Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -21,12 +21,12 @@
   "revision": null,
   "target_modules": [
     "o_proj",
-    "q_proj",
+    "k_proj",
     "v_proj",
-    "up_proj",
     "gate_proj",
-    "k_proj",
-    "down_proj"
+    "up_proj",
+    "down_proj",
+    "q_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:e9d51d2804e9eb66c99e0663ca54fdbf7e2197f70fba2a201c59c81b983e8fbe
+oid sha256:325cb32d5f05c80711a58279e1bc9150fafff207ff357968092e92b82e580841
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b6de4428d8a1002e9f1a9a352b0e1b686f90a04cf27f85eccd6cc46c9921084
+oid sha256:f3af1a16b061b7f5b92de242f0ba33b08816aad4f6e949c0b8772ac9dafb2dcb
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:963c6079547089ef3f2e4bbb56358af00a798aecd87788d715d499ceb6b4e90c
+oid sha256:0b1c0cdaa630492fcf9e05c59dd863c4d360e74eb26a4f7750b500741c15d6bb
 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": 0.004246284501061571,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.055201698513800426,
+  "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": 0.004246284501061571,
       "eval_loss": NaN,
-      "eval_runtime": 6.2732,
-      "eval_samples_per_second": 15.941,
-      "eval_steps_per_second": 7.97,
+      "eval_runtime": 6.0962,
+      "eval_samples_per_second": 16.404,
+      "eval_steps_per_second": 8.202,
       "step": 1
+    },
+    {
+      "epoch": 0.021231422505307854,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.04246284501061571,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.04246284501061571,
+      "eval_loss": NaN,
+      "eval_runtime": 5.2518,
+      "eval_samples_per_second": 19.041,
+      "eval_steps_per_second": 9.521,
+      "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": 114816649789440.0,
+  "total_flos": 1584469767094272.0,
   "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 sha256:76485f03d1b1a71365f61d17b30cffee03db32d5a3b087fc7c3bba560a9bf5a0
+oid sha256:cfb7697513410ad601232616536ac4106ab8b691e9be42092a0361be40e27692
 size 6776