Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "q_proj",
+    "k_proj",
     "o_proj",
     "down_proj",
-    "v_proj",
     "gate_proj",
-    "up_proj",
-    "k_proj"
+    "q_proj",
+    "v_proj",
+    "up_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:fd159528db20aff1ddb8156190759c42093b78456dace82da3c383a4ec46c646
+oid sha256:c172e63c865bb0bbd0c610d68b6a821d0a63fbdc51b20752fc36799506522b03
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ae9922aba3c4534d28552e415c8ac1ff3f1634471f4c6e62ed2d77c64af9305
+oid sha256:15497b6ccc1f04d3826a1b323fc6e3cac20f25733722c8eccea24411f15f8105
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
+oid sha256:c5d58a77b7e7abf4f99c2b253ea7d0012eb34f29163a114391e783f09fc5bd6f
 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": 4.3481096593256084e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0005652542557123291,
+  "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": 4.3481096593256084e-05,
       "eval_loss": 1.4841827154159546,
-      "eval_runtime": 769.8733,
-      "eval_samples_per_second": 12.579,
-      "eval_steps_per_second": 6.289,
+      "eval_runtime": 769.5249,
+      "eval_samples_per_second": 12.584,
+      "eval_steps_per_second": 6.292,
       "step": 1
+    },
+    {
+      "epoch": 0.0002174054829662804,
+      "grad_norm": 0.3885715901851654,
+      "learning_rate": 5e-05,
+      "loss": 1.4751,
+      "step": 5
+    },
+    {
+      "epoch": 0.0004348109659325608,
+      "grad_norm": 0.3961728513240814,
+      "learning_rate": 0.0001,
+      "loss": 1.3895,
+      "step": 10
+    },
+    {
+      "epoch": 0.0004348109659325608,
+      "eval_loss": 1.4605967998504639,
+      "eval_runtime": 782.2609,
+      "eval_samples_per_second": 12.38,
+      "eval_steps_per_second": 6.19,
+      "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": 164316422602752.0,
+  "total_flos": 2218271705137152.0,
   "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 sha256:76071a4afc89eecaf49a0e2eae801fc45aff04a571d9324e4dcf2210eb036cc4
+oid sha256:0fa604057e15260371d73517f07343e6e55da9f85862fdeffc28d49854fa9cf2
 size 6776