": 2,
   "trial_name": null,
   "trial_params": null