Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "o_proj",
-    "v_proj",
     "q_proj",
+    "gate_proj",
     "k_proj",
-    "up_proj",
-    "gate_proj"
+    "v_proj",
+    "o_proj",
+    "down_proj",
+    "up_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 sha256:6712c93e349eacb523bf0adf3e9c793d7a2a02fcf103536ca4f3503a137aca2b
+oid sha256:2f4e2ef59a58c0d820c52ef4ecb0c4eea47fd2a0800ea031f08a8ab39969905f
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1000f3e867ac236f0d57d0c8301ee9dfd9d88b37648fbb1980204d64c9a3fa77
+oid sha256:2e9d4fb73752ac2948aead84030a470b6153623fc4d5f943d9c96485a713416b
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
+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": 0.0015455950540958269,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.02009273570324575,
+  "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": 0.0015455950540958269,
       "eval_loss": 10.375998497009277,
-      "eval_runtime": 1.6004,
-      "eval_samples_per_second": 170.583,
-      "eval_steps_per_second": 85.604,
+      "eval_runtime": 1.5673,
+      "eval_samples_per_second": 174.182,
+      "eval_steps_per_second": 87.41,
       "step": 1
+    },
+    {
+      "epoch": 0.0077279752704791345,
+      "grad_norm": 0.04116315767168999,
+      "learning_rate": 5e-05,
+      "loss": 10.3764,
+      "step": 5
+    },
+    {
+      "epoch": 0.015455950540958269,
+      "grad_norm": 0.03205065801739693,
+      "learning_rate": 0.0001,
+      "loss": 10.3734,
+      "step": 10
+    },
+    {
+      "epoch": 0.015455950540958269,
+      "eval_loss": 10.375765800476074,
+      "eval_runtime": 1.5404,
+      "eval_samples_per_second": 177.229,
+      "eval_steps_per_second": 88.939,
+      "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": 19396362240.0,
+  "total_flos": 187498168320.0,
   "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 sha256:545087bd0a38832c71156680c84a71a9305da77cbbde0624deca3b06c5844543
+oid sha256:2d552ad652704f2bee3e5ca86de3c71f0e56efb29ad0e1022c67dccf60e6f511
 size 6776