Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,12 +20,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
     "down_proj",
     "o_proj",
-    "q_proj",
+    "v_proj",
     "k_proj",
     "gate_proj",
+    "q_proj",
     "up_proj"
   ],
   "task_type": "CAUSAL_LM",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef5392287baa62be7354d0d02b8835e3576c573c586e890e7f124ee5634df83f
+oid sha256:408d2e8f4245ab5f329fc35b9aa228b9f0ad880802243bf434d70b4b8c224355
 size 604317736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:719162ba9f3aa64f82ad460fd3e4afc5aa4abe9227b1ce7f001ccf061432e1bb
+oid sha256:b7dcd32071b18ec26170e9432369066d720c6bad49eac20fbbbf138eddace34c
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:792d1546ebf93af6d5f2808ada23d245a92ec7ea7130b1c43c380eba2e821f58
+oid sha256:d04ce38a4b1ebe155394d1cb2e43ba46dcd389805a0df7f2671ac2a395b23d6c
 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

@@ -1,27 +1,49 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005640953321111268,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.007333239317444648,
+  "eval_steps": 10,
+  "global_step": 13,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.0005640953321111268,
-      "eval_loss": 3.324923038482666,
-      "eval_runtime": 53.2376,
-      "eval_samples_per_second": 14.031,
-      "eval_steps_per_second": 7.025,
+      "eval_loss": 3.325026750564575,
+      "eval_runtime": 53.1499,
+      "eval_samples_per_second": 14.055,
+      "eval_steps_per_second": 7.037,
       "step": 1
+    },
+    {
+      "epoch": 0.0028204766605556338,
+      "grad_norm": 0.7551614046096802,
+      "learning_rate": 5e-05,
+      "loss": 3.3613,
+      "step": 5
+    },
+    {
+      "epoch": 0.0056409533211112676,
+      "grad_norm": 1.139972448348999,
+      "learning_rate": 0.0001,
+      "loss": 3.3191,
+      "step": 10
+    },
+    {
+      "epoch": 0.0056409533211112676,
+      "eval_loss": 3.2550063133239746,
+      "eval_runtime": 55.9381,
+      "eval_samples_per_second": 13.354,
+      "eval_steps_per_second": 6.686,
+      "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": 162873414254592.0,
+  "total_flos": 2117354385309696.0,
   "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 sha256:335c9cd643ed2ad17f2b803c8d03b15d7ac4d364fec3ab9b82eec14fe707f5d6
+oid sha256:a0af454ef177e13eb679188c8e463281b8201cf28b06aa3ed8efe6492a2a8b41
 size 6776