Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "v_proj",
-    "up_proj",
     "gate_proj",
+    "up_proj",
     "down_proj",
-    "o_proj",
+    "k_proj",
     "q_proj",
-    "k_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 sha256:210f2c8b5d2eaef82388179b728d04fbe585f063046547bc1b1abb18e7fca168
+oid sha256:02b48e67acb1b6535b15c01d489348bff25f3fac47112840aedd064b54c78ac6
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94c39bef9f7f674c407b664c77f353b0cb47d735f34c2d030cff15860fa1c80c
+oid sha256:dbd5e642f8b14d44f56babb699485d8b9d14cc93b2a9f0e78740962c0b62936b
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
+oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
 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": 0.0002961427408010661,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0038498556304138597,
+  "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": 0.0002961427408010661,
       "eval_loss": 11.932991981506348,
-      "eval_runtime": 12.619,
-      "eval_samples_per_second": 112.687,
-      "eval_steps_per_second": 56.343,
+      "eval_runtime": 12.6985,
+      "eval_samples_per_second": 111.982,
+      "eval_steps_per_second": 55.991,
       "step": 1
+    },
+    {
+      "epoch": 0.0014807137040053306,
+      "grad_norm": 0.02087347023189068,
+      "learning_rate": 5e-05,
+      "loss": 11.9333,
+      "step": 5
+    },
+    {
+      "epoch": 0.0029614274080106613,
+      "grad_norm": 0.012602627277374268,
+      "learning_rate": 0.0001,
+      "loss": 11.932,
+      "step": 10
+    },
+    {
+      "epoch": 0.0029614274080106613,
+      "eval_loss": 11.932961463928223,
+      "eval_runtime": 12.9074,
+      "eval_samples_per_second": 110.169,
+      "eval_steps_per_second": 55.085,
+      "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": 118161408.0,
+  "total_flos": 1536098304.0,
   "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:a31f5f62fcf1ac82ff727bc5d125d6f2b6bc7abcf6c57e1699dc80482a6f5c33
+oid sha256:ded83cc5da1d585cbd5bdc109de10ec095d7e218443391505e2586f48f8d1cc9
 size 6776