Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,9 +21,9 @@
   "revision": null,
   "target_modules": [
     "query_key_value",
+    "dense",
     "dense_h_to_4h",
-    "dense_4h_to_h",
-    "dense"
+    "dense_4h_to_h"
   ],
   "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:bcefda107ae0a0874813dd92eb35923f5cbf7885d3618830bfea37aa01a3b01a
+oid sha256:824ae469c6063a0efa80795f36a5fecfcede9ef9c2aca4c3a0666be19ccecb6a
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49dffc5f069d5848da423004da5d6a5d02b1de81926f84e7e46ca2af244fa593
+oid sha256:c763222db616c9f29a484a6203361406ff9384f9cb22f2ac97f7e9bec82ff737
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e41786d93022ecb8c77c66c54399ef1b8e95dd48a633f70ac7335d6fde4af8f
+oid sha256:ec24b3854134798d2456e1dd854b45d6659c142bc296821da1aaf13f07c042eb
 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": 0.00040816326530612246,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.005306122448979592,
+  "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": 0.00040816326530612246,
       "eval_loss": 1.038622498512268,
-      "eval_runtime": 99.9875,
-      "eval_samples_per_second": 10.321,
-      "eval_steps_per_second": 5.161,
+      "eval_runtime": 100.2598,
+      "eval_samples_per_second": 10.293,
+      "eval_steps_per_second": 5.147,
       "step": 1
+    },
+    {
+      "epoch": 0.0020408163265306124,
+      "grad_norm": 1.570367455482483,
+      "learning_rate": 5e-05,
+      "loss": 4.0227,
+      "step": 5
+    },
+    {
+      "epoch": 0.004081632653061225,
+      "grad_norm": 1.5186132192611694,
+      "learning_rate": 0.0001,
+      "loss": 3.7081,
+      "step": 10
+    },
+    {
+      "epoch": 0.004081632653061225,
+      "eval_loss": 0.9728806614875793,
+      "eval_runtime": 100.715,
+      "eval_samples_per_second": 10.247,
+      "eval_steps_per_second": 5.123,
+      "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": 285280535838720.0,
+  "total_flos": 4493168439459840.0,
   "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 sha256:56752e5c5d93e34804ef8aea592a799213eec12639397e6704425ae76557f381
+oid sha256:ab62f4fadd2647bf2ef10fab70431d7906a988aa3e92349bfec4360d260cff21
 size 6776