Training in progress, step 20, checkpoint

last-checkpoint/adapter_config.json

@@ -20,7 +20,6 @@
   "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 sha256:35d4dacf6ca7235a630206be47c57307ec59d042c586237f5ee3685830f353ca
-size 12803224
+oid sha256:8772894d12f78b8fc6af826e5276f655e373807dd07b22aed0543e66cbef5292
+size 4725640

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5205fd6548534ff72becdbb489dd70821e6049f447e4343f8253d3626b2c27dd
-size 6472698
+oid sha256:af22a61da37ba89fb906663ab84e4be41468f2ac1684b76b88311f42c59c536f
+size 2423738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db81002b0a79810ae6ea06692dfc424400086dbd3dd457addd6b3b0966398690
+oid sha256:ad35aae38bdb55d17557911fb95298bbafabf6ae7c3c9106d36788ba438d412a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e578c8608f70526ffbfa08fcf305a3b9476a76b7d3e79b963ae3bc487a64238
+oid sha256:bd9af3bd0fffafb125626179d8875b2db50ea3974e8522bd88f257772b2ca911
 size 1064

last-checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17a208233d2ee8d8c83b23bc214df737c44806a1919f444e89b31e586cd956ba
-size 14500471
+oid sha256:3fe0e32d5e685050c0787e7fa781db4fc73bddea1b6da68659010dedc06005b3
+size 14500638

last-checkpoint/trainer_state.json

@@ -1,54 +1,19 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 9.339030141719783e-05,
+  "epoch": 3.1130100472399276e-05,
   "eval_steps": 500,
-  "global_step": 120,
+  "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": Infinity,
-      "learning_rate": 2.0000000000000003e-06,
-      "loss": 3.747,
+      "grad_norm": 1.776742935180664,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 3.5415,
       "step": 20
-    },
-    {
-      "epoch": 0.0,
-      "grad_norm": 90.38651275634766,
-      "learning_rate": 5.333333333333334e-06,
-      "loss": 3.7962,
-      "step": 40
-    },
-    {
-      "epoch": 0.0,
-      "grad_norm": 108.40189361572266,
-      "learning_rate": 8.666666666666668e-06,
-      "loss": 3.5164,
-      "step": 60
-    },
-    {
-      "epoch": 0.0,
-      "grad_norm": 109.34711456298828,
-      "learning_rate": 1.2e-05,
-      "loss": 4.0846,
-      "step": 80
-    },
-    {
-      "epoch": 0.0,
-      "grad_norm": 75.66071319580078,
-      "learning_rate": 1.5333333333333334e-05,
-      "loss": 3.594,
-      "step": 100
-    },
-    {
-      "epoch": 0.0,
-      "grad_norm": 17.74490737915039,
-      "learning_rate": 1.866666666666667e-05,
-      "loss": 3.6379,
-      "step": 120
     }
   ],
   "logging_steps": 20,
@@ -56,8 +21,8 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 20,
-  "total_flos": 511252181299200.0,
-  "train_batch_size": 1,
+  "total_flos": 184619525971968.0,
+  "train_batch_size": 2,
   "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:c205a7e969e6f1dcf3b778c2a6e73ae9c14e499d2d6f811d14482423148ebe9a
+oid sha256:da5d41afb0ddac16c18350b7a14dbb4a1e14941c08946cda5f16f71c0aaf525c
 size 4984