Training in progress, step 300, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0ddf70e3b717c4942eb29e5cb233383ecd1afc20c58cc985636fa0e06d5b136
+oid sha256:145ec1241d02e5ad7c0c5963a613fa26a9f50d41b13b54cf4e31c3a3fd967930
 size 194563400

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b1d2da135690fff7c0e120e786351cf9750b8ea31f819ca37b532af0ea60ef3
-size 99240837
+oid sha256:9fe898fa16b6709fa0c7a7e7fc599faecd85a247cbb9d57e586320b5d424d3ee
+size 99241221

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11ed94202eb6e3eaeb8f032cfd9fd46e9b4657a59638d69479f047c360d252a9
-size 14709
+oid sha256:ecb3d01905ba3db4c3065c85697c168d9e32937350baf828e8a0685920ef9c35
+size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f3a67d47428d0f6084a0c2e68b54a6b89dcabf900532b585b519c3b42aa7fc
+oid sha256:ca4f7c0edc6c0f32a409cb7bdaa5a2587da793fda2041cd5c6f57585074491a5
 size 1465

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4764031561709096,
+  "epoch": 0.7146047342563644,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -147,6 +147,76 @@
       "learning_rate": 5.6174528158664096e-05,
       "loss": 1.0359,
       "step": 200
+    },
+    {
+      "epoch": 0.5002233139794551,
+      "grad_norm": 0.11049015820026398,
+      "learning_rate": 5.232054001413941e-05,
+      "loss": 1.03,
+      "step": 210
+    },
+    {
+      "epoch": 0.5240434717880006,
+      "grad_norm": 0.11212771385908127,
+      "learning_rate": 4.845266449876645e-05,
+      "loss": 1.0016,
+      "step": 220
+    },
+    {
+      "epoch": 0.5478636295965461,
+      "grad_norm": 0.12015224993228912,
+      "learning_rate": 4.4594049078802925e-05,
+      "loss": 1.0311,
+      "step": 230
+    },
+    {
+      "epoch": 0.5716837874050915,
+      "grad_norm": 0.11489170789718628,
+      "learning_rate": 4.076778580306999e-05,
+      "loss": 1.0325,
+      "step": 240
+    },
+    {
+      "epoch": 0.595503945213637,
+      "grad_norm": 0.11050307750701904,
+      "learning_rate": 3.69967731075996e-05,
+      "loss": 0.9939,
+      "step": 250
+    },
+    {
+      "epoch": 0.6193241030221825,
+      "grad_norm": 0.11331106722354889,
+      "learning_rate": 3.330357877896577e-05,
+      "loss": 1.0314,
+      "step": 260
+    },
+    {
+      "epoch": 0.643144260830728,
+      "grad_norm": 0.1162668839097023,
+      "learning_rate": 2.9710304896401802e-05,
+      "loss": 0.9822,
+      "step": 270
+    },
+    {
+      "epoch": 0.6669644186392735,
+      "grad_norm": 0.11404977738857269,
+      "learning_rate": 2.6238455560962884e-05,
+      "loss": 0.9947,
+      "step": 280
+    },
+    {
+      "epoch": 0.690784576447819,
+      "grad_norm": 0.11031963676214218,
+      "learning_rate": 2.2908808203314635e-05,
+      "loss": 0.9889,
+      "step": 290
+    },
+    {
+      "epoch": 0.7146047342563644,
+      "grad_norm": 0.11861108988523483,
+      "learning_rate": 1.9741289240311755e-05,
+      "loss": 1.0303,
+      "step": 300
     }
   ],
   "logging_steps": 10,
@@ -166,7 +236,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.691246653341696e+17,
+  "total_flos": 2.536869980012544e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null