Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "k_proj",
-    "o_proj",
+    "down_proj",
     "up_proj",
-    "q_proj",
+    "o_proj",
+    "gate_proj",
     "v_proj",
-    "down_proj"
+    "k_proj",
+    "q_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 sha256:759b328b324b8575f6efec20b4a12a364aaf9a096a35326fd8a748014e8fc99a
+oid sha256:8b2cb53ce4097ebb1fc7562064683c252c3d9869d99a6bbdf3a2bab404f670f2
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65711308a7d9768407f814a848a1424b1629e4fc8db7f8f82d8578ebf197565e
+oid sha256:70be69df5bf6f98001193ad48e3be216ee54a8b7d29475c032de96a6f9ac5361
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c6aec7ebe1cf0946dfc9ec4cb3dac1a717cf177a62534e9c05548ccfc197a8
+oid sha256:1355c639766d3952c3be512dc3398093c55d179396a88b0f2916aee9460092db
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0027710426047800486,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.03602355386214063,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.0027710426047800486,
       "eval_loss": 4.355137825012207,
-      "eval_runtime": 58.8996,
-      "eval_samples_per_second": 41.274,
-      "eval_steps_per_second": 5.161,
+      "eval_runtime": 58.9712,
+      "eval_samples_per_second": 41.223,
+      "eval_steps_per_second": 5.155,
       "step": 1
+    },
+    {
+      "epoch": 0.027710426047800486,
+      "grad_norm": 1.860477089881897,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 3.6053,
+      "step": 10
+    },
+    {
+      "epoch": 0.027710426047800486,
+      "eval_loss": 3.0410964488983154,
+      "eval_runtime": 59.162,
+      "eval_samples_per_second": 41.091,
+      "eval_steps_per_second": 5.138,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 818534330400768.0,
+  "total_flos": 1.0257258327834624e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73ebd60a924bc03adf3f6c0f2abfda672f71358d03739a4f429c14bf946b06d1
+oid sha256:bd00cdbdc01527daa05e8a43ea4ed49675ffae206215f528f1cbdb2a63f63925
 size 6776