Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:501fef97e868de2fe769f6afcc199fa4dcdcac6dc0d54a7fbfd43f4bcdb09305
+oid sha256:96b024e29ee002125e0394130f2c1434a37544b552d5f05373e4dc65b70c827d
 size 200068512

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94750ae2885a37a4bbc50a398a3ab56133a4ae66975744ebe68424cb12b41246
+oid sha256:a92ae950eb8973fe8640444e0074865635039b57fc8c54fd68215261244083ca
 size 102030196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:946bd86f101a9915666543051804c83e95356c740ad2bfc8b9b0bebcc0db0f88
+oid sha256:bf37acca7be357f62122feeb3f459fad809c08da8f473029dfb0c15bf0fdfba1
 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": 0.030669419050427603,
+  "epoch": 0.03931976801336872,
   "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": 2.703,
       "eval_steps_per_second": 1.351,
       "step": 39
+    },
+    {
+      "epoch": 0.03145581441069498,
+      "grad_norm": 1.3485429286956787,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6484,
+      "step": 40
+    },
+    {
+      "epoch": 0.03224220977096235,
+      "grad_norm": 1.2892612218856812,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 0.7116,
+      "step": 41
+    },
+    {
+      "epoch": 0.033028605131229724,
+      "grad_norm": 1.8880107402801514,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.5925,
+      "step": 42
+    },
+    {
+      "epoch": 0.0338150004914971,
+      "grad_norm": 1.4518492221832275,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 0.6824,
+      "step": 43
+    },
+    {
+      "epoch": 0.03460139585176447,
+      "grad_norm": 2.3983242511749268,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 0.9552,
+      "step": 44
+    },
+    {
+      "epoch": 0.03538779121203185,
+      "grad_norm": 1.543707013130188,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8833,
+      "step": 45
+    },
+    {
+      "epoch": 0.036174186572299226,
+      "grad_norm": 1.7945361137390137,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 0.8763,
+      "step": 46
+    },
+    {
+      "epoch": 0.0369605819325666,
+      "grad_norm": 1.6415727138519287,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 0.7373,
+      "step": 47
+    },
+    {
+      "epoch": 0.03774697729283397,
+      "grad_norm": 1.7929890155792236,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 0.6606,
+      "step": 48
+    },
+    {
+      "epoch": 0.03853337265310135,
+      "grad_norm": 1.3461647033691406,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 0.7808,
+      "step": 49
+    },
+    {
+      "epoch": 0.03931976801336872,
+      "grad_norm": 1.1689928770065308,
+      "learning_rate": 0.0,
+      "loss": 0.7459,
+      "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": 2.3927104080130867e+17,
+  "total_flos": 3.067577446170624e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null