Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "down_proj",
     "up_proj",
-    "gate_proj",
-    "o_proj",
     "k_proj",
-    "v_proj",
-    "down_proj",
-    "q_proj"
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_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 sha256:2c69fee6afa137794740aa57fd5b9d59026bda47334aab83aad8e37c93470ef8
+oid sha256:a755e1d0f1557988bd0880ff24428bb3a31be51f774e6ccb3e0d7a668a6e3c04
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d930a18e9cff8d959e1a819111286e23e570eef0ce394fac0a0a5b86dc0ec77
+oid sha256:721d5eeecd9ca8691fe3713444d1af10d2b3ced4b3adc2b6e8a62f56ca184bed
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a558901d5df150dd0cdb5c060b8698cb43e908d605d145d79fdaf4961b201b36
+oid sha256:badd5b37bc59ed340e5cf0ea08f8cb665ed44eee63ba2c43b29ca2ff05a28c64
 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": 0.00013633729847643068,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0017723848801935989,
+  "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": 0.00013633729847643068,
       "eval_loss": 1.9493560791015625,
-      "eval_runtime": 106.0469,
-      "eval_samples_per_second": 29.129,
-      "eval_steps_per_second": 14.569,
+      "eval_runtime": 105.7257,
+      "eval_samples_per_second": 29.217,
+      "eval_steps_per_second": 14.613,
       "step": 1
+    },
+    {
+      "epoch": 0.0006816864923821534,
+      "grad_norm": 0.7078530788421631,
+      "learning_rate": 5e-05,
+      "loss": 1.9136,
+      "step": 5
+    },
+    {
+      "epoch": 0.0013633729847643068,
+      "grad_norm": 0.6613458395004272,
+      "learning_rate": 0.0001,
+      "loss": 1.8295,
+      "step": 10
+    },
+    {
+      "epoch": 0.0013633729847643068,
+      "eval_loss": 1.932807445526123,
+      "eval_runtime": 106.4571,
+      "eval_samples_per_second": 29.016,
+      "eval_steps_per_second": 14.513,
+      "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": 36081827315712.0,
+  "total_flos": 547241047621632.0,
   "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:ccaf5ef8c32a44ec6114d32e92abe2fde6f87d0749296f2ee82b423f6d0df089
+oid sha256:a9b8104735c3061c95fa77023270e4ca9f0b8cbf83f5cdb5d352a8bcda9418ae
 size 6776