Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
     "v_proj",
     "o_proj",
-    "up_proj",
-    "down_proj",
-    "gate_proj",
-    "q_proj",
-    "k_proj"
+    "gate_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 sha256:1a78a7706803463c12d9ca4bb62dddee34b2f91d959bf642b578942447f5551d
+oid sha256:4da4128d3003d685b3f97b23d6b2cda336a5e534c2cdee68424c05163a2706b7
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:daae811aee3fbd7dad18bd5877ca3a5c2849b6be839add6f52fc37f5564fdc80
+oid sha256:04e7c7294f04e84cda276b521b27c4e27b0e4d9879c90726dd7a9db6e21ca7f1
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bb5dd3632f621f63027a71316dd458a1d0eb2cb6f6bdb9c2be6da1bb386cb19
+oid sha256:4479d8612262ecedc656e3fb719b965a26864f43306d791dee922d685b13b6f5
 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": 0.00010893542852474196,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0014161605708216455,
+  "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": 0.00010893542852474196,
       "eval_loss": 4.965454578399658,
-      "eval_runtime": 151.3032,
-      "eval_samples_per_second": 25.551,
-      "eval_steps_per_second": 12.776,
+      "eval_runtime": 146.1989,
+      "eval_samples_per_second": 26.443,
+      "eval_steps_per_second": 13.222,
       "step": 1
+    },
+    {
+      "epoch": 0.0005446771426237097,
+      "grad_norm": 2.617262125015259,
+      "learning_rate": 5e-05,
+      "loss": 4.4074,
+      "step": 5
+    },
+    {
+      "epoch": 0.0010893542852474195,
+      "grad_norm": 3.2852272987365723,
+      "learning_rate": 0.0001,
+      "loss": 4.7221,
+      "step": 10
+    },
+    {
+      "epoch": 0.0010893542852474195,
+      "eval_loss": 4.596639633178711,
+      "eval_runtime": 146.8778,
+      "eval_samples_per_second": 26.321,
+      "eval_steps_per_second": 13.161,
+      "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": 82004866498560.0,
+  "total_flos": 1066063264481280.0,
   "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 sha256:83644ae8dd61b37dce45f6e14d39f8a79e0d522931a2ac357e1c125344aefaf5
+oid sha256:b45f17fffd88e5135cb31d5cedd2028ada9e980c39e29c8171b98a64630e051b
 size 6776