Training in progress, step 6, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8cae26ec0ea9b8d8aef33be9f3910cf76cec4588f2cd8f1d19ee5a3e49f0556
+oid sha256:fe278349d6c49411e4506ec80adca4c56257fffe5dd91e5a51c1a50a112f7966
 size 28350504

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c441286cead4cc051e15c136fcf8badf856de665a6408a2a2f403dbd04818e64
+oid sha256:54e22458b6e277f60c705388f5e433980a3f1257a307bf5a8bcfaab42363f7ec
 size 14714004

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a70d38a1d9cebbea8036393a9b3d797a45881fdb89c1ef14ae4312bc6dae3141
+oid sha256:7e615bb87d75efd43dc13426cc66767122ba58f763e3142ae1e59090342e90e2
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c237a6ed32c2da6e4c48e32ba0037725e16c7d85eed174d3b3a02e3d6735c096
+oid sha256:38fce6464e7c23ecd34a5d4fccfabe59074dd72094cc5fccbfc6244d3f7fa787
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c286a144f47b2686fa63ff203b2c0e28b8d4edcbda01b8d4ac64a1aac8b73b36
+oid sha256:def85091309617cb5d86098ac759e9484f4372554837f9b1553ddae14f267f4d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20f883c54dee1916e8ac0b1483920fbd30f191d049387ff869103c28e4937771
+oid sha256:7b4daa8970d71ed1689ed53f04b5888e991ec1c549d4989c13b065e4abd83bb2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
+oid sha256:92b4cf85d7ba7a497f88ff799bf4dec5af7dd95be6e00f78bf46ba5deb56bbf8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6736842105263158,
+  "epoch": 1.0842105263157895,
   "eval_steps": 2,
-  "global_step": 4,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -59,6 +59,28 @@
       "eval_samples_per_second": 413.083,
       "eval_steps_per_second": 51.635,
       "step": 4
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 2.6789450645446777,
+      "learning_rate": 5e-05,
+      "loss": 10.8379,
+      "step": 5
+    },
+    {
+      "epoch": 1.0842105263157895,
+      "grad_norm": 2.534017562866211,
+      "learning_rate": 6e-05,
+      "loss": 11.8271,
+      "step": 6
+    },
+    {
+      "epoch": 1.0842105263157895,
+      "eval_loss": 0.699511706829071,
+      "eval_runtime": 0.097,
+      "eval_samples_per_second": 412.269,
+      "eval_steps_per_second": 51.534,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -73,12 +95,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1911868184592384.0,
+  "total_flos": 2867802276888576.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null