Training in progress, step 100, checkpoint

checkpoint-100/README.md

@@ -202,5 +202,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ### Framework versions
 
 - PEFT 0.9.0
-- 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:fb59f848c88a5b1b5cab3242d4c331dc775e603ff7609a07f42436d4de84a99b
+oid sha256:c1a1118bbcbdab8294afd7683e4ef0e3a54d94d1b86e8087686f7e2822a75195
 size 9443384

checkpoint-100/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57188196c44f6f175fe4a57663b3d96a4c9aa25b1a71e5c17d4937f7a159ec03
+oid sha256:5445f987e06033ca8180dcacac7106c163198139c090c3fb6a5c5a123d3e3751
 size 18914450

checkpoint-100/trainer_state.json

@@ -10,79 +10,79 @@
   "log_history": [
     {
       "epoch": 0.42,
-      "grad_norm": 0.18964600563049316,
+      "grad_norm": 0.18415939807891846,
       "learning_rate": 2.9999999999999997e-05,
-      "loss": 3.866,
+      "loss": 3.8654,
       "step": 10
     },
     {
       "epoch": 0.84,
-      "grad_norm": 0.240617036819458,
+      "grad_norm": 0.23708771169185638,
       "learning_rate": 5.9999999999999995e-05,
-      "loss": 3.8202,
+      "loss": 3.8218,
       "step": 20
     },
     {
       "epoch": 1.25,
-      "grad_norm": 0.32437172532081604,
+      "grad_norm": 0.3239809572696686,
       "learning_rate": 8.999999999999999e-05,
-      "loss": 3.7224,
+      "loss": 3.725,
       "step": 30
     },
     {
       "epoch": 1.67,
-      "grad_norm": 0.39009416103363037,
+      "grad_norm": 0.38910844922065735,
       "learning_rate": 0.00011999999999999999,
-      "loss": 3.4906,
+      "loss": 3.4953,
       "step": 40
     },
     {
       "epoch": 2.09,
-      "grad_norm": 0.5346343517303467,
+      "grad_norm": 0.520912230014801,
       "learning_rate": 0.00015,
-      "loss": 3.0915,
+      "loss": 3.0984,
       "step": 50
     },
     {
       "epoch": 2.51,
-      "grad_norm": 0.6114345788955688,
+      "grad_norm": 0.6063631772994995,
       "learning_rate": 0.00017999999999999998,
-      "loss": 2.5238,
+      "loss": 2.5316,
       "step": 60
     },
     {
       "epoch": 2.92,
-      "grad_norm": 0.4761127531528473,
+      "grad_norm": 0.4615532457828522,
       "learning_rate": 0.00020999999999999998,
-      "loss": 1.8914,
+      "loss": 1.8987,
       "step": 70
     },
     {
       "epoch": 3.34,
-      "grad_norm": 0.16753199696540833,
+      "grad_norm": 0.16907210648059845,
       "learning_rate": 0.00023999999999999998,
-      "loss": 1.5992,
+      "loss": 1.6041,
       "step": 80
     },
     {
       "epoch": 3.76,
-      "grad_norm": 0.11089170724153519,
+      "grad_norm": 0.11257671564817429,
       "learning_rate": 0.00027,
-      "loss": 1.4703,
+      "loss": 1.4732,
       "step": 90
     },
     {
       "epoch": 4.18,
-      "grad_norm": 0.08356910198926926,
+      "grad_norm": 0.08190377801656723,
       "learning_rate": 0.0003,
-      "loss": 1.4324,
+      "loss": 1.4341,
       "step": 100
     }
   ],
   "logging_steps": 10,
-  "max_steps": 250,
+  "max_steps": 175,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 11,
+  "num_train_epochs": 8,
   "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:f37336d61cdddd86a38ff87d00b592ca42a595577f8ec34bb99a3ac69a0ed524
+oid sha256:79f806349f0bb61a00c2d540daba3c569079d7140776f830f475a964ef346330
 size 4960