Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "o_proj",
-    "up_proj",
+    "v_proj",
     "down_proj",
+    "o_proj",
+    "gate_proj",
     "k_proj",
     "q_proj",
-    "v_proj",
-    "gate_proj"
+    "up_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:aa7aecee2dd9f26fc433c381fd5f3edc1d400c247a49ce3d62c168eac428b8f0
+oid sha256:55dc3608129b87e09a770ff9fbca542d26973af6dc4339f24b5c71a5d4b426a2
 size 1134088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92a77cc5b59dbc70d0dfb64c7b8c300179c3f5e57210f145f2d0b43fbaca4952
+oid sha256:97927b8a7128d62029666aff33c27699e389d3c0a6b9fe278dab4a61d80e8ef1
 size 608186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9df21ef7cde8684745ae29796094fa06bd5b1098cf5dc51f0f452bab5ba91fc2
+oid sha256:d704b9e24fa200b5a926459a5b6d9223dd8d23234c0ffd1e8506a0cdc12ea729
 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": 0.00042927666881305,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.00558059669456965,
+  "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": 0.00042927666881305,
       "eval_loss": 3.512066602706909,
-      "eval_runtime": 7.362,
-      "eval_samples_per_second": 133.252,
-      "eval_steps_per_second": 66.694,
+      "eval_runtime": 7.0523,
+      "eval_samples_per_second": 139.104,
+      "eval_steps_per_second": 69.623,
       "step": 1
+    },
+    {
+      "epoch": 0.0021463833440652502,
+      "grad_norm": 3.5879456996917725,
+      "learning_rate": 5e-05,
+      "loss": 3.5804,
+      "step": 5
+    },
+    {
+      "epoch": 0.0042927666881305004,
+      "grad_norm": 3.9762721061706543,
+      "learning_rate": 0.0001,
+      "loss": 3.4079,
+      "step": 10
+    },
+    {
+      "epoch": 0.0042927666881305004,
+      "eval_loss": 3.3738131523132324,
+      "eval_runtime": 6.9494,
+      "eval_samples_per_second": 141.163,
+      "eval_steps_per_second": 70.653,
+      "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": 2149752766464.0,
+  "total_flos": 27409347772416.0,
   "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:e92442341b2bed819b57fd723900445e1d78302c8706640dfb23a816dc1a5b70
+oid sha256:eec0b91f14735bc9de22648181807297e18fdfd4c1cf5cfd502b45d864a955d1
 size 6776