Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01d97f6629441cde537637c556aebbb5e8c292d20f39cf509240ed732adda0ab
+oid sha256:69dde06f34516b4b753d9050c72aba6206ce84295664e58de9cb6336cebd48bc
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b6de4428d8a1002e9f1a9a352b0e1b686f90a04cf27f85eccd6cc46c9921084
+oid sha256:f3af1a16b061b7f5b92de242f0ba33b08816aad4f6e949c0b8772ac9dafb2dcb
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c581a322ccb115680b65475b1eab69b643b5de15ce2c699864253548d637017f
+oid sha256:ad6b572d3f3f97e1976ed765ec9c9d9b243d8f30653f841246601f862868db7b
 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": 3.6378518484834707e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0004729207403028512,
+  "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": 3.6378518484834707e-05,
       "eval_loss": NaN,
-      "eval_runtime": 506.1995,
-      "eval_samples_per_second": 22.866,
-      "eval_steps_per_second": 11.434,
+      "eval_runtime": 492.9294,
+      "eval_samples_per_second": 23.482,
+      "eval_steps_per_second": 11.742,
       "step": 1
+    },
+    {
+      "epoch": 0.00018189259242417353,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.00036378518484834707,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.00036378518484834707,
+      "eval_loss": NaN,
+      "eval_runtime": 489.1132,
+      "eval_samples_per_second": 23.665,
+      "eval_steps_per_second": 11.834,
+      "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": 91853319831552.0,
+  "total_flos": 1262983147683840.0,
   "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:ed2aa29cc7a3d6c08e23292667e026240fc4e4ce1ec4933d4c61ca9d06b86408
+oid sha256:b924f47b1dab202c8562556d42c36c7f24636d3f5a2f3406b2f9d54e90d9d4c0
 size 6776