Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
+    "down_proj",
     "up_proj",
+    "q_proj",
     "k_proj",
-    "down_proj",
-    "gate_proj",
-    "o_proj"
+    "v_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:e470707fc0d6f39f87d22835873a08a2a73cdd9f9dbe68dba0a31509ccc2cd4f
+oid sha256:8bb0bdf2d2c38c6036a94bfc2422b6d1f8edc1b6ebdafd77143ad5060ff7382a
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b117c821abe2ff61cf8d7dcc29d9c9f6f28541f5c8b9d2b2b54168158a8426f7
+oid sha256:94168f68153c6364968db359f80a1433ead0ae605ecd08840d45d2f40604b768
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e8a4b5e8d178ed69448cd2faf4a00e084a9849f20593fafd5b19694920450ac
+oid sha256:6f568ed351f6eae84afcd2aee8da5ac8ae6ce1f596e1fef8462445a04d986b44
 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": 1.6563146997929607e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00021532091097308488,
+  "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": 1.6563146997929607e-05,
       "eval_loss": 1.7334619760513306,
-      "eval_runtime": 1473.2292,
-      "eval_samples_per_second": 17.255,
-      "eval_steps_per_second": 8.628,
+      "eval_runtime": 1478.9308,
+      "eval_samples_per_second": 17.189,
+      "eval_steps_per_second": 8.595,
       "step": 1
+    },
+    {
+      "epoch": 8.281573498964803e-05,
+      "grad_norm": 0.30731433629989624,
+      "learning_rate": 5e-05,
+      "loss": 1.7783,
+      "step": 5
+    },
+    {
+      "epoch": 0.00016563146997929605,
+      "grad_norm": 0.3904305696487427,
+      "learning_rate": 0.0001,
+      "loss": 1.6939,
+      "step": 10
+    },
+    {
+      "epoch": 0.00016563146997929605,
+      "eval_loss": 1.6821030378341675,
+      "eval_runtime": 1481.8112,
+      "eval_samples_per_second": 17.155,
+      "eval_steps_per_second": 8.578,
+      "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": 143508516372480.0,
+  "total_flos": 1845109496217600.0,
   "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 sha256:382a1be13fcb80bf2e7ff36a0fc820d8615b4645a95f4424879f2d4932f689de
+oid sha256:72209604b1adc64692c6c5089e1d41b60838ebebbace626bb414e8d12f559c5a
 size 6776