Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "o_proj",
     "k_proj",
-    "q_proj",
     "gate_proj",
     "down_proj",
+    "q_proj",
+    "v_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc2c78a33fb9171f48a125f3231ce82854656c3ed95aa26fc7b04fd6140d480a
+oid sha256:9eec26cd0c921fc9e9c8f092b29801c7bd2c054c7b6e26a690bbf06da8f21987
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:baa04099b7363a9d81d97ee4becda4a344e4341990451342d779b3375b4e03e8
+oid sha256:245ae9cc3955b089056be740e8d79b18f6d9bc333e017703bf22ea8aed542f62
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e97a7c0e9f50406794ef917e97b861cbf13a749af9dddcb140b22484d48b48ba
+oid sha256:7d41e780f6f8db2d84292a4579c83fc105cfc0f4ebc331ae11cd9a51338da323
 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": 3.103830903292389e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0004034980174280105,
+  "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": 3.103830903292389e-05,
       "eval_loss": 3.7120916843414307,
-      "eval_runtime": 1348.7793,
-      "eval_samples_per_second": 10.058,
-      "eval_steps_per_second": 5.029,
+      "eval_runtime": 1355.8503,
+      "eval_samples_per_second": 10.006,
+      "eval_steps_per_second": 5.003,
       "step": 1
+    },
+    {
+      "epoch": 0.00015519154516461942,
+      "grad_norm": 2.1552507877349854,
+      "learning_rate": 5e-05,
+      "loss": 3.9595,
+      "step": 5
+    },
+    {
+      "epoch": 0.00031038309032923884,
+      "grad_norm": 3.6430537700653076,
+      "learning_rate": 0.0001,
+      "loss": 3.5018,
+      "step": 10
+    },
+    {
+      "epoch": 0.00031038309032923884,
+      "eval_loss": 3.1252193450927734,
+      "eval_runtime": 1356.105,
+      "eval_samples_per_second": 10.004,
+      "eval_steps_per_second": 5.002,
+      "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": 325749848408064.0,
+  "total_flos": 4071873105100800.0,
   "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 sha256:2d12e809b3426e2b7083d14bd96b3e6f95a6bddcb4ba14c4ed81726a6a013a3b
+oid sha256:af0fc664b0f78b5edce403061af19e752e893c93796aa5a2da8ae2299e61a712
 size 6776