Training in progress, step 20, checkpoint

last-checkpoint/adapter_config.json

@@ -20,6 +20,7 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "word_embeddings",
     "query_key_value"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82a235dcf79ae46d5d74eb2c277b2a88d917b4d0fe58e9c0483a1c6ef77bd3d0
-size 4725640
+oid sha256:5b717fc47fc6ca0f43cd64801c3f49ad862250ba32a036c80639250fcb7e18cd
+size 12803224

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cafd0997844310ce6894d5bb35d3a49ea4d5dabe1e810d400c91685f3a3abb0
-size 2423738
+oid sha256:5295139bb5ea53c3cb17ab006d58608d0220293d8748ba7d455a435ffff93806
+size 6472698

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac4bf1426427b0e2a018f4b1750c36bb7e3e5ebba9e8a477845308163b2a7fb5
+oid sha256:df81fc9d078b3589f3e74ce10344ae2b9ba2f47edb0c855a81de1c3ca1991673
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba9088914de78dc99d767c21058d110a360c0bb50564c9ed4886490601d97b6d
+oid sha256:1fcf032e6256b2cd4d659b09985077ab1961c6c13c26975c094dd36ab0c1ff74
 size 1064

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12cb93e09fed5cf770f42b645926821cd300de44a57db3ca5e284142571864c2
-size 14500638
+oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
+size 14500471

last-checkpoint/trainer_state.json

@@ -1,26 +1,19 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005451076587626056,
+  "epoch": 0.002725538293813028,
   "eval_steps": 500,
-  "global_step": 40,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0,
-      "grad_norm": 2.1512844562530518,
-      "learning_rate": 1.5833333333333336e-06,
-      "loss": 4.4875,
+      "grad_norm": 36.511024475097656,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 4.6323,
       "step": 20
-    },
-    {
-      "epoch": 0.01,
-      "grad_norm": 2.2963316440582275,
-      "learning_rate": 3.2500000000000002e-06,
-      "loss": 4.1113,
-      "step": 40
     }
   ],
   "logging_steps": 20,
@@ -28,7 +21,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 20,
-  "total_flos": 334860439191552.0,
+  "total_flos": 167893794816000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2144efe638cdc54910486057ddff9e1420f8f369906d08c03aeb6ed693951c8e
+oid sha256:2e025a4e68c1d22e7dc695a50138fa18070a7258d30cfd192237c2cea9e5c360
 size 4984