Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e1ddb55498e50628c3310f9086dc621dc5fb0c6268ed92605cab47f2644b67
+oid sha256:f7253ba1237acfee8c78a3575cba5cfadccea4524aadeaacebe294db62c9f85d
 size 2964338224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3df4c3f5410aef96aa5d1b1220d16d0e42419e2f967dd28291d6cd8a4e444dc
+oid sha256:088943970770a526c2bcbbff1af74447c48df2eb3818f77c5660bb058e25196e
 size 1485440604

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7361d096916f558d6b135e234cb87021fe9c6dc7f10a56868e5238d1d27c50e
+oid sha256:adfc1f6d17ce11f5de73773c697955bd372b113d0cb6335c07b1343d875e4043
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:927fd63e57181ecc0ac827facbdec2bc46e991f92e1716e5d98f2005a0b865c2
+oid sha256:6cd5cd4d318d8a5b26b81d3764647251e70de609f8492e3bb5f24f102d716e01
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9192100538599641,
+  "epoch": 1.1490125673249552,
   "eval_steps": 500,
-  "global_step": 16,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,6 +119,34 @@
       "learning_rate": 4.740413892402639e-05,
       "loss": 2.1777,
       "step": 16
+    },
+    {
+      "epoch": 0.9766606822262118,
+      "grad_norm": 1.5398966073989868,
+      "learning_rate": 4.648924017468003e-05,
+      "loss": 2.2126,
+      "step": 17
+    },
+    {
+      "epoch": 1.0341113105924595,
+      "grad_norm": 1.4850305318832397,
+      "learning_rate": 4.5448234019167945e-05,
+      "loss": 2.1019,
+      "step": 18
+    },
+    {
+      "epoch": 1.0915619389587075,
+      "grad_norm": 1.4637010097503662,
+      "learning_rate": 4.428722949554857e-05,
+      "loss": 2.1119,
+      "step": 19
+    },
+    {
+      "epoch": 1.1490125673249552,
+      "grad_norm": 1.3282859325408936,
+      "learning_rate": 4.301303984001967e-05,
+      "loss": 2.0976,
+      "step": 20
     }
   ],
   "logging_steps": 1,
@@ -138,7 +166,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.0873463700504576e+16,
+  "total_flos": 1.3667697985769472e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null