Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "gate_proj",
     "up_proj",
-    "down_proj",
     "o_proj",
-    "q_proj",
-    "k_proj"
+    "v_proj",
+    "down_proj",
+    "gate_proj",
+    "k_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:de6841db236a68974869b6d9b42a6450c6c406e9ebf863c50569610f1079503d
+oid sha256:d7cbb08df4805011c8a5f7d27a8fec066b371439095f7fd83c152011419e4d39
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b590e524f7cdd361ece5ded145affe4e460d97e0f2579b434ca85acac1f7332a
+oid sha256:f8fe64515736952da0a50b0a801eb5541231334860dfbbb1a4e75b2e76f712d5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb6245a3f3fe99fd9d96194c8979b73f0b09d7fc7edf23d255b0a7cb132b6b75
+oid sha256:36cfe1be5c7989270a7ce0df3c215f47905de3f6ac294a27fed514d5adcc156f
 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": 3.238210888484113e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00042096741550293464,
+  "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": 3.238210888484113e-05,
       "eval_loss": 1.5096166133880615,
-      "eval_runtime": 1087.7908,
+      "eval_runtime": 1087.7586,
       "eval_samples_per_second": 11.954,
       "eval_steps_per_second": 5.977,
       "step": 1
+    },
+    {
+      "epoch": 0.00016191054442420561,
+      "grad_norm": 2.1016464233398438,
+      "learning_rate": 5e-05,
+      "loss": 1.3974,
+      "step": 5
+    },
+    {
+      "epoch": 0.00032382108884841123,
+      "grad_norm": 1.9378647804260254,
+      "learning_rate": 0.0001,
+      "loss": 1.3497,
+      "step": 10
+    },
+    {
+      "epoch": 0.00032382108884841123,
+      "eval_loss": 1.039423942565918,
+      "eval_runtime": 1092.1981,
+      "eval_samples_per_second": 11.905,
+      "eval_steps_per_second": 5.953,
+      "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": 184956424814592.0,
+  "total_flos": 3005541903237120.0,
   "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 sha256:2528cb390846b9bf12c679e9ef881d308aebbac0bd4f9ddc972cdcfd4abc6e1b
+oid sha256:163840142d76a9a8ac934fd93f0c906fa8feed26927ca297e3856c2ecb4cdab3
 size 6776