Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26378e9e8974d76a51be2d53603cc61688be9b0f0e94e180c2afd8a6145e3ab4
+oid sha256:7e89567b0e432294742835782378d779073fb131bbd6fea52f2e6e42c7a4e87d
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17c2d1a8aef225b8fe858a02475b80de9e3372b6a5ab803643b7f70b887b0d46
+oid sha256:0639c518ecb1dae95fc5e95ffd1ecd8595158ad82373d327f6fb246e7ce63311
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
 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": 0.016632903294594305,
+  "epoch": 0.021324234993069624,
   "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": 11.9326,
       "step": 35
+    },
+    {
+      "epoch": 0.0170593879944557,
+      "grad_norm": 0.014193267561495304,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9328,
+      "step": 40
+    },
+    {
+      "epoch": 0.0170593879944557,
+      "eval_loss": 11.933220863342285,
+      "eval_runtime": 9.3191,
+      "eval_samples_per_second": 106.018,
+      "eval_steps_per_second": 53.009,
+      "step": 40
+    },
+    {
+      "epoch": 0.019191811493762662,
+      "grad_norm": 0.010223680175840855,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9346,
+      "step": 45
+    },
+    {
+      "epoch": 0.021324234993069624,
+      "grad_norm": 0.013457508757710457,
+      "learning_rate": 0.0,
+      "loss": 11.9313,
+      "step": 50
+    },
+    {
+      "epoch": 0.021324234993069624,
+      "eval_loss": 11.933218002319336,
+      "eval_runtime": 9.0369,
+      "eval_samples_per_second": 109.329,
+      "eval_steps_per_second": 54.665,
+      "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": 4667375616.0,
+  "total_flos": 5996691456.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null