Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,13 +21,13 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "q_proj",
-    "gate",
+    "k_proj",
     "o_proj",
     "w2",
-    "k_proj",
-    "w1",
-    "w3"
+    "w3",
+    "gate",
+    "q_proj",
+    "w1"
   ],
   "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:e3a08338a36f574d0fef4254afe8af1db3ea2ffd6722e79bb719605d22095dde
+oid sha256:a280596039ff6cde198cc161153f5788ab23c934c0acb319309a691ac65a8af2
 size 7586384

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a70333b765ade3f0fa861aeefe44b9c4fc06b289c56b5f7379e257dd23e5a20
+oid sha256:e91d47a69ae003b4db840302a1e6d2c09a5003466af613248ec3e50a3ec8c0a4
 size 4027642

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a28dd489e202930a3d7490ffd2abcba3e66379760692341ce0b1a4f1cb17d34
+oid sha256:0af930d700afde228120280273798d5498f92ed1ea9564a37b92fc5b6af6c2d7
 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": 0.0004018485031143259,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.005224030540486237,
+  "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": 0.0004018485031143259,
       "eval_loss": NaN,
-      "eval_runtime": 11.9971,
-      "eval_samples_per_second": 87.355,
-      "eval_steps_per_second": 43.677,
+      "eval_runtime": 12.1629,
+      "eval_samples_per_second": 86.164,
+      "eval_steps_per_second": 43.082,
       "step": 1
+    },
+    {
+      "epoch": 0.0020092425155716293,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.004018485031143259,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.004018485031143259,
+      "eval_loss": NaN,
+      "eval_runtime": 11.3335,
+      "eval_samples_per_second": 92.469,
+      "eval_steps_per_second": 46.235,
+      "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": 9293410861056.0,
+  "total_flos": 96916998979584.0,
   "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 sha256:632dcb0a81919101fc6a96f0be19df24bc016c085c5719d6e4f59a459e7897ae
+oid sha256:ac741bcbf7114aae3320a4e32272c1e2d17b9dd57b5bd7daa4651f6387700fb1
 size 6776