Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "k_proj",
     "q_proj",
-    "up_proj",
-    "gate_proj",
+    "down_proj",
     "v_proj",
-    "o_proj"
+    "up_proj",
+    "o_proj",
+    "gate_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 sha256:4f4c36c1dd4925dc3435dff8f70e13ac5e9d98921cf0731918240b0f94179449
+oid sha256:ff97cfa533ad8493ac18c41efb36765df7f4887379a431e20c3215be59699a82
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec3ffb1f4de2887688e23675ed7b0559594cddb9684f6a2b485575558505ce7e
+oid sha256:847485b2b2d5d3351b735dcda2306d73bcd417236b21a3d16d907f3f63455a31
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7484c1a22d352ce83f5f015e796e9ceb701757f35d7de923c63231cfddeda93
+oid sha256:f940394d31917ffb2b05fe76a0061afb3125719306bdf6e3d7cd408a94c74ecd
 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": 1.5612985319890554e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00020296880915857718,
+  "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": 1.5612985319890554e-05,
       "eval_loss": 1.5307185649871826,
-      "eval_runtime": 3505.7925,
-      "eval_samples_per_second": 7.693,
-      "eval_steps_per_second": 3.846,
+      "eval_runtime": 3503.1138,
+      "eval_samples_per_second": 7.699,
+      "eval_steps_per_second": 3.849,
       "step": 1
+    },
+    {
+      "epoch": 7.806492659945277e-05,
+      "grad_norm": 1.2548145055770874,
+      "learning_rate": 5e-05,
+      "loss": 1.5664,
+      "step": 5
+    },
+    {
+      "epoch": 0.00015612985319890554,
+      "grad_norm": 1.7928839921951294,
+      "learning_rate": 0.0001,
+      "loss": 1.3714,
+      "step": 10
+    },
+    {
+      "epoch": 0.00015612985319890554,
+      "eval_loss": 1.3988229036331177,
+      "eval_runtime": 3558.3404,
+      "eval_samples_per_second": 7.579,
+      "eval_steps_per_second": 3.79,
+      "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": 277434637221888.0,
+  "total_flos": 3467932965273600.0,
   "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 sha256:62054dd862a7a489d88060976f5d114efa131e5659829d4b9c6646ff4c9ac995
+oid sha256:4c97fe7d3f106288583a6f26d022e142d8e95fccd2299c459dd110dc7353104c
 size 6776