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:b2d4a000e05e951915abe7e277fa3ecb4ce433331ebfb985ecb99e45a1e7baed
+oid sha256:ea582f83a7b503f0af3c2317ca4731403da75bd9d4a81daadbc87f95a12d9e59
 size 124756544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11148edc4c8db0b7da18f92c81a0b19f2834196ad5af885e60345e1de9f1d5dc
+oid sha256:7e340326d2975e84ca0380806fc09a39b4a8223cd5b32897f6ba5557f26a729b
 size 63958740

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4fe6edaed203836109846c9373c72af92af579005375d18dfc07a6ffc24fda9
+oid sha256:6db5623a7dfbae47cc2c2f2d1105e6fdf1531d36ed29f450b50b1071453ceafb
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd8c58e5d02492554dbaa495f8cf80dff41fabc0e1288cb2fd18a103d402219
+oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0015904572564612327,
+  "epoch": 0.0031809145129224653,
   "eval_steps": 3,
-  "global_step": 3,
+  "global_step": 6,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 12.008,
       "eval_steps_per_second": 6.012,
       "step": 3
+    },
+    {
+      "epoch": 0.0021206096752816434,
+      "grad_norm": 0.6277130842208862,
+      "learning_rate": 8e-05,
+      "loss": 1.666,
+      "step": 4
+    },
+    {
+      "epoch": 0.0026507620941020544,
+      "grad_norm": 0.7468717694282532,
+      "learning_rate": 0.0001,
+      "loss": 1.6473,
+      "step": 5
+    },
+    {
+      "epoch": 0.0031809145129224653,
+      "grad_norm": 1.006897211074829,
+      "learning_rate": 0.00012,
+      "loss": 1.7221,
+      "step": 6
+    },
+    {
+      "epoch": 0.0031809145129224653,
+      "eval_loss": 1.4851133823394775,
+      "eval_runtime": 66.272,
+      "eval_samples_per_second": 11.996,
+      "eval_steps_per_second": 6.006,
+      "step": 6
     }
   ],
   "logging_steps": 1,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1813940199751680.0,
+  "total_flos": 3462976744980480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null