Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "gate_proj",
     "v_proj",
+    "q_proj",
+    "down_proj",
     "o_proj",
+    "gate_proj",
     "k_proj",
-    "down_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c82c73246ade5e6caff3cb7448c4957f93ae29871df7a1131ac815f63162467d
+oid sha256:0b91680c03e645c8f2b94e51a0d04c6b27949a227b8ac0684eed18c4f83a6597
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7a84eb4aeea525b6507d582c8dd8cdb4a2bc866790253105cc42eb36467860a
+oid sha256:96045c3c99b4b17d4e21f3206026cbe712de82908e7ed7072eafe7773007f87d
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2e95d0cd5eca35603a5a3c0ca696f7994fa22b506f91b184142a0cdef47baa6
+oid sha256:12ae4986d784d8a3f0dc4588c65313f8ad63ed83111e4efcff53754e01e67493
 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": 3.288986827607755e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0004275682875890082,
+  "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": 3.288986827607755e-05,
       "eval_loss": 2.7174880504608154,
-      "eval_runtime": 2023.3662,
-      "eval_samples_per_second": 6.327,
-      "eval_steps_per_second": 3.164,
+      "eval_runtime": 2021.0944,
+      "eval_samples_per_second": 6.334,
+      "eval_steps_per_second": 3.167,
       "step": 1
+    },
+    {
+      "epoch": 0.00016444934138038777,
+      "grad_norm": 2.2541286945343018,
+      "learning_rate": 5e-05,
+      "loss": 2.8779,
+      "step": 5
+    },
+    {
+      "epoch": 0.00032889868276077554,
+      "grad_norm": 3.0431084632873535,
+      "learning_rate": 0.0001,
+      "loss": 2.5379,
+      "step": 10
+    },
+    {
+      "epoch": 0.00032889868276077554,
+      "eval_loss": 2.3707923889160156,
+      "eval_runtime": 2026.1498,
+      "eval_samples_per_second": 6.318,
+      "eval_steps_per_second": 3.159,
+      "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": 382218283253760.0,
+  "total_flos": 4968837682298880.0,
   "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 sha256:7ce486229881d3b74f10db3b45b69a9e9859424286e212b6eb3041471e264216
+oid sha256:447093cec584099ff08ae29a888aa65b12a90f7253961c9107febbd1e4932e82
 size 6776