Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
-    "gate_proj",
     "v_proj",
     "up_proj",
+    "gate_proj",
+    "q_proj",
+    "down_proj",
     "k_proj",
-    "o_proj",
-    "down_proj"
+    "o_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 sha256:1c75e16539d60da76eb46d1c103646ff22566533cf01ba0feec812c9884b8d3e
+oid sha256:c572ac4d384a3fc5cc7aed7fa3d3be0451819e99c5ee3e04b7b20aced39c78fa
 size 48679352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1742d67669489474413214e7fc726c24f49a937033a6ea8d27f285946f167fa
+oid sha256:7034b2a46f4ba566680888eace569f40000648dc4196686a161268ecd9eb8606
 size 25152500

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb458b5a1f8cef8f2c5efceafe5cd8d2f44ca1d3c450cdb5235d4e5d6680372b
+oid sha256:7c171c2897ca9d2f89e7a6497a214756f9883df2e8fed753bb9125824302999f
 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": 0.016771488469601678,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.2180293501048218,
+  "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": 0.016771488469601678,
       "eval_loss": 10.19597053527832,
-      "eval_runtime": 22.6365,
-      "eval_samples_per_second": 17.759,
-      "eval_steps_per_second": 2.253,
+      "eval_runtime": 22.5864,
+      "eval_samples_per_second": 17.798,
+      "eval_steps_per_second": 2.258,
       "step": 1
+    },
+    {
+      "epoch": 0.16771488469601678,
+      "grad_norm": 8.230109214782715,
+      "learning_rate": 9.330127018922194e-05,
+      "loss": 9.3317,
+      "step": 10
+    },
+    {
+      "epoch": 0.16771488469601678,
+      "eval_loss": 6.821496963500977,
+      "eval_runtime": 22.9033,
+      "eval_samples_per_second": 17.552,
+      "eval_steps_per_second": 2.227,
+      "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": 2087169137049600.0,
+  "total_flos": 2.803763874103296e+16,
   "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 sha256:1f1f82c456e190a11568ca33ba181f8d2c6c17b7873b2eda3aa3a6c34a4e62cc
+oid sha256:ba711e0d4b7959880cfb9b560cfb60590223f1698f2d97bb928b2478d3023c3d
 size 6776