Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "k_proj",
     "q_proj",
-    "gate_proj",
-    "up_proj",
     "v_proj",
+    "down_proj",
     "o_proj",
-    "down_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 sha256:7951358be01b42cc624c370e22a666e89b7fc9d7e5c705d3e95e176c4fcabd90
+oid sha256:252ed57a9c24d44d315f17e266c3262466702d18620587d64737897ce78f6978
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e86ca44a6778891c2223beb3f2ff54f124027d831bb24c268664f664dd234d6b
+oid sha256:c29f8530ed79bd06b84736c6c2b4be4f81afada2eb8bf190832ba7008011f594
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d20938fdf180abcaa5fb4311a1433c95811c7ad7a2a935c0fa2fec209987e03
+oid sha256:c43d204983049079e13404efd288d14125bb2ca2e7a98897797a6812d6e7b7a3
 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": 4.349953781741069e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.000565493991626339,
+  "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": 4.349953781741069e-05,
       "eval_loss": 0.7465932369232178,
-      "eval_runtime": 324.6146,
-      "eval_samples_per_second": 29.82,
-      "eval_steps_per_second": 14.91,
+      "eval_runtime": 324.7203,
+      "eval_samples_per_second": 29.81,
+      "eval_steps_per_second": 14.905,
       "step": 1
+    },
+    {
+      "epoch": 0.00021749768908705346,
+      "grad_norm": 0.3783012926578522,
+      "learning_rate": 5e-05,
+      "loss": 0.7311,
+      "step": 5
+    },
+    {
+      "epoch": 0.0004349953781741069,
+      "grad_norm": 0.41249537467956543,
+      "learning_rate": 0.0001,
+      "loss": 0.7084,
+      "step": 10
+    },
+    {
+      "epoch": 0.0004349953781741069,
+      "eval_loss": 0.7224622368812561,
+      "eval_runtime": 334.342,
+      "eval_samples_per_second": 28.952,
+      "eval_steps_per_second": 14.476,
+      "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": 51158395650048.0,
+  "total_flos": 652269544538112.0,
   "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:f7b5d2222cca03a15918486f37b886114571a6463a33478e4b0f01a88e4e5c66
+oid sha256:7a46ee7909a1d190f3c89529f7668e5a1de096059b3f49a8989a406d84712d82
 size 6776