Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "up_proj",
-    "o_proj",
-    "down_proj",
     "k_proj",
+    "o_proj",
+    "v_proj",
     "q_proj",
-    "gate_proj"
+    "up_proj",
+    "gate_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 sha256:2623b7716548cd9ed1819c66568d7dd26385f060c20cc79f5fff6ce0b8148c2f
+oid sha256:413e3615da725e165aeece201e6ef8eda8159d0f4ab03bd6b4f9f0b2238f4900
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07b54a3945b59c43e9556d55db57970d5279e34259e2c231027869979e8e254d
+oid sha256:2b50eb639738e235d33e441a4411dc2d7a05a3f7ccae9599c28f40a11664aa24
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
+oid sha256:11ba2173c152f94714fb9f1e41fd4ca1e5e7fe0bc567e9b87b39fd86183b2acc
 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": 7.541620317125135e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0009804106412262675,
+  "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": 7.541620317125135e-05,
       "eval_loss": 2.0435900688171387,
-      "eval_runtime": 664.6372,
-      "eval_samples_per_second": 8.402,
-      "eval_steps_per_second": 4.201,
+      "eval_runtime": 665.4247,
+      "eval_samples_per_second": 8.392,
+      "eval_steps_per_second": 4.196,
       "step": 1
+    },
+    {
+      "epoch": 0.0003770810158562567,
+      "grad_norm": 2.116191864013672,
+      "learning_rate": 5e-05,
+      "loss": 2.0936,
+      "step": 5
+    },
+    {
+      "epoch": 0.0007541620317125134,
+      "grad_norm": 1.9126191139221191,
+      "learning_rate": 0.0001,
+      "loss": 1.8052,
+      "step": 10
+    },
+    {
+      "epoch": 0.0007541620317125134,
+      "eval_loss": 1.2857778072357178,
+      "eval_runtime": 669.1514,
+      "eval_samples_per_second": 8.345,
+      "eval_steps_per_second": 4.172,
+      "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": 369912849629184.0,
+  "total_flos": 4577671514161152.0,
   "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:d6e431437190c85bbf0121b3ac42b51c1a6a5c51746564d480e1ed54efc40e61
+oid sha256:41f95d7d211663de3a6cbb869c3e4b1b34984af1e4125b5a95c029829bf37fd4
 size 6776