Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
-    "o_proj",
-    "gate_proj",
+    "k_proj",
     "q_proj",
+    "down_proj",
     "v_proj",
-    "k_proj",
-    "up_proj"
+    "up_proj",
+    "gate_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 sha256:688e1418b5d95b1c3239f9893e6c1004ca417cdadb0ef8b386931682cd7beaf5
+oid sha256:2c920e6366b74a76e09d2ca519b1c8742da7f0f45f6b719f42dd2ec3937aac3f
 size 27024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04f502a0a37b6f89f658de0b6257ac6bb16424fc0bd3a0b13a688fb3f9c772f8
+oid sha256:35cc19a483db3c29d30376610cbd1d8604b0294d465abff849e53a3d752792d0
 size 63974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e7b432d4c1390a80984e093813a079e02823704a7187bbae0ecafb3a9eb8384
+oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
 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": 0.00014989132878662968,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.001948587274226186,
+  "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": 0.00014989132878662968,
       "eval_loss": 10.374155044555664,
-      "eval_runtime": 13.0779,
-      "eval_samples_per_second": 214.867,
-      "eval_steps_per_second": 107.433,
+      "eval_runtime": 12.6184,
+      "eval_samples_per_second": 222.691,
+      "eval_steps_per_second": 111.346,
       "step": 1
+    },
+    {
+      "epoch": 0.0007494566439331485,
+      "grad_norm": 0.039108939468860626,
+      "learning_rate": 5e-05,
+      "loss": 10.3732,
+      "step": 5
+    },
+    {
+      "epoch": 0.001498913287866297,
+      "grad_norm": 0.04206083342432976,
+      "learning_rate": 0.0001,
+      "loss": 10.3743,
+      "step": 10
+    },
+    {
+      "epoch": 0.001498913287866297,
+      "eval_loss": 10.373963356018066,
+      "eval_runtime": 12.6553,
+      "eval_samples_per_second": 222.042,
+      "eval_steps_per_second": 111.021,
+      "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": 12930908160.0,
+  "total_flos": 168101806080.0,
   "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:ee15ef0d4b7854b8c61262dd35fec3d3c23cf2e5275d4813c600ca9316d20bc0
+oid sha256:a9ae95aefcfd904b0061f40d07b05c27300af5e86d67d0fce245c4d2081751d7
 size 6776