Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "down_proj",
-    "q_proj",
-    "k_proj",
     "o_proj",
+    "k_proj",
+    "v_proj",
+    "q_proj",
+    "down_proj",
     "up_proj",
-    "v_proj"
+    "gate_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 sha256:062ab53e9df2ae2bbb3b0fb91968e2f6b2baef3f53b9551cda91e6382eec98e8
+oid sha256:f8ebade2d646b25eda69973e6397ab9ff975c321d7ef2e073f6f80fbb88c1bf7
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31ff64b722bd4f53f5e1cfb05e7b90fa221def3354baaeef9fd7320dff08b282
+oid sha256:86543cc233003dc006ccee53994ca456e760bbe882a317f5cd6bb9bde92c551e
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
+oid sha256:a5cba764fcb0e7f18b6d06759624dccc13afd567f3245791b3de96f9fcfce3c5
 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": 3.814282581125023e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.000495856735546253,
+  "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": 3.814282581125023e-05,
       "eval_loss": 0.48583489656448364,
-      "eval_runtime": 1318.1054,
-      "eval_samples_per_second": 8.375,
-      "eval_steps_per_second": 4.188,
+      "eval_runtime": 1315.3619,
+      "eval_samples_per_second": 8.392,
+      "eval_steps_per_second": 4.197,
       "step": 1
+    },
+    {
+      "epoch": 0.00019071412905625112,
+      "grad_norm": 4.663794040679932,
+      "learning_rate": 5e-05,
+      "loss": 1.8977,
+      "step": 5
+    },
+    {
+      "epoch": 0.00038142825811250225,
+      "grad_norm": 3.249136209487915,
+      "learning_rate": 0.0001,
+      "loss": 1.729,
+      "step": 10
+    },
+    {
+      "epoch": 0.00038142825811250225,
+      "eval_loss": 0.3942370116710663,
+      "eval_runtime": 1320.2014,
+      "eval_samples_per_second": 8.362,
+      "eval_steps_per_second": 4.181,
+      "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": 350533957189632.0,
+  "total_flos": 4556941443465216.0,
   "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:dddc5f7c595a8c0084551c8a72782d8b144c9840038defb05b25582f6b4b01b0
+oid sha256:5ba781ec71f2b1e4154e41f641b65d6830701dea48973ba89dc1e8c05fdad1cd
 size 6776