Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:923cc0f5a96094dd719e8afa8941d4443979185f2c0e9ff063a672334b7d78a9
+oid sha256:39c0a59bab192c4041f83d5aa3f87022df8554006b51e316ab0580bdd2898692
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fd7f85808bfb26562ff7bb5a23f7fe5c355bbd0baed34d0e1e1e1e9db067e52
+oid sha256:643a695399ab179ddc0902019ef293a5789c05d855d1750bbf7a30dbf273b16f
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:797a708f786d9242fa82fa7de05ec119bfaabd9acfe319cf8e37ea4b3f95034e
+oid sha256:6d437ba5a7d7b0a1bb13e3ae664cca438f232b73f2614b5df005f31eef92ca4b
 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": 0.002391867649990034,
+  "epoch": 0.00306649698716671,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 1.9872,
       "step": 35
+    },
+    {
+      "epoch": 0.002453197589733368,
+      "grad_norm": 0.5072303414344788,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.1677,
+      "step": 40
+    },
+    {
+      "epoch": 0.002453197589733368,
+      "eval_loss": 2.004227876663208,
+      "eval_runtime": 270.7902,
+      "eval_samples_per_second": 25.355,
+      "eval_steps_per_second": 12.678,
+      "step": 40
+    },
+    {
+      "epoch": 0.002759847288450039,
+      "grad_norm": 0.5852988958358765,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.0915,
+      "step": 45
+    },
+    {
+      "epoch": 0.00306649698716671,
+      "grad_norm": 0.5973790287971497,
+      "learning_rate": 0.0,
+      "loss": 2.0098,
+      "step": 50
+    },
+    {
+      "epoch": 0.00306649698716671,
+      "eval_loss": 2.002565622329712,
+      "eval_runtime": 269.0572,
+      "eval_samples_per_second": 25.519,
+      "eval_steps_per_second": 12.759,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1483664532701184.0,
+  "total_flos": 1872822442917888.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null