Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71351beb17c56a5d48ab7e52ff02d532954d4182ebf0e30e387fa05c052873db
+oid sha256:8baa45bc9746ed5d8ae95dd594c9dc66734c749e5061e53c0e8174340e624a94
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf6600010e116a8765f4e0784d3b0743fa9b3ae050e8067cf3a390e40c7db931
+oid sha256:eb364fd4759bdea0a2a30f70446c8e9e4baf6bd6e193fbde445801834f25aaef
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbfb026cea3c0bd78af5f1903ef6e5080b6ae65abe88663dd4484bb3582c1409
+oid sha256:6d72898f9fb03c8d8cfda2a4d260fc9f9c60c3f67eb6d127b7f9779c0bb7d1fd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28418a35cb7e15ebbce37743b08fd366c25ee320167b307a3e449a74781d02de
+oid sha256:439e51f57871ee9c2bc8b35458a0c03f9b948af7a0d15ffe5e1cf9789955c6c8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0010954671535409572,
+  "epoch": 0.0014044450686422527,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -312,6 +312,83 @@
       "eval_samples_per_second": 32.786,
       "eval_steps_per_second": 16.393,
       "step": 39
+    },
+    {
+      "epoch": 0.0011235560549138022,
+      "grad_norm": 0.6307317018508911,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 1.7394,
+      "step": 40
+    },
+    {
+      "epoch": 0.0011516449562866472,
+      "grad_norm": 0.6566604971885681,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 2.3986,
+      "step": 41
+    },
+    {
+      "epoch": 0.0011797338576594923,
+      "grad_norm": 0.4315185844898224,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 1.5226,
+      "step": 42
+    },
+    {
+      "epoch": 0.0012078227590323373,
+      "grad_norm": 0.5117611885070801,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 2.1566,
+      "step": 43
+    },
+    {
+      "epoch": 0.0012359116604051825,
+      "grad_norm": 0.7823176980018616,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 2.8308,
+      "step": 44
+    },
+    {
+      "epoch": 0.0012640005617780275,
+      "grad_norm": 0.6485798954963684,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 2.1785,
+      "step": 45
+    },
+    {
+      "epoch": 0.0012920894631508724,
+      "grad_norm": 0.6772187948226929,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 2.3526,
+      "step": 46
+    },
+    {
+      "epoch": 0.0013201783645237176,
+      "grad_norm": 0.534871518611908,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 2.0306,
+      "step": 47
+    },
+    {
+      "epoch": 0.0013482672658965626,
+      "grad_norm": 0.9086105823516846,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 3.1027,
+      "step": 48
+    },
+    {
+      "epoch": 0.0013763561672694078,
+      "grad_norm": 0.6149564385414124,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 2.2754,
+      "step": 49
+    },
+    {
+      "epoch": 0.0014044450686422527,
+      "grad_norm": 0.7337858080863953,
+      "learning_rate": 0.0,
+      "loss": 2.0508,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -326,12 +403,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 6926978283208704.0,
+  "total_flos": 9105273340821504.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null