Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
     "v_proj",
-    "k_proj",
-    "o_proj",
-    "gate_proj",
     "down_proj",
-    "up_proj"
+    "gate_proj",
+    "up_proj",
+    "q_proj",
+    "o_proj",
+    "k_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:b1658257d9a0ebc2e2a0b2ea4e109552a426e1348bb390f235d95fac2f3e2cbd
+oid sha256:188e71d9bfa67c85644a29bde0939de8fedaf3b884b482fe15a2d41549bab806
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f19cb011e6e67803346cf79ce198a1005783b77bc4c591ef75e1e77295da36ac
+oid sha256:7a1080c9d277b85afcbb5a7d4774379c5dcb6b3df9a38625b087fef3c6c876b1
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
+oid sha256:b9afaef5d5a881aad7a4d7f56dee797e2bfaf24e0e0195fec33bed705a83390f
 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": 0.000847457627118644,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.011016949152542373,
+  "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": 0.000847457627118644,
       "eval_loss": NaN,
-      "eval_runtime": 75.906,
-      "eval_samples_per_second": 6.548,
-      "eval_steps_per_second": 3.28,
+      "eval_runtime": 76.8386,
+      "eval_samples_per_second": 6.468,
+      "eval_steps_per_second": 3.241,
       "step": 1
+    },
+    {
+      "epoch": 0.00423728813559322,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00847457627118644,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.00847457627118644,
+      "eval_loss": NaN,
+      "eval_runtime": 74.2551,
+      "eval_samples_per_second": 6.693,
+      "eval_steps_per_second": 3.353,
+      "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": 162874924204032.0,
+  "total_flos": 2443123863060480.0,
   "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 sha256:0feb124cea94b70d74fc03c271be1c96278bc9569ddd801c47ba25eb8dc6e963
+oid sha256:2bc7efd3fc33a4d1856db7290c823c8ab235e62e6b5fdb600e666a5d54e47371
 size 6776