Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f95658a4d013f802419368ea1dff55b02efda026073b81c7f27cdfb560556fe
+oid sha256:6991b5160cd4d11ffc03d24b46ff1bfd398b134447cf1d28fe04307c2c01bb7f
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c127f49910178b4a3fe279b0ecaab71af47109933c061fb667432f223756885a
+oid sha256:d58e8e53a80a200c85a727b30dfd81e1023a02a56250e3efdb19ef7598711f21
 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

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00010742869420422194,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0013965730246548852,
+  "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": 0.00010742869420422194,
       "eval_loss": 3.1173388957977295,
-      "eval_runtime": 479.8575,
-      "eval_samples_per_second": 8.169,
+      "eval_runtime": 479.8029,
+      "eval_samples_per_second": 8.17,
       "eval_steps_per_second": 4.085,
       "step": 1
+    },
+    {
+      "epoch": 0.0005371434710211097,
+      "grad_norm": 3.4544060230255127,
+      "learning_rate": 5e-05,
+      "loss": 2.8156,
+      "step": 5
+    },
+    {
+      "epoch": 0.0010742869420422194,
+      "grad_norm": 3.225125551223755,
+      "learning_rate": 0.0001,
+      "loss": 2.5232,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010742869420422194,
+      "eval_loss": 2.313772439956665,
+      "eval_runtime": 482.0841,
+      "eval_samples_per_second": 8.131,
+      "eval_steps_per_second": 4.066,
+      "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": 369919292080128.0,
+  "total_flos": 4808950797041664.0,
   "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 sha256:98b9f23ccd099e45a3cdc30af4204cb1ec0aafbeacb30d52484994a553e7e646
+oid sha256:1c05c438e5c71f215d01c936f9417c0fafc4d07ddfacda06fbf27c317bfd6780
 size 6776