Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c3482f05a3239c5148a658dda997b8699ad5eeaf7dff065d7b6a6a79c27838f
+oid sha256:7886389a1c62281327c1eca1cd0e07c3b6db0c73ced74ec03e0d7176f3526570
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0feb68ccd71fce67bcec7159424a7e0185a7e0f658f584bae13d1f2d01d5a7e0
+oid sha256:b983456ef79e79fc4e25b694388c17f27e8aa050a23f5c6d9c9403a6dfa6574b
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:638af6f593094a558f5283bf1669c955a044e33851610e2150ab691bd43844c0
+oid sha256:6473b014bdc320950dfa5ea285c9ac39b533139eb5d6d4f5d176c560d5dfd812
 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": 6.02364279798208e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0007830735637376704,
+  "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": 6.02364279798208e-05,
       "eval_loss": 5.864229202270508,
-      "eval_runtime": 653.0494,
-      "eval_samples_per_second": 10.704,
-      "eval_steps_per_second": 5.352,
+      "eval_runtime": 643.2876,
+      "eval_samples_per_second": 10.866,
+      "eval_steps_per_second": 5.433,
       "step": 1
+    },
+    {
+      "epoch": 0.00030118213989910396,
+      "grad_norm": 1.7193124294281006,
+      "learning_rate": 5e-05,
+      "loss": 5.7912,
+      "step": 5
+    },
+    {
+      "epoch": 0.0006023642797982079,
+      "grad_norm": 3.2139346599578857,
+      "learning_rate": 0.0001,
+      "loss": 5.5145,
+      "step": 10
+    },
+    {
+      "epoch": 0.0006023642797982079,
+      "eval_loss": 4.955783843994141,
+      "eval_runtime": 646.6116,
+      "eval_samples_per_second": 10.81,
+      "eval_steps_per_second": 5.405,
+      "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": 287553739554816.0,
+  "total_flos": 3738198614212608.0,
   "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 sha256:33f423efd63cc50e446a5d1ea9f62f6627a5376c3f1316c9b2fdbf06aa95d34c
+oid sha256:628970152feeac105812f9c8682fefb7aa0b323a791b99c70b7ddeccc6d98f93
 size 6776