Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "k_proj",
-    "down_proj",
-    "o_proj",
+    "up_proj",
     "q_proj",
+    "down_proj",
+    "k_proj",
+    "v_proj",
     "gate_proj",
-    "up_proj"
+    "o_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:fe4977d4a11b0966c486b49a296ccb33b4de9145a716a6e8b5241a42a5f5fda3
+oid sha256:fe70676dabcf9334d4ec359e264daed9fc295c88f0adf72c08e5020ba768954a
 size 608249904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1e23a87f79ac180c0686d5352bc24c648c1c540d5fbc0e378065a911c89afd8
+oid sha256:d6e0891b60672bfd7e28970519d5cb75d00f86c37ed69fe8372f7df4c9b29329
 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

@@ -1,27 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0001271860095389507,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0016534181240063592,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0001271860095389507,
-      "eval_loss": 0.9849432706832886,
-      "eval_runtime": 593.5016,
-      "eval_samples_per_second": 5.579,
-      "eval_steps_per_second": 2.79,
+      "eval_loss": 0.9393907189369202,
+      "eval_runtime": 593.7044,
+      "eval_samples_per_second": 5.577,
+      "eval_steps_per_second": 2.789,
       "step": 1
+    },
+    {
+      "epoch": 0.0006359300476947536,
+      "grad_norm": 1.0778148174285889,
+      "learning_rate": 5e-05,
+      "loss": 0.9545,
+      "step": 5
+    },
+    {
+      "epoch": 0.0012718600953895071,
+      "grad_norm": 1.1839332580566406,
+      "learning_rate": 0.0001,
+      "loss": 0.7874,
+      "step": 10
+    },
+    {
+      "epoch": 0.0012718600953895071,
+      "eval_loss": 0.6840765476226807,
+      "eval_runtime": 607.8025,
+      "eval_samples_per_second": 5.447,
+      "eval_steps_per_second": 2.725,
+      "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": 350534158516224.0,
+  "total_flos": 4556944060710912.0,
   "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 sha256:32ba51e423552cc7a3bcfff2060e9dfb179e45655b931a9d87a4bc9796133833
+oid sha256:074564c0050d5ebba844b5aea47ce4d1dd80dfdbc256a6f06ef599853caa1b7f
 size 6776