Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
     "down_proj",
-    "k_proj",
-    "up_proj",
-    "q_proj",
     "gate_proj",
-    "v_proj"
+    "o_proj",
+    "up_proj",
+    "k_proj",
+    "v_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 sha256:5dead7d8006694706e3f1df4c6bc5c87136a6203fd7432ad06901df3be58e88b
+oid sha256:febcd29439a7c2494848a7d092474a43a0e686ccda9ff7740de69045adae660f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d27ab6bdd241f5381e2e26de09e9379af7163918f95dd780478672128c0d75a
+oid sha256:1941d67004639421b4a23b61c3e36738cc1983b652d551235e4700e1616a3491
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
+oid sha256:a5cba764fcb0e7f18b6d06759624dccc13afd567f3245791b3de96f9fcfce3c5
 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": 0.0033003300330033004,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0429042904290429,
+  "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": 0.0033003300330033004,
       "eval_loss": 0.7488853931427002,
-      "eval_runtime": 19.7223,
-      "eval_samples_per_second": 6.49,
-      "eval_steps_per_second": 3.245,
+      "eval_runtime": 19.7022,
+      "eval_samples_per_second": 6.497,
+      "eval_steps_per_second": 3.248,
       "step": 1
+    },
+    {
+      "epoch": 0.0165016501650165,
+      "grad_norm": 3.9368174076080322,
+      "learning_rate": 5e-05,
+      "loss": 2.8219,
+      "step": 5
+    },
+    {
+      "epoch": 0.033003300330033,
+      "grad_norm": 4.35306978225708,
+      "learning_rate": 0.0001,
+      "loss": 2.5563,
+      "step": 10
+    },
+    {
+      "epoch": 0.033003300330033,
+      "eval_loss": 0.6635968089103699,
+      "eval_runtime": 19.9265,
+      "eval_samples_per_second": 6.424,
+      "eval_steps_per_second": 3.212,
+      "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": 350533957189632.0,
+  "total_flos": 4556941443465216.0,
   "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:caf9da4d5bdcc07024718cb2e42124b035eae23a2b4f6ac4b89d6bce843ae800
+oid sha256:15215836ea161afae89b3b16faffcdf0bd67fb3d20845cd4cdc8fb943a1df126
 size 6776