Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,11 +21,11 @@
   "revision": null,
   "target_modules": [
     "gate_proj",
+    "down_proj",
     "q_proj",
+    "k_proj",
     "up_proj",
     "o_proj",
-    "down_proj",
-    "k_proj",
     "v_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40594e70e268cf30ca0bc2106528894973b8ecefdb9e0d5e7cfde4f0caf1e3ef
+oid sha256:11d0fdfe76e903c3805e5a86d7f7a3ea54ac608ea87dd4fe401713b824aa6e2a
 size 36981072

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1c840391a21fbb35ce4846a625e1f63917d6d5d754442f8daed3465d346a0e7
+oid sha256:d6b25c752847b616122f69c31210833d88a139298d792a264acf326e4f7f32f6
 size 19859140

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c51f146f4fc53b947536c3e81e6193448dfdd10418dbeabf6b11a43fc5e532ac
+oid sha256:77ce7eb2a81e98a75d9cf725ae82f418a5dbbd53b1a3beac074903b7c0f3fa0a
 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": 5.7839408881241236e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.000751912315456136,
+  "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": 5.7839408881241236e-05,
       "eval_loss": NaN,
-      "eval_runtime": 653.3279,
-      "eval_samples_per_second": 11.143,
-      "eval_steps_per_second": 5.571,
+      "eval_runtime": 839.3884,
+      "eval_samples_per_second": 8.673,
+      "eval_steps_per_second": 4.336,
       "step": 1
+    },
+    {
+      "epoch": 0.0002891970444062062,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0005783940888124124,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.0005783940888124124,
+      "eval_loss": NaN,
+      "eval_runtime": 948.1831,
+      "eval_samples_per_second": 7.678,
+      "eval_steps_per_second": 3.839,
+      "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": 40537282314240.0,
+  "total_flos": 689133799342080.0,
   "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 sha256:79f36fe6051b2d9a5dc3965f147afa9ef1ae8b0478717b47a01222184ef83dd0
+oid sha256:b18172c65ce095b7576e9b70e85c94e767da396adfc112e2889a75f29b948bb5
 size 6776