Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "up_proj",
-    "gate_proj",
+    "v_proj",
     "q_proj",
+    "down_proj",
+    "gate_proj",
     "k_proj",
-    "v_proj",
-    "o_proj",
-    "down_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 sha256:257650b23f56c765f8a3904b2e90f063fe63679b3509eb083807fe4f89524352
+oid sha256:0305b6512fb4a901896da1fe3530dcd08e96fefef5d7a23e2fc12cc832041da4
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b7bd8267e04cd7e2d1d2563e1fe6c53f129fa1d2a7b5f1d6da3f36eff59a2e
+oid sha256:9a04ea89e27d81bdfadd01a2e32a838b97dd199b922186e5ed62d456c997190b
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0c65cb830141b86197fa636bf0e1a9001559cdb8db09d6076de536139f58f0c
+oid sha256:a61cd905eba9e23c6467fd82a282993cf61bf1eb44ee77bd9b2a76971a581017
 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": 4.6975373160620544e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.000610679851088067,
+  "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": 4.6975373160620544e-05,
       "eval_loss": NaN,
-      "eval_runtime": 322.0674,
-      "eval_samples_per_second": 27.833,
-      "eval_steps_per_second": 13.916,
+      "eval_runtime": 322.5942,
+      "eval_samples_per_second": 27.787,
+      "eval_steps_per_second": 13.894,
       "step": 1
+    },
+    {
+      "epoch": 0.00023487686580310273,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00046975373160620547,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.00046975373160620547,
+      "eval_loss": NaN,
+      "eval_runtime": 323.35,
+      "eval_samples_per_second": 27.722,
+      "eval_steps_per_second": 13.861,
+      "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": 13355724570624.0,
+  "total_flos": 173624419418112.0,
   "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 sha256:5c2a067d266703e66e147956bec4aac17b7bf783aa195f6829cc00805d99b5e1
+oid sha256:5968d1d40b53c64eae707a242626993b4b230da8a6ecac774ded28f2712193d7
 size 6776