Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -22,11 +22,11 @@
   "target_modules": [
     "up_proj",
     "k_proj",
+    "gate_proj",
     "down_proj",
-    "q_proj",
-    "o_proj",
     "v_proj",
-    "gate_proj"
+    "q_proj",
+    "o_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 sha256:80f8dd0ca9dcd881a96f19dc688eda70dd7f3a4c385cc65d8e6dd0793426083a
+oid sha256:cce4411ef2d6eb097fbe6ea8762361cf2ca7f5927b5c2643f4bd742383b94cb9
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b6de4428d8a1002e9f1a9a352b0e1b686f90a04cf27f85eccd6cc46c9921084
+oid sha256:f3af1a16b061b7f5b92de242f0ba33b08816aad4f6e949c0b8772ac9dafb2dcb
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac701cc4f550f3468031bdf90d2764e5851e5c9ce905de7dda69e4883f6b7133
+oid sha256:9ee1305fcd17562353003de733920dc2a7a89f52a6271daebed80f894e9a5913
 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": 0.001238390092879257,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.01609907120743034,
+  "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": 0.001238390092879257,
       "eval_loss": NaN,
-      "eval_runtime": 24.1716,
-      "eval_samples_per_second": 14.066,
-      "eval_steps_per_second": 7.033,
+      "eval_runtime": 24.0496,
+      "eval_samples_per_second": 14.137,
+      "eval_steps_per_second": 7.069,
       "step": 1
+    },
+    {
+      "epoch": 0.006191950464396285,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.01238390092879257,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.01238390092879257,
+      "eval_loss": NaN,
+      "eval_runtime": 22.9903,
+      "eval_samples_per_second": 14.789,
+      "eval_steps_per_second": 7.394,
+      "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": 160743309705216.0,
+  "total_flos": 2342259655704576.0,
   "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 sha256:5aca1c91699cd99908e0fcc127c24138a83b9d382d9bfff87a8732ff9d6c8a1c
+oid sha256:74948d7aebc301c9b3c6359689d60423b04c150d9b45cf31c1d1542eab9becfb
 size 6776