Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3cba42492e4359436c8e95f1e537c68b51251cd15e1825b82e7e04ef06ccec71
+oid sha256:f65b61f784215322f35ac2518e380a2f5228a8b2ca3d0e3f1a6e74fd815ff387
 size 125248064

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b93625a6c71c7ef43cc67bb08fd7b88b6fd434cfe018f0ae8c4cc2563fcd21c0
+oid sha256:4d7d641ca068830e19068b5fb302221d255d22fd0175399ad8d4038f54b860a1
 size 64219860

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": 0.0025780223593862323,
+  "epoch": 0.00330515687100799,
   "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": 26.144,
       "eval_steps_per_second": 13.072,
       "step": 39
+    },
+    {
+      "epoch": 0.0026441254968063922,
+      "grad_norm": 5.080392360687256,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 13.3521,
+      "step": 40
+    },
+    {
+      "epoch": 0.0027102286342265518,
+      "grad_norm": 7.58221960067749,
+      "learning_rate": 1.1979701719998453e-05,
+      "loss": 16.6197,
+      "step": 41
+    },
+    {
+      "epoch": 0.0027763317716467117,
+      "grad_norm": 5.832557201385498,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 14.2864,
+      "step": 42
+    },
+    {
+      "epoch": 0.0028424349090668717,
+      "grad_norm": 5.146307468414307,
+      "learning_rate": 7.367991782295391e-06,
+      "loss": 14.2749,
+      "step": 43
+    },
+    {
+      "epoch": 0.0029085380464870312,
+      "grad_norm": 7.585702896118164,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 18.1122,
+      "step": 44
+    },
+    {
+      "epoch": 0.002974641183907191,
+      "grad_norm": 7.673133850097656,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 15.479,
+      "step": 45
+    },
+    {
+      "epoch": 0.003040744321327351,
+      "grad_norm": 5.815083980560303,
+      "learning_rate": 2.4471741852423237e-06,
+      "loss": 12.2292,
+      "step": 46
+    },
+    {
+      "epoch": 0.0031068474587475107,
+      "grad_norm": 5.892566204071045,
+      "learning_rate": 1.3815039801161721e-06,
+      "loss": 13.7316,
+      "step": 47
+    },
+    {
+      "epoch": 0.0031729505961676707,
+      "grad_norm": 5.821976184844971,
+      "learning_rate": 6.15582970243117e-07,
+      "loss": 14.5609,
+      "step": 48
+    },
+    {
+      "epoch": 0.0032390537335878302,
+      "grad_norm": 5.67319393157959,
+      "learning_rate": 1.5413331334360182e-07,
+      "loss": 16.7106,
+      "step": 49
+    },
+    {
+      "epoch": 0.00330515687100799,
+      "grad_norm": 6.600288391113281,
+      "learning_rate": 0.0,
+      "loss": 14.476,
+      "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": 4.939309916356608e+16,
+  "total_flos": 6.3324486107136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null