Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
+    "up_proj",
     "v_proj",
-    "q_proj",
+    "down_proj",
     "k_proj",
-    "up_proj",
     "gate_proj",
-    "down_proj"
+    "q_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 sha256:67bc5a9472bac687a1cc030490b924961522fa07832fc575bad81f9178b225d4
+oid sha256:46d608aa1dd791645543595a25bb2995a763e8aadb507768c20a053b9ac2b2d7
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e759bc76150fdc2d87cd050eed4665d0db1a5057cda18ce9f55a9ec70604ef56
+oid sha256:00e8924b8bad3c29336d8960777e07ae1c5f645f34cefeedea9fc5202351040d
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:cf3c4a2e5cad8425a70bb7989e81f5a4e47e5f54a4760cc1141b93404eca1148
 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": 2.8232039129606233e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.000367016508684881,
+  "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": 2.8232039129606233e-05,
       "eval_loss": 1.372756004333496,
-      "eval_runtime": 1296.2608,
-      "eval_samples_per_second": 11.506,
-      "eval_steps_per_second": 5.753,
+      "eval_runtime": 1295.716,
+      "eval_samples_per_second": 11.511,
+      "eval_steps_per_second": 5.756,
       "step": 1
+    },
+    {
+      "epoch": 0.00014116019564803118,
+      "grad_norm": 9.01905632019043,
+      "learning_rate": 5e-05,
+      "loss": 5.2824,
+      "step": 5
+    },
+    {
+      "epoch": 0.00028232039129606236,
+      "grad_norm": 6.25973653793335,
+      "learning_rate": 0.0001,
+      "loss": 4.8007,
+      "step": 10
+    },
+    {
+      "epoch": 0.00028232039129606236,
+      "eval_loss": 1.1299453973770142,
+      "eval_runtime": 1315.7538,
+      "eval_samples_per_second": 11.336,
+      "eval_steps_per_second": 5.668,
+      "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": 175266978594816.0,
+  "total_flos": 2278470721732608.0,
   "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:b133015bc7def26eb31252d9e6682e1cf9fd87b2588815b916c742255269931a
+oid sha256:b4bd1a8c777406f7eeffcba3a40a3e2ec8f453094a1bb12e162e4f96cf26d078
 size 6776