Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "k_proj",
+    "gate_proj",
+    "down_proj",
     "o_proj",
     "up_proj",
-    "down_proj",
-    "q_proj",
-    "gate_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 sha256:9d5dee444342f9c19d0a04ed68173882bf18ca21741bc5bc235c482dbd7c65df
+oid sha256:0733ef25405f32b1573b8aca7ac0e9d3f81b68f206d44dfb9ac5cc8c3019ee15
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b7bd8267e04cd7e2d1d2563e1fe6c53f129fa1d2a7b5f1d6da3f36eff59a2e
+oid sha256:9a04ea89e27d81bdfadd01a2e32a838b97dd199b922186e5ed62d456c997190b
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d17cd0b5f1e33bd6dba2461570a653efdaf1fb902096b4df09992935b3fc24a4
+oid sha256:3bcb00611cefc3be90fcf85b9c7538ee5189f93f06f6431a2dc9a2bc3c732ea8
 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": 0.002628120893561104,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.03416557161629435,
+  "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": 0.002628120893561104,
       "eval_loss": NaN,
-      "eval_runtime": 6.6783,
-      "eval_samples_per_second": 24.108,
-      "eval_steps_per_second": 12.129,
+      "eval_runtime": 6.5943,
+      "eval_samples_per_second": 24.415,
+      "eval_steps_per_second": 12.283,
       "step": 1
+    },
+    {
+      "epoch": 0.013140604467805518,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.026281208935611037,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.026281208935611037,
+      "eval_loss": NaN,
+      "eval_runtime": 5.3138,
+      "eval_samples_per_second": 30.298,
+      "eval_steps_per_second": 15.243,
+      "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": 8903816380416.0,
+  "total_flos": 115749612945408.0,
   "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 sha256:670112c545ffebe9637bf18073ac8e09e0e11182117c4f1faf79d161828016ab
+oid sha256:309687c87037e56d0af169ab810f4083bcc8c56c5fcdfc4232fee9eed27454b0
 size 6776