Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:525268cf2be2cff2c8e5f406086cdf257d67385527264222bc92fb88129f0413
+oid sha256:4232393d503c25639efffdd69d2d5ee84b482df4963e1850ef3fee93105d4f8a
 size 35237104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c135f204ccd43133c000be268603006cc522036b84274deb7af9689bb26863bb
+oid sha256:412dd53905df3253add5ef56e5ccc304794a7072e97e231a765ee116f1827c5a
 size 18810036

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:652365ff63294ffff01ffedb52e831cc2560ab06b5699bca21d63e81dd0efbe7
+oid sha256:2edc13c60910e9acd555e90579b2ee1807926bb393c7c79b1e24163c3f5bfc9f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0026382658475640436,
+  "epoch": 0.0033823921122615942,
   "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": 28.568,
       "eval_steps_per_second": 14.284,
       "step": 39
+    },
+    {
+      "epoch": 0.0027059136898092756,
+      "grad_norm": 0.787195086479187,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4687,
+      "step": 40
+    },
+    {
+      "epoch": 0.002773561532054507,
+      "grad_norm": 0.7193476557731628,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 1.8403,
+      "step": 41
+    },
+    {
+      "epoch": 0.002841209374299739,
+      "grad_norm": 0.7137141227722168,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.396,
+      "step": 42
+    },
+    {
+      "epoch": 0.002908857216544971,
+      "grad_norm": 0.571948230266571,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 1.6501,
+      "step": 43
+    },
+    {
+      "epoch": 0.0029765050587902027,
+      "grad_norm": 0.5318587422370911,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 1.1225,
+      "step": 44
+    },
+    {
+      "epoch": 0.0030441529010354347,
+      "grad_norm": 0.7348474860191345,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4402,
+      "step": 45
+    },
+    {
+      "epoch": 0.0031118007432806667,
+      "grad_norm": 0.7427931427955627,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 1.9161,
+      "step": 46
+    },
+    {
+      "epoch": 0.0031794485855258987,
+      "grad_norm": 0.917795717716217,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 2.0163,
+      "step": 47
+    },
+    {
+      "epoch": 0.0032470964277711302,
+      "grad_norm": 0.6537682414054871,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 1.3718,
+      "step": 48
+    },
+    {
+      "epoch": 0.0033147442700163622,
+      "grad_norm": 0.796440839767456,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 1.6624,
+      "step": 49
+    },
+    {
+      "epoch": 0.0033823921122615942,
+      "grad_norm": 0.7888891696929932,
+      "learning_rate": 0.0,
+      "loss": 1.7127,
+      "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": 1.124688709287936e+16,
+  "total_flos": 1.4419086016512e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null