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",
+    "k_proj",
     "up_proj",
+    "gate_proj",
     "v_proj",
-    "k_proj",
-    "down_proj",
-    "o_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 sha256:3d954a9f0baf6e0ed97a6bc26b62d4039e066f2f85d58cb73a40481c26385752
+oid sha256:3097813250249bed31a265d0459450cb885679ff29197c19b1fa502d70860a08
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:286a1b8712e62790f5616d10e1c0bcc90e7876f10d3448398c039436b4232dde
+oid sha256:5e876f1f9842d88b6b8158efabd533e8ffd9610577ac05687d6d3df25ea16830
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
+oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
 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": 0.00042211903756859433,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.005487547488391726,
+  "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": 0.00042211903756859433,
       "eval_loss": 2.3645458221435547,
-      "eval_runtime": 751.4972,
-      "eval_samples_per_second": 1.328,
-      "eval_steps_per_second": 0.664,
+      "eval_runtime": 777.7782,
+      "eval_samples_per_second": 1.283,
+      "eval_steps_per_second": 0.642,
       "step": 1
+    },
+    {
+      "epoch": 0.002110595187842972,
+      "grad_norm": 6.993026256561279,
+      "learning_rate": 5e-05,
+      "loss": 9.41,
+      "step": 5
+    },
+    {
+      "epoch": 0.004221190375685944,
+      "grad_norm": 13.77673625946045,
+      "learning_rate": 0.0001,
+      "loss": 8.1771,
+      "step": 10
+    },
+    {
+      "epoch": 0.004221190375685944,
+      "eval_loss": 1.9789879322052002,
+      "eval_runtime": 838.986,
+      "eval_samples_per_second": 1.19,
+      "eval_steps_per_second": 0.595,
+      "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": 162873313591296.0,
+  "total_flos": 2117353076686848.0,
   "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 sha256:4a8173a0de43c0b9fd0a6b8bcc35da460d3ef4a8e5cb2a1a5f8f8bf20c827686
+oid sha256:d02311778ddfe186877f52e8350d2fab3ae16cfcb0eaf1c78a0347f269402d53
 size 6776