Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8139e9640ee0864a375706fd7f9570c0c4fad2fd41156938370a186a454086f
+oid sha256:bd49d25e55f37306375c7a1b28f0340b1324e3018bfd72063f01f3ae8ddd2bd6
 size 100059752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85579c5c6724ebf549b29c238a0f11034182d917d5dabeb9269a3c46809ef9b0
+oid sha256:2864e4ad8f83b34c9e6a6fbbf0e187081e091f50037471755dae6ef5eaf888da
 size 51244020

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5c629d4455efff92a03f89d92e6c8ae03a0b4377f56fcd62a3bbf69d0746550
+oid sha256:0f4a7095e2c9a92fc4e9e7ec1485dbdbe05d9de13f2f18e978e6e1e728b72450
 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": 4.669515070859891e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0006070369592117859,
+  "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": 4.669515070859891e-05,
       "eval_loss": 3.852412462234497,
-      "eval_runtime": 1236.3067,
-      "eval_samples_per_second": 7.294,
-      "eval_steps_per_second": 3.647,
+      "eval_runtime": 1236.6296,
+      "eval_samples_per_second": 7.292,
+      "eval_steps_per_second": 3.646,
       "step": 1
+    },
+    {
+      "epoch": 0.00023347575354299455,
+      "grad_norm": 4.815019607543945,
+      "learning_rate": 5e-05,
+      "loss": 3.556,
+      "step": 5
+    },
+    {
+      "epoch": 0.0004669515070859891,
+      "grad_norm": 6.179628372192383,
+      "learning_rate": 0.0001,
+      "loss": 3.0412,
+      "step": 10
+    },
+    {
+      "epoch": 0.0004669515070859891,
+      "eval_loss": 2.0145978927612305,
+      "eval_runtime": 1246.3355,
+      "eval_samples_per_second": 7.236,
+      "eval_steps_per_second": 3.618,
+      "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": 191109141626880.0,
+  "total_flos": 2484418841149440.0,
   "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 sha256:5baf6a0bafcec0a77aa2cd1ee204d112d10d4c16352bd7d4443f2f2a31e22517
+oid sha256:e2171ad6e67a4cf3c4923fb570e5915036f72dc38ed88eef69de39a539731ea2
 size 6776