Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68b45d7731fb9f9558dafe56490ed1bbe581557a2aa7a7e6e4509b6826a85826
+oid sha256:5a9a73146cc50d6468a1dde70cb182b7c165cf8d89b66dbe60e801d17abff41a
 size 108113968

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37cf412ec29a5f1e12c9ee20b190c0b06ceff4073c954e035ce478c911d61d4d
+oid sha256:436ea7e2fe615cbdb3d1a4b429c71dbe84201155ecc2afe3fcbdc6a0ca9fbe10
 size 55549892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8fc440eab6dca053ba0b298f5686f0a61a4cbfdc381fe890c4993a7dab1b142
+oid sha256:56110da92f5ce40b49d72bce33f1e5f6a5afa08b3a6ce366b93706cbc7fb869b
 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": 0.034597471723220224,
+  "epoch": 0.04435573297848747,
   "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": 20.901,
       "eval_steps_per_second": 10.472,
       "step": 39
+    },
+    {
+      "epoch": 0.03548458638278998,
+      "grad_norm": 1.6044561862945557,
+      "learning_rate": 7.3223304703363135e-06,
+      "loss": 0.525,
+      "step": 40
+    },
+    {
+      "epoch": 0.036371701042359726,
+      "grad_norm": 2.315598726272583,
+      "learning_rate": 5.989850859999227e-06,
+      "loss": 0.6067,
+      "step": 41
+    },
+    {
+      "epoch": 0.037258815701929474,
+      "grad_norm": 1.8639142513275146,
+      "learning_rate": 4.7745751406263165e-06,
+      "loss": 0.6147,
+      "step": 42
+    },
+    {
+      "epoch": 0.03814593036149922,
+      "grad_norm": 2.1164658069610596,
+      "learning_rate": 3.6839958911476957e-06,
+      "loss": 0.5504,
+      "step": 43
+    },
+    {
+      "epoch": 0.039033045021068975,
+      "grad_norm": 2.0981204509735107,
+      "learning_rate": 2.7248368952908053e-06,
+      "loss": 0.6325,
+      "step": 44
+    },
+    {
+      "epoch": 0.03992015968063872,
+      "grad_norm": 1.7437758445739746,
+      "learning_rate": 1.9030116872178316e-06,
+      "loss": 0.4499,
+      "step": 45
+    },
+    {
+      "epoch": 0.04080727434020847,
+      "grad_norm": 2.0806751251220703,
+      "learning_rate": 1.2235870926211619e-06,
+      "loss": 0.5006,
+      "step": 46
+    },
+    {
+      "epoch": 0.041694388999778224,
+      "grad_norm": 2.024292469024658,
+      "learning_rate": 6.907519900580861e-07,
+      "loss": 0.5585,
+      "step": 47
+    },
+    {
+      "epoch": 0.04258150365934797,
+      "grad_norm": 1.8988577127456665,
+      "learning_rate": 3.077914851215585e-07,
+      "loss": 0.4586,
+      "step": 48
+    },
+    {
+      "epoch": 0.04346861831891772,
+      "grad_norm": 2.1858489513397217,
+      "learning_rate": 7.706665667180091e-08,
+      "loss": 0.5561,
+      "step": 49
+    },
+    {
+      "epoch": 0.04435573297848747,
+      "grad_norm": 2.0317609310150146,
+      "learning_rate": 0.0,
+      "loss": 0.5758,
+      "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": 8004335107571712.0,
+  "total_flos": 1.02619680866304e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null