Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

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

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1ec4213ca99b4aa7e7d06c734d90dd4370ddf1f6f7d05a5f6b93a517b8dd8a8
+oid sha256:0d91688ce3768a69954db44c8c1acdc02717f34c575763b1b145b45153be92ca
 size 17640136

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b7bd8267e04cd7e2d1d2563e1fe6c53f129fa1d2a7b5f1d6da3f36eff59a2e
+oid sha256:9a04ea89e27d81bdfadd01a2e32a838b97dd199b922186e5ed62d456c997190b
 size 9568884

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a954ed0e5199298ae76484c0a66e4d5dad334c9034860208823f77d7f555120
+oid sha256:17f459dc0ff0b8de89db88bfdf5bedfd0c0ef4c576938a039c8c06b9e448f916
 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": 7.029259291802126e-05,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.0009138037079342764,
+  "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": 7.029259291802126e-05,
       "eval_loss": NaN,
-      "eval_runtime": 226.2732,
-      "eval_samples_per_second": 26.472,
-      "eval_steps_per_second": 13.236,
+      "eval_runtime": 224.3798,
+      "eval_samples_per_second": 26.696,
+      "eval_steps_per_second": 13.348,
       "step": 1
+    },
+    {
+      "epoch": 0.00035146296459010633,
+      "grad_norm": NaN,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 5
+    },
+    {
+      "epoch": 0.0007029259291802127,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.0007029259291802127,
+      "eval_loss": NaN,
+      "eval_runtime": 222.0838,
+      "eval_samples_per_second": 26.972,
+      "eval_steps_per_second": 13.486,
+      "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": 15581678665728.0,
+  "total_flos": 175850373513216.0,
   "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 sha256:7fffc132c397e9c0f8e8f2fc1e4cb1e12095fcbcd9f8e025b89e16bf822d3334
+oid sha256:ee3a417ce5b0807f7190e52620a982c03fcc170d0cfe618d39bb323c76dcf5c9
 size 6776