Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "down_proj",
-    "k_proj",
+    "up_proj",
+    "o_proj",
     "gate_proj",
     "q_proj",
-    "v_proj",
-    "up_proj",
-    "o_proj"
+    "k_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:f6c6ac4f253a9a4f56dde79824ceeb973306276804f757a76de519bb6a0d7ab5
+oid sha256:24abc8c0c8b80c86552b5a6d6c6ba4c7f5659a2e8b6488ac187df19c2315c4a0
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c5cd8caae93956d4375f4787c0f1ffd48ad8a2e2e5817b19ab25af5532b102a
+oid sha256:f0a7a2471a9f4d3b7d61f5a5a11c07ef35d1b71831716257397740d3212a234f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64dc269c204efc2e9a4c4cbe20de7c7547b2a048bf7e9385229ea63d598fdfd
+oid sha256:3f0082b9ee265cb0c6910d3944f6a738794d996da2e7f7ac5ed1f97dde094437
 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": 0.009237875288683603,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.12009237875288684,
+  "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": 0.009237875288683603,
       "eval_loss": 2.44881272315979,
-      "eval_runtime": 3.1005,
-      "eval_samples_per_second": 14.836,
-      "eval_steps_per_second": 7.418,
+      "eval_runtime": 3.1089,
+      "eval_samples_per_second": 14.796,
+      "eval_steps_per_second": 7.398,
       "step": 1
+    },
+    {
+      "epoch": 0.046189376443418015,
+      "grad_norm": 13.313944816589355,
+      "learning_rate": 5e-05,
+      "loss": 9.1038,
+      "step": 5
+    },
+    {
+      "epoch": 0.09237875288683603,
+      "grad_norm": 14.019678115844727,
+      "learning_rate": 0.0001,
+      "loss": 8.1093,
+      "step": 10
+    },
+    {
+      "epoch": 0.09237875288683603,
+      "eval_loss": 2.2830543518066406,
+      "eval_runtime": 3.3082,
+      "eval_samples_per_second": 13.905,
+      "eval_steps_per_second": 6.952,
+      "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": 175267179921408.0,
+  "total_flos": 2409923723919360.0,
   "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:dafaae1b2f30f95ade87776a1affb1ecb895e37ad1fb22b212e93d52115ba7d6
+oid sha256:d4e30a6b31cddba2a7f523c3cbf64393640bffe09afec9bde34205ef10eb3719
 size 6776