Training in progress, epoch 5, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "q_proj",
     "gate_proj",
-    "down_proj",
+    "v_proj",
     "up_proj",
-    "k_proj",
-    "v_proj"
+    "q_proj",
+    "o_proj",
+    "down_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM",
   "use_dora": false,

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5f81144f3abdd4b9336dbf567cc518c743891535bce46c41c871859fd53e8f8
+oid sha256:7926c258e829a349e1860bc71ad7e40234ea1357bc12a31ab05106033a7fde81
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61278bb066bed6ba2339b6e6be9da2b0fa64362a1a63346a64441adfc35c0057
+oid sha256:7c2624a406cf87a3df2fc167c2f9e04e4aa15bc3e527aa9a9e04e363de35c74c
 size 60252034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:632aa854a40432dba8b1338e10c00d9f505aa22bf415065d94fa1822b713261c
+oid sha256:0a842fd724fcba5d7d6d56984b8336769268e12a26c2bba9cb1ca5bf48a77fef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:790ecab4184234dd697049c7d153605f6c55677d2b29e88ccca0b9879b7a6700
+oid sha256:db7f9d155f11eec6bdf3d43c5ca6f5f6cf43cf75f6656a15f9fe0a28724699a8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.989939637826962,
+  "epoch": 5.997987927565393,
   "eval_steps": 500,
-  "global_step": 1240,
+  "global_step": 1488,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -91,12 +91,26 @@
       "learning_rate": 0.0002,
       "loss": 0.4705,
       "step": 1200
+    },
+    {
+      "epoch": 5.241448692152917,
+      "grad_norm": 0.3148166239261627,
+      "learning_rate": 0.0002,
+      "loss": 0.4095,
+      "step": 1300
+    },
+    {
+      "epoch": 5.6438631790744465,
+      "grad_norm": 0.34497711062431335,
+      "learning_rate": 0.0002,
+      "loss": 0.4081,
+      "step": 1400
     }
   ],
   "logging_steps": 100,
-  "max_steps": 1240,
+  "max_steps": 2480,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 10,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -105,12 +119,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.8688747298095104e+17,
+  "total_flos": 2.243403254291497e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a8ea776e4e929e94b51f1d9fa6012981ab844ca4b441d263a8517c0e8ca0c30
+oid sha256:7714ea7b857663fe52f58f00898a1b407ca1ca4c773b45c499ca49bdb9e8e40d
 size 5432