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",
     "up_proj",
     "k_proj",
-    "o_proj",
+    "v_proj",
     "down_proj",
-    "gate_proj"
+    "gate_proj",
+    "o_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 sha256:535f34be40354d68f64a8ea4e868dac0f99af06e4cde094a5d982357f0f7e806
+oid sha256:a841841b200b8c26e36e19e6cf16cd09f95d64eca403f154a16591045e4d8a87
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4810d102e98acbf75d4516fb95eb7a32f7fc5abe771d58f866e9471b71280507
+oid sha256:30ca88ecbe3b8e2bccabf86b0f8acca271ae3b0a07515ce2124870f9a70d81b0
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77d813df95ed5c5cb8c129d473a02cf923cf514e9f2baa1159356ec373c5aca4
+oid sha256:15160272ffddfe27c654df211d1192733c9457f0ce97b19578f9cd078fb647f8
 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": 2.591680704937152e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00033691849164182975,
+  "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": 2.591680704937152e-05,
       "eval_loss": 11.910928726196289,
-      "eval_runtime": 204.8118,
-      "eval_samples_per_second": 79.326,
-      "eval_steps_per_second": 39.666,
+      "eval_runtime": 201.7525,
+      "eval_samples_per_second": 80.529,
+      "eval_steps_per_second": 40.267,
       "step": 1
+    },
+    {
+      "epoch": 0.0001295840352468576,
+      "grad_norm": 5.612617492675781,
+      "learning_rate": 5e-05,
+      "loss": 11.9112,
+      "step": 5
+    },
+    {
+      "epoch": 0.0002591680704937152,
+      "grad_norm": 5.775433540344238,
+      "learning_rate": 0.0001,
+      "loss": 11.8222,
+      "step": 10
+    },
+    {
+      "epoch": 0.0002591680704937152,
+      "eval_loss": 11.683552742004395,
+      "eval_runtime": 201.5314,
+      "eval_samples_per_second": 80.618,
+      "eval_steps_per_second": 40.311,
+      "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": 65558544384.0,
+  "total_flos": 868650713088.0,
   "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:dfac766eb348f50a26e616ad789456be01af4e63fcda1d2146bec535bf7f43b0
+oid sha256:fafb2fe72ae5321f9ec45b388a3d0d2461d718d6ea4adee0facfeaeb28db9357
 size 6776