Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "up_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
     "down_proj",
     "gate_proj",
-    "k_proj",
-    "v_proj",
-    "q_proj",
+    "up_proj",
     "o_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6f93befe875f7e0e4bd81646a0729e574b9862cf2a933e4e3b3decfc3daa47f
+oid sha256:309b5c31e1eb4682e6592efa0e258e736f4727905e7cfa68f9e4334246f47591
 size 25271744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e563da3243560ef1a52ea0cd28134b3db22114edd3f08bfa1016efd125bd9471
+oid sha256:f6983d10ff574d14623acb1bcd2cbf458c7d22a4892645f9e4c7976cb341a069
 size 13685516

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2f2b1fe1ee433d0949425d85cbc1e7db562c93cb1fc4f9c675368fbffc7b15d
+oid sha256:8584eb0606268fe40a7b607403caf1bbfdb0ed83707fc0a067fb7329a1dc8581
 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": 0.0021482277121374865,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.027926960257787327,
+  "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": 0.0021482277121374865,
       "eval_loss": 9.146766662597656,
-      "eval_runtime": 5.9671,
-      "eval_samples_per_second": 32.847,
-      "eval_steps_per_second": 16.424,
+      "eval_runtime": 6.1234,
+      "eval_samples_per_second": 32.008,
+      "eval_steps_per_second": 16.004,
       "step": 1
+    },
+    {
+      "epoch": 0.010741138560687433,
+      "grad_norm": 48.73690414428711,
+      "learning_rate": 5e-05,
+      "loss": 9.132,
+      "step": 5
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "grad_norm": 42.14037322998047,
+      "learning_rate": 0.0001,
+      "loss": 7.8659,
+      "step": 10
+    },
+    {
+      "epoch": 0.021482277121374866,
+      "eval_loss": 6.615852355957031,
+      "eval_runtime": 6.0593,
+      "eval_samples_per_second": 32.347,
+      "eval_steps_per_second": 16.173,
+      "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": 25579197825024.0,
+  "total_flos": 332529571725312.0,
   "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 sha256:98e374460b1812312e02a76c370929cb486ed8a830c27b29414bbb90715187e8
+oid sha256:f6b5b23c8ebf4587262994556550bb53cde959ca12121b99e0d8959ba5573a94
 size 6776