Training in progress, step 13, checkpoint

last-checkpoint/adapter_config.json

@@ -20,13 +20,13 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "gate_proj",
     "v_proj",
+    "down_proj",
+    "q_proj",
     "o_proj",
     "up_proj",
-    "q_proj",
-    "k_proj",
-    "down_proj",
-    "gate_proj"
+    "k_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:f1fb9f6d1dd61bc4d0f839fa95567bd5381fef3ee052d12dfc4def59fe0d514b
+oid sha256:cbca87e9f87d27183a77bea205d4f506ba415ec4b17d8ef356961eca25c454e8
 size 39256456

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2239b6e063e081042d0979d5b505d8083c39964ff9e3967b77bee1b94fbf91f
+oid sha256:c6c4104206296beba11fdffee8decaa21800e4fccb160ccb69106d402a1449d4
 size 20632826

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9006d347e550dc52ea749568b6042ad57e164ba0a0287ffcf44f2ec958ae167
+oid sha256:6d934d6f4dbc26dc5abbe7275398b8505b09114da73f9a91808ece5d3f915603
 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": 0.0029154518950437317,
-  "eval_steps": 1,
-  "global_step": 1,
+  "epoch": 0.037900874635568516,
+  "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": 0.0029154518950437317,
       "eval_loss": 1.0678009986877441,
-      "eval_runtime": 30.2441,
-      "eval_samples_per_second": 4.794,
-      "eval_steps_per_second": 2.414,
+      "eval_runtime": 29.9955,
+      "eval_samples_per_second": 4.834,
+      "eval_steps_per_second": 2.434,
       "step": 1
+    },
+    {
+      "epoch": 0.014577259475218658,
+      "grad_norm": 3.4854559898376465,
+      "learning_rate": 5e-05,
+      "loss": 1.1082,
+      "step": 5
+    },
+    {
+      "epoch": 0.029154518950437316,
+      "grad_norm": 0.5768101215362549,
+      "learning_rate": 0.0001,
+      "loss": 0.8683,
+      "step": 10
+    },
+    {
+      "epoch": 0.029154518950437316,
+      "eval_loss": 0.7050144672393799,
+      "eval_runtime": 16.5492,
+      "eval_samples_per_second": 8.762,
+      "eval_steps_per_second": 4.411,
+      "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": 97895558676480.0,
+  "total_flos": 1260405317959680.0,
   "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:a467695ee508e6ba6cb4e33d96b749c3942661eef75a64e16a6ff9adacbf96c5
+oid sha256:f67da69815b06f4e12d889ca297658c546af41bcb0ee806453ec7d9f9296d659
 size 6776