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:eb658c1e128ae211c4a80a703805f71d272e2c8ced9c73a70148c0f532e9b16b
+oid sha256:1eff986956761b06552cceaa3b070df0a6853085da4bca1769607c640647f962
 size 50365768

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fbeca8010759600245cc5b750e78d3f72140f139cc64b3b357c82d9b497c7c3
+oid sha256:39f8d0fced1dc71b9baf20fbee4405e4a9ace1fa071121ef0ce8da0b47494dad
 size 25859156

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:539f6fec05424d4999d48d5e57223c607bec5f3cd6f24e3fe3db842c0cd3c8b6
+oid sha256:05de8ba730614bdca36c6904efb922d2f22e45330307675212af81d99bdda974
 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": 0.0035929798700999587,
+  "epoch": 0.004606384448846101,
   "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": 7.9359,
       "step": 35
+    },
+    {
+      "epoch": 0.0036851075590768807,
+      "grad_norm": 3.254136562347412,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 8.5177,
+      "step": 40
+    },
+    {
+      "epoch": 0.0036851075590768807,
+      "eval_loss": 2.112778663635254,
+      "eval_runtime": 268.0758,
+      "eval_samples_per_second": 17.051,
+      "eval_steps_per_second": 8.527,
+      "step": 40
+    },
+    {
+      "epoch": 0.0041457460039614905,
+      "grad_norm": 3.4319705963134766,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 8.4412,
+      "step": 45
+    },
+    {
+      "epoch": 0.004606384448846101,
+      "grad_norm": 3.498079776763916,
+      "learning_rate": 0.0,
+      "loss": 8.5155,
+      "step": 50
+    },
+    {
+      "epoch": 0.004606384448846101,
+      "eval_loss": 2.092695713043213,
+      "eval_runtime": 268.109,
+      "eval_samples_per_second": 17.049,
+      "eval_steps_per_second": 8.526,
+      "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": 4222585537560576.0,
+  "total_flos": 5301180756393984.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null