Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "gate_proj",
-    "q_proj",
-    "o_proj",
-    "down_proj",
     "k_proj",
+    "v_proj",
     "up_proj",
-    "v_proj"
+    "q_proj",
+    "down_proj",
+    "o_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 sha256:89437aaa3a1d9124c890814f2b972530bd19af98873838dc641b9707ec92deec
+oid sha256:c66e7dad77a7cad86ef11d7e5eea616108ba29817a978922e661d881d76a665d
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51d24c87790c127824a91d2b547ac1b3a9556c332f53a3adf4ee4b0dc5aac5af
+oid sha256:667d9e914589f9acc8e0dc04bfcd040e4feddbcca9a9ab399dc0e94270e85f0d
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4865c784751f08fb8deff9071128988f7eb961f669d74f7bc3864ebf22f64623
+oid sha256:c778eff2399d91336cbbfb56a52fe8b5dc33458c58aee8df07f2b7da9eaab1ad
 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": 1.6231065447713652e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00021100385082027746,
+  "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": 1.6231065447713652e-05,
       "eval_loss": 1.1903656721115112,
-      "eval_runtime": 1377.5734,
-      "eval_samples_per_second": 18.832,
-      "eval_steps_per_second": 9.416,
+      "eval_runtime": 1380.1159,
+      "eval_samples_per_second": 18.797,
+      "eval_steps_per_second": 9.398,
       "step": 1
+    },
+    {
+      "epoch": 8.115532723856825e-05,
+      "grad_norm": 0.3520669639110565,
+      "learning_rate": 5e-05,
+      "loss": 0.9505,
+      "step": 5
+    },
+    {
+      "epoch": 0.0001623106544771365,
+      "grad_norm": 0.2661932110786438,
+      "learning_rate": 0.0001,
+      "loss": 1.2073,
+      "step": 10
+    },
+    {
+      "epoch": 0.0001623106544771365,
+      "eval_loss": 1.1880683898925781,
+      "eval_runtime": 1378.339,
+      "eval_samples_per_second": 18.821,
+      "eval_steps_per_second": 9.411,
+      "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": 123007299747840.0,
+  "total_flos": 1722102196469760.0,
   "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 sha256:2c65f5a3afadeeb37e4a9f529396f76ffbdf5fefa60d8a49dd50156969e0d544
+oid sha256:34467d464a1014f734add1fd005384274b5eb325f890f9c8d872bab038d4721a
 size 6776