Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
     "o_proj",
-    "k_proj",
-    "down_proj",
+    "gate_proj",
     "up_proj",
-    "v_proj"
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "q_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:abd188195b64e0e201ee8b91c8114ebfb5483b482576facdeb059e57f9482009
+oid sha256:1c4e37ddb84c5302ee8d29df171b0943807a678df869261e80e5ef854ed5ca4f
 size 22573704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3707fc9e96157e8c76388a43b3d2b0a83ba25f758a5e877b4f6306eb959c46c
+oid sha256:b07573c569bd3235043e6c70c48c19e0eca0ec2891a235c48ca3b7f577132000
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e96084db0d88b3f6f054fd8e1ee389d8068f68911086b40d9534c6441e1738ec
+oid sha256:38c6291480501dedfdd188a2dde82d0e9dc6215c3786cd8b8b61e96d2ad44a53
 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": 0.00035622050048980317,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.004630866506367442,
+  "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": 0.00035622050048980317,
       "eval_loss": 2.1373324394226074,
-      "eval_runtime": 34.1619,
-      "eval_samples_per_second": 34.6,
-      "eval_steps_per_second": 17.3,
+      "eval_runtime": 34.2205,
+      "eval_samples_per_second": 34.541,
+      "eval_steps_per_second": 17.27,
       "step": 1
+    },
+    {
+      "epoch": 0.0017811025024490159,
+      "grad_norm": 0.5844210386276245,
+      "learning_rate": 5e-05,
+      "loss": 1.476,
+      "step": 5
+    },
+    {
+      "epoch": 0.0035622050048980318,
+      "grad_norm": 0.7585830688476562,
+      "learning_rate": 0.0001,
+      "loss": 1.4674,
+      "step": 10
+    },
+    {
+      "epoch": 0.0035622050048980318,
+      "eval_loss": 2.102182388305664,
+      "eval_runtime": 34.1546,
+      "eval_samples_per_second": 34.607,
+      "eval_steps_per_second": 17.304,
+      "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": 24054551543808.0,
+  "total_flos": 348790997385216.0,
   "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:dca1389008b39d8aa4e1457d4125df6aeec30b5f6dbf27be49dcacaabbc3926f
+oid sha256:efeb6a3d28bc132eeee0d6534b19f224e2b8189b5e22aebd86acf4456bfe1081
 size 6776