Training in progress, epoch 1, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e979dbd3cbd940f959a4ba68cfe39ed192ba6aaf26b940558b355981237dddf9
+oid sha256:b367de47e5966fa8aad849c95b23eaff4a33c70ff5298d5b3d88e91984573b55
 size 69527352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39a2e574caffeb2fdfdb41ce93130d1ac0d397bbcadbeb7dd4e2d64b60937f1b
+oid sha256:c0b40cd55d966e26ccaed9c05a73c18c5bccd3f041050c4308e1b1f5ab6c377f
 size 35778900

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aff15d3484f18cecf83b769183ac0cc241615e7ba3d43c9e65497b2930f18c5
+oid sha256:522b123c0533634a3c8a15c4e1445a6191f73e80bcc350dc28da1bb5df0f111c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcf348532606e290f3cddebc7f00005cce6f05bb1cced2bad1d4a15482755657
+oid sha256:884dbcf1f76cdf64d0ca16f2c81847fd9a35ed97a8bdfbbdeee456fb385a47c3
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0,
+  "epoch": 1.6348773841961854,
   "eval_steps": 500,
-  "global_step": 367,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -64,6 +64,49 @@
       "eval_samples_per_second": 72.046,
       "eval_steps_per_second": 18.186,
       "step": 367
+    },
+    {
+      "epoch": 1.0899182561307903,
+      "grad_norm": 0.2055899053812027,
+      "learning_rate": 0.0004,
+      "loss": 0.2806,
+      "step": 400
+    },
+    {
+      "epoch": 1.226158038147139,
+      "grad_norm": 0.28835996985435486,
+      "learning_rate": 0.0004,
+      "loss": 0.2058,
+      "step": 450
+    },
+    {
+      "epoch": 1.3623978201634879,
+      "grad_norm": 0.30920594930648804,
+      "learning_rate": 0.0004,
+      "loss": 0.1817,
+      "step": 500
+    },
+    {
+      "epoch": 1.4986376021798364,
+      "grad_norm": 0.18480294942855835,
+      "learning_rate": 0.0004,
+      "loss": 0.1557,
+      "step": 550
+    },
+    {
+      "epoch": 1.6348773841961854,
+      "grad_norm": 0.6040850877761841,
+      "learning_rate": 0.0004,
+      "loss": 0.1337,
+      "step": 600
+    },
+    {
+      "epoch": 1.6348773841961854,
+      "eval_loss": 0.14192721247673035,
+      "eval_runtime": 4.3794,
+      "eval_samples_per_second": 70.557,
+      "eval_steps_per_second": 17.811,
+      "step": 600
     }
   ],
   "logging_steps": 50,
@@ -78,12 +121,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.189318078660608e+16,
+  "total_flos": 1.945276023865344e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null