Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "up_proj",
-    "gate_proj",
-    "v_proj",
     "q_proj",
+    "v_proj",
     "o_proj",
-    "k_proj"
+    "down_proj",
+    "k_proj",
+    "gate_proj",
+    "up_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 sha256:18826326be4c640520938886a55b328ea1ea12b2c46b0d17723a543509e340e1
+oid sha256:bfab4842945e24a6f52b862f7e2ad6a26d59d2bad5ad50db250f03ded2feb7fa
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a44323f32a69462cccd5dd5ee3dd0cc4960a3de4f99de7117c22b0184df54dc
+oid sha256:858098554e0416f86144a06ee521868829605dc7addb789a5e64caa48183effe
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:3f0082b9ee265cb0c6910d3944f6a738794d996da2e7f7ac5ed1f97dde094437
 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": 0.0021152829190904283,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.02749867794817557,
+  "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": 0.0021152829190904283,
       "eval_loss": 0.8276494741439819,
-      "eval_runtime": 16.2103,
-      "eval_samples_per_second": 12.276,
-      "eval_steps_per_second": 6.169,
+      "eval_runtime": 16.2246,
+      "eval_samples_per_second": 12.265,
+      "eval_steps_per_second": 6.163,
       "step": 1
+    },
+    {
+      "epoch": 0.010576414595452142,
+      "grad_norm": 63.81797790527344,
+      "learning_rate": 5e-05,
+      "loss": 4.1889,
+      "step": 5
+    },
+    {
+      "epoch": 0.021152829190904283,
+      "grad_norm": 21.4931697845459,
+      "learning_rate": 0.0001,
+      "loss": 0.841,
+      "step": 10
+    },
+    {
+      "epoch": 0.021152829190904283,
+      "eval_loss": 0.2516094148159027,
+      "eval_runtime": 16.9953,
+      "eval_samples_per_second": 11.709,
+      "eval_steps_per_second": 5.884,
+      "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": 175344288006144.0,
+  "total_flos": 2410983960084480.0,
   "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:b464b350f0e5fa5b202b4b418389890b46d44d3f17a3bad62d1a8afbcf949c2c
+oid sha256:2fcc16a2714ef911ab1cdf2614609d610dd8e2dc32ca24d75143b11bc61d55b9
 size 6776