Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "k_proj",
     "gate_proj",
     "q_proj",
-    "v_proj",
     "o_proj",
-    "up_proj"
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "down_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 sha256:1c7f912949dd5aec990f079f07140081b4fe69c031f1a8244eaf8a39ff5dd359
+oid sha256:263af0d0ecc3dd92bf3572419c7b2b85512ff89dc5bf9cb8283273dea62f255f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43fae12747d64bf07460c3143716a3dfeb27d395a10044887d5dc8635506824d
+oid sha256:580aec9c9570e7496cf594bb0db8a39121196c524ee2fbe796c48ddbb0915c43
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0004033477866290209,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0052435212261772715,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,39 @@
     {
       "epoch": 0.0004033477866290209,
       "eval_loss": 1.4710214138031006,
-      "eval_runtime": 78.4083,
-      "eval_samples_per_second": 13.315,
-      "eval_steps_per_second": 6.657,
+      "eval_runtime": 78.2284,
+      "eval_samples_per_second": 13.346,
+      "eval_steps_per_second": 6.673,
       "step": 1
+    },
+    {
+      "epoch": 0.0020167389331451043,
+      "grad_norm": 27.991483688354492,
+      "learning_rate": 5e-05,
+      "loss": 6.1142,
+      "step": 5
+    },
+    {
+      "epoch": 0.0040334778662902086,
+      "grad_norm": 36.424503326416016,
+      "learning_rate": 0.0001,
+      "loss": 4.5091,
+      "step": 10
+    },
+    {
+      "epoch": 0.0040334778662902086,
+      "eval_loss": 0.7015925645828247,
+      "eval_runtime": 82.5957,
+      "eval_samples_per_second": 12.64,
+      "eval_steps_per_second": 6.32,
+      "step": 10
     }
   ],
   "logging_steps": 5,
-  "max_steps": 1,
+  "max_steps": 50,
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
-  "save_steps": 1,
+  "save_steps": 13,
   "stateful_callbacks": {
     "TrainerControl": {
       "args": {
@@ -29,12 +51,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 175267179921408.0,
+  "total_flos": 2278473338978304.0,
   "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 sha256:5b48c2023cbdc010449c0c539fcb72b9a639d24f1416a6f0e7e8c64773030ce0
+oid sha256:3d14c0c539a5ff29e44abc0ff3e0b381a86b740575f237ab00c676d4948dca1d
 size 6776