Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "o_proj",
     "up_proj",
+    "k_proj",
     "down_proj",
-    "v_proj",
-    "o_proj",
-    "gate_proj",
-    "q_proj"
+    "v_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 sha256:424e4080b97c03861ff6aa27ffd6ddf1810220850b51e058b8141a47c6d7c7a8
+oid sha256:8de08a61e0bb279e10ef5c2b8fddf2cc8de726c2c357aa27e6ba20e40c07762e
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6591e2917469f977a2447132bdb8bcfea9de2241d1706bebd7ebfc8226af27cb
+oid sha256:d1e639258da4aad6bb3e0891702d8f236460a4ad9306d75e018488723172faf5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce18d2d551de9284109c0e2530e5f04b91a8696554c7740e97ea2b7bdd6d1090
+oid sha256:a5cba764fcb0e7f18b6d06759624dccc13afd567f3245791b3de96f9fcfce3c5
 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": 0.0002450379808870375,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0031854937515314874,
+  "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": 0.0002450379808870375,
       "eval_loss": 1.2887710332870483,
-      "eval_runtime": 202.4887,
-      "eval_samples_per_second": 8.489,
-      "eval_steps_per_second": 4.247,
+      "eval_runtime": 202.0425,
+      "eval_samples_per_second": 8.508,
+      "eval_steps_per_second": 4.257,
       "step": 1
+    },
+    {
+      "epoch": 0.0012251899044351876,
+      "grad_norm": 9.062094688415527,
+      "learning_rate": 5e-05,
+      "loss": 5.26,
+      "step": 5
+    },
+    {
+      "epoch": 0.002450379808870375,
+      "grad_norm": 7.3053297996521,
+      "learning_rate": 0.0001,
+      "loss": 4.7386,
+      "step": 10
+    },
+    {
+      "epoch": 0.002450379808870375,
+      "eval_loss": 1.099696159362793,
+      "eval_runtime": 203.9631,
+      "eval_samples_per_second": 8.428,
+      "eval_steps_per_second": 4.216,
+      "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": 350534359842816.0,
+  "total_flos": 4556946677956608.0,
   "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:b667ecdad4b1d208e887420aa527ea863a9ae8cf05f340d9699417da663227f5
+oid sha256:5e1ec8db54512968a3032b1cb525ddae50f2932f286af1b3b3966828a82ed480
 size 6776