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",
-    "up_proj",
+    "o_proj",
     "down_proj",
     "v_proj",
-    "o_proj",
+    "q_proj",
+    "up_proj",
+    "k_proj",
     "gate_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66a532c0f6bf9e219076e4a4897cbffe2ed738cef862f00f7459037f1c39c8e7
+oid sha256:8b13da2f77aa424dbc93cd4e1d826c83ca8d94743cdb6bc83e2b24fedebddf30
 size 30026872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d40f7243917c41a8359c693d3b44b6bd1b73f92eec2261b51cc2266e0c10595e
+oid sha256:30867b6933df59d3d0b0e5725bc7201987f2e4c26512f89e93a7586faa77c15b
 size 15611412

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:367fbe03f91326df644be2bfe939b003dfc530dae41e5dcfc34826d3a7c610c8
+oid sha256:2f79b645bbe79c0be97bb100e04ee9555a2d25ef0b6a1707f08fe43d99815c25
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae751897b8e87ff08962a91d1d3485984775a96aa89e29a1caac3d6f449228f7
+oid sha256:5adea6def46a60dd5782726d51a89bdf0f30226cd791e511d8af09a5644f99e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.008506113769271665,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.11057947900053164,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -11,17 +11,32 @@
     {
       "epoch": 0.008506113769271665,
       "eval_loss": 2.6882784366607666,
-      "eval_runtime": 13.6997,
-      "eval_samples_per_second": 57.811,
-      "eval_steps_per_second": 7.226,
+      "eval_runtime": 13.726,
+      "eval_samples_per_second": 57.701,
+      "eval_steps_per_second": 7.213,
       "step": 1
+    },
+    {
+      "epoch": 0.08506113769271664,
+      "grad_norm": 2.610746383666992,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 2.2492,
+      "step": 10
+    },
+    {
+      "epoch": 0.08506113769271664,
+      "eval_loss": 1.2946914434432983,
+      "eval_runtime": 13.264,
+      "eval_samples_per_second": 59.711,
+      "eval_steps_per_second": 7.464,
+      "step": 10
     }
   ],
   "logging_steps": 10,
-  "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 +44,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
   },
-  "total_flos": 506219609456640.0,
+  "total_flos": 6580854922936320.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e56c493efd377cec26af6879c2998ee417c01c9b03cb082fdd81af5bd381b8d
+oid sha256:b9cd14347c06c0d71cf7b2a71c12cc3feb4b7f65921a3b8aa0d9de54766fcc4e
 size 6776