Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "k_proj",
+    "gate_proj",
+    "down_proj",
     "o_proj",
+    "k_proj",
+    "q_proj",
     "up_proj",
-    "v_proj",
-    "down_proj",
-    "gate_proj"
+    "v_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 sha256:68e888b349c3225de18ae4a20d592195ceaf673901c8dd153b946666cbed5728
+oid sha256:283c9218103b83fa4eb24efb346320014ab9bce9a0c20a41ba705468edd04b45
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5134a65740425d5dcc23123a650efd12f6a8b5baf53fe0e6b4a82b4eff8df7d8
+oid sha256:e76276f1217a05ddc39174905e0d60075a31d9af542b46311d48206d90824a5c
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:638af6f593094a558f5283bf1669c955a044e33851610e2150ab691bd43844c0
+oid sha256:0bc95f8ef66804917a60b19acbb3aaab5647926085d4ddb008103acb36348fb2
 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": 0.0020232675771370764,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.026302478502781994,
+  "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": 0.0020232675771370764,
       "eval_loss": 1.7532789707183838,
-      "eval_runtime": 22.5275,
-      "eval_samples_per_second": 9.278,
-      "eval_steps_per_second": 4.661,
+      "eval_runtime": 22.6911,
+      "eval_samples_per_second": 9.211,
+      "eval_steps_per_second": 4.627,
       "step": 1
+    },
+    {
+      "epoch": 0.010116337885685382,
+      "grad_norm": 2.5933752059936523,
+      "learning_rate": 5e-05,
+      "loss": 1.5813,
+      "step": 5
+    },
+    {
+      "epoch": 0.020232675771370764,
+      "grad_norm": 1.89445161819458,
+      "learning_rate": 0.0001,
+      "loss": 1.1502,
+      "step": 10
+    },
+    {
+      "epoch": 0.020232675771370764,
+      "eval_loss": 0.7085664868354797,
+      "eval_runtime": 23.9995,
+      "eval_samples_per_second": 8.709,
+      "eval_steps_per_second": 4.375,
+      "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": 288369011589120.0,
+  "total_flos": 3295645846732800.0,
   "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 sha256:16da6857c46cc983a8b31adc3473f7bbe8ac906f68fa198e036a5ab1da69942b
+oid sha256:81b2c35e5c215aaca5ac5a2addff8a3af7fa440e77dffb271c07c5ad20770c34
 size 6776