Training in progress, step 100, checkpoint

checkpoint-100/README.md

@@ -202,4 +202,5 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ### Framework versions
 
 - PEFT 0.9.0
-- PEFT 0.8.2
+- PEFT 0.8.2
+- PEFT 0.7.1

checkpoint-100/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:274d63560e28ff9071de84560968bf675cbef8e9fd1c92a42018142d4c84bf60
+oid sha256:fb59f848c88a5b1b5cab3242d4c331dc775e603ff7609a07f42436d4de84a99b
 size 9443384

checkpoint-100/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6477c1f6b7f8c73eeb14d7c4314be2a685cfe187dcdaaa3ae5408f640288400b
+oid sha256:57188196c44f6f175fe4a57663b3d96a4c9aa25b1a71e5c17d4937f7a159ec03
 size 18914450

checkpoint-100/trainer_state.json

@@ -10,79 +10,79 @@
   "log_history": [
     {
       "epoch": 0.42,
-      "grad_norm": 0.1815568506717682,
+      "grad_norm": 0.18964600563049316,
       "learning_rate": 2.9999999999999997e-05,
-      "loss": 3.8657,
+      "loss": 3.866,
       "step": 10
     },
     {
       "epoch": 0.84,
-      "grad_norm": 0.23455914855003357,
+      "grad_norm": 0.240617036819458,
       "learning_rate": 5.9999999999999995e-05,
-      "loss": 3.8223,
+      "loss": 3.8202,
       "step": 20
     },
     {
       "epoch": 1.25,
-      "grad_norm": 0.32260793447494507,
+      "grad_norm": 0.32437172532081604,
       "learning_rate": 8.999999999999999e-05,
-      "loss": 3.7255,
+      "loss": 3.7224,
       "step": 30
     },
     {
       "epoch": 1.67,
-      "grad_norm": 0.38705918192863464,
+      "grad_norm": 0.39009416103363037,
       "learning_rate": 0.00011999999999999999,
-      "loss": 3.4952,
+      "loss": 3.4906,
       "step": 40
     },
     {
       "epoch": 2.09,
-      "grad_norm": 0.5273059606552124,
+      "grad_norm": 0.5346343517303467,
       "learning_rate": 0.00015,
-      "loss": 3.098,
+      "loss": 3.0915,
       "step": 50
     },
     {
       "epoch": 2.51,
-      "grad_norm": 0.6030514240264893,
+      "grad_norm": 0.6114345788955688,
       "learning_rate": 0.00017999999999999998,
-      "loss": 2.5299,
+      "loss": 2.5238,
       "step": 60
     },
     {
       "epoch": 2.92,
-      "grad_norm": 0.459722101688385,
+      "grad_norm": 0.4761127531528473,
       "learning_rate": 0.00020999999999999998,
-      "loss": 1.899,
+      "loss": 1.8914,
       "step": 70
     },
     {
       "epoch": 3.34,
-      "grad_norm": 0.1655016839504242,
+      "grad_norm": 0.16753199696540833,
       "learning_rate": 0.00023999999999999998,
-      "loss": 1.6018,
+      "loss": 1.5992,
       "step": 80
     },
     {
       "epoch": 3.76,
-      "grad_norm": 0.10938003659248352,
+      "grad_norm": 0.11089170724153519,
       "learning_rate": 0.00027,
-      "loss": 1.4726,
+      "loss": 1.4703,
       "step": 90
     },
     {
       "epoch": 4.18,
-      "grad_norm": 0.09813433140516281,
+      "grad_norm": 0.08356910198926926,
       "learning_rate": 0.0003,
-      "loss": 1.4336,
+      "loss": 1.4324,
       "step": 100
     }
   ],
   "logging_steps": 10,
-  "max_steps": 300,
+  "max_steps": 250,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 14,
+  "num_train_epochs": 11,
   "save_steps": 100,
   "total_flos": 1.863006384782131e+16,
   "train_batch_size": 4,

checkpoint-100/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e101655a2c30ed323838269a1b44a8d1f49e703e9180438d91b23c9fd7ee9379
+oid sha256:f37336d61cdddd86a38ff87d00b592ca42a595577f8ec34bb99a3ac69a0ed524
 size 4960