Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "up_proj",
+    "v_proj",
     "o_proj",
-    "k_proj",
+    "q_proj",
     "gate_proj",
-    "up_proj",
-    "down_proj",
-    "v_proj"
+    "k_proj",
+    "down_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 sha256:1c5b06f3dbcea30575a1fce72911f968c47c696fd3d6f1e450cf66ac6552a131
+oid sha256:177128138fa4d33a37bac233ad555bc2daebc47fd0624757a618d7d58ce2af4a
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cfb1f7df59e59f41bd40add21a6efe3d68e00abc0e0b1b4d040542970663bdb
+oid sha256:b4321198b235398d41571ef0bc4cf90406fe35356c0e51e85f74b617c9189962
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4de5db1833cab0d59fd52c3c45e4ac2e7df3a6dbe62013795bf41fc12fe1f3e
+oid sha256:3ef2cd54db7aa44d7ce15aa60e17a159e954b389b719292da45c956fa837ba1d
 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": 7.448096080439437e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0009682524904571269,
+  "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": 7.448096080439437e-05,
       "eval_loss": 11.930380821228027,
-      "eval_runtime": 50.4262,
-      "eval_samples_per_second": 112.124,
-      "eval_steps_per_second": 56.062,
+      "eval_runtime": 49.5414,
+      "eval_samples_per_second": 114.127,
+      "eval_steps_per_second": 57.063,
       "step": 1
+    },
+    {
+      "epoch": 0.0003724048040219719,
+      "grad_norm": 0.023313909769058228,
+      "learning_rate": 5e-05,
+      "loss": 11.9262,
+      "step": 5
+    },
+    {
+      "epoch": 0.0007448096080439438,
+      "grad_norm": 0.024473126977682114,
+      "learning_rate": 0.0001,
+      "loss": 11.931,
+      "step": 10
+    },
+    {
+      "epoch": 0.0007448096080439438,
+      "eval_loss": 11.930343627929688,
+      "eval_runtime": 50.4719,
+      "eval_samples_per_second": 112.023,
+      "eval_steps_per_second": 56.011,
+      "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": 118161408.0,
+  "total_flos": 1536098304.0,
   "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:bc29202312f7a0ffc3d0ae90f424b70bcbe8dfdc52d9829e81403ec62c1fa165
+oid sha256:32b7ee7b22b5215ca21bdbbdf762062a47cfee48aaa1fb12de37658a0596b47c
 size 6776