Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
+    "down_proj",
     "o_proj",
-    "v_proj",
     "q_proj",
-    "down_proj",
+    "up_proj",
     "k_proj",
-    "up_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:bba3c0d143ebcc35063b471bec424dacd4302886c00f411e6f02ef7dc6ceae14
+oid sha256:edf7d87fcdca88aa1b6fa535ef91797d6811da6bfa87a0d56cd65927232bebec
 size 15182728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a40967553465aa984f663b0834ed484cc62f8127c7fc2b943791f130432834a2
+oid sha256:eac0bfacfa7ddc249bea2ad2a11b14426a04d3792ee7d98968ffb85c32d74b11
 size 8075796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04207184997b90437a66d21dbe3ed05249a2532734150985c211787523de76d1
+oid sha256:fd0b94e8a1de35876dfa0fd2f2f412500e043fd76773f3755c7f6e1a13b0bcbd
 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": 0.013289036544850499,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.17275747508305647,
+  "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": 0.013289036544850499,
       "eval_loss": 2.996713399887085,
-      "eval_runtime": 1.7769,
-      "eval_samples_per_second": 18.009,
-      "eval_steps_per_second": 9.004,
+      "eval_runtime": 1.7935,
+      "eval_samples_per_second": 17.842,
+      "eval_steps_per_second": 8.921,
       "step": 1
+    },
+    {
+      "epoch": 0.0664451827242525,
+      "grad_norm": 3.3227691650390625,
+      "learning_rate": 5e-05,
+      "loss": 2.7445,
+      "step": 5
+    },
+    {
+      "epoch": 0.132890365448505,
+      "grad_norm": 2.976918935775757,
+      "learning_rate": 0.0001,
+      "loss": 2.4895,
+      "step": 10
+    },
+    {
+      "epoch": 0.132890365448505,
+      "eval_loss": 2.711103916168213,
+      "eval_runtime": 1.1402,
+      "eval_samples_per_second": 28.066,
+      "eval_steps_per_second": 14.033,
+      "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": 7672380260352.0,
+  "total_flos": 99740943384576.0,
   "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:f41339b35777a9eb45349e6c9dc463018481cf422ea8aec0367bb10345c5f579
+oid sha256:12d96d744688bfbfa7336eb0d24d7e6abb29b9d3d1ee2f0ff8ac506ba4dc9e6f
 size 6776